{"slug":"gaasher-exploratory-autoresearch","name":"exploratory-autoresearch","description":"Use when the user wants an autonomous ML research loop that explores the space broadly rather than hill-climbing one approach. A temperature scheduler replaces the usual hypothesis step: it forces several wild, diverse swings (full rewrites, different architectures/regimes) early, then enters an adaptive phase that picks swing / merge / exploit per iteration — with a hard stagnation guard that bans further small-step exploits once they run too long, forcing a pivot back to a swing or merge. Tracks an approaches.md registry and a move_type per iteration; analyses every run before the next move. One change per iteration; loops forever until interrupted. Not for the standard analysis-first ml-autoresearch (which lets analysis alone choose each change), one-off training runs, or sweeps.","long_description":"---\nname: exploratory-autoresearch\ndescription: >\n Use when the user wants an autonomous ML research loop that explores the space broadly rather than\n hill-climbing one approach. A temperature scheduler replaces the usual hypothesis step: it forces\n several wild, diverse swings (full rewrites, different architectures/regimes) early, then enters an\n adaptive phase that picks swing / merge / exploit per iteration — with a hard stagnation guard that\n bans further small-step exploits once they run too long, forcing a pivot back to a swing or merge.\n Tracks an approaches.md registry and a move_type per iteration; analyses every run before the next\n move. One change per iteration; loops forever until interrupted. Not for the standard analysis-first\n ml-autoresearch (which lets analysis alone choose each change), one-off training runs, or sweeps.\ncompatibility: Requires Python 3.9+\nmetadata:\n version: \"0.1.0\"\n---\n\n# Exploratory Autoresearch Loop\n\nThis loop runs hot. Like the standard `ml-autoresearch`, every experiment is followed by a diagnostic\nanalysis pass. **Unlike** it, the *type* of change at each iteration is set by a **temperature\nscheduler**, not the agent's intuition: it forces wide, diverse swings early (full rewrites,\nfundamentally different architectures and training regimes), then drops into an adaptive phase that\nchooses between **swing** (a fresh wild approach), **merge** (combine two registered approaches), or\n**exploit** (a focused tweak of the best). A **stagnation guard** bans exploit once it has run\n`` times in a row, forcing a pivot back to swing or merge so the loop never gets\nstuck hill-climbing. The feedback signal is `` read from the run log; an `approaches.md`\nregistry and a `move_type` per iteration are what make the scheduler work.\n\nYou are the researcher. Do not pause to ask for permission once the loop is running.\n\n## When to use\nUse for an open-ended ML campaign where you want forced breadth before refinement — the scheduler\nguarantees you sample several distinct families before converging, and the stagnation guard prevents\nendless small steps. Default to ` = 3` and ` = 3`; raise ``\nfor wider initial exploration. Not for the standard analysis-first `ml-autoresearch` (use that when you\nwant the analysis alone to drive each change, with no forced-swing scheduler), not for a single training\nrun or a fixed sweep, and not for tasks with no measurable scalar metric.\n\n## Setup\n**Resolve bindings interactively.** If `loop.run.yaml` exists in the working dir, load it, confirm the\nvalues in one line, and skip to the loop. Otherwise: on Claude Code (the `AskUserQuestion` tool is\navailable — record `` = `claude-code`) infer a likely value for each binding from the project and\npresent it as the recommended option; on other hosts (`` = `other`) ask each as a quoted plain-text\nprompt. Then write `loop.run.yaml` (format: `examples/run.example.yaml`) and **confirm every value with\nthe user before creating any other files.** For `branches` strategy, create\n`git checkout -b autoresearch/` (tag from today's date; branch must not exist). For `time`\ngating, write `/run_with_timeout.sh` (`timeout $(( * 60 )) \"$@\"`) and\nuse it as the run command, hard-killing at `2 × ` min; for `epochs`, patch the epoch cap in an\n`` file.\n\n| binding | meaning | default | how to infer |\n|---|---|---|---|\n| `` / `` | scalar to optimize + `minimize`/`maximize` | — | scan editable files + README for metric names |\n| `` / `` | command that runs one experiment end to end | — | `pyproject.toml` / `.venv` / README |\n| `` | files fair game to edit (never the eval harness) | — | model / config / train scripts; exclude data, logs, env, harness |\n| `` | where snapshots + ledgers live | `./sandbox` | next to the editable files |\n| `` | `snapshots` or `branches` | `snapshots` | is the working dir a clean git repo? |\n| `` / `` | `time` (min) or `epochs`, and the limit | — | existing time/epoch settings in config |\n| `` | forced wild swings before adaptive mode | 3 (3–5) | wider = more initial breadth |\n| `` | max consecutive exploits before a forced pivot | 3 | — |\n\n**FILE EDIT GUARD**: before touching any file at any point — setup or loop — confirm it is in\n``, because everything else is read-only ground truth (the eval harness defines\n``). No exceptions.\n\n### Initialise the sandbox\nCreate the layout and write the ledger headers:\n```\n/\n├── loop.run.yaml ← resolved bindings (written now)\n├── results.tsv ← experiment ledger, header only (written now)\n├── approaches.md ← registry of every distinct approach (header only, written now)\n└── iter1/ ← created at loop start\n```\n`results.tsv` header (tab-separated; `move_type` ∈ {`swing`, `merge`, `exploit`}):\n```\niter\t\tstatus\tmove_type\tanalysis_summary\tdescription\n```\n`approaches.md` header: `# Approach Registry` plus a one-line note that the merge step consults it to\nfind complementary approaches to combine.\n\n## The loop (LOOP FOREVER — until interrupted)\nIteration 1 is always the **unmodified baseline** (it does not count as a swing): skip move-selection and\nchange-planning, but still run the **mandatory analysis** — it is the first empirical anchor iteration 2\nbuilds on. Everything in `` is fair game (architecture, optimizer, hyperparameters, data\npipeline, loss, init, eval); on swings especially, full rewrites are encouraged. The only constraints are\nthat the code runs and finishes within ``. **Epoch efficiency is part of the objective** — a\nchange that reaches the same score in fewer effective steps is a real win. **Simplicity criterion**: all\nelse equal, simpler is better — a 0.001 gain that adds 20 lines of hacky code is not worth it; a 0.001\ngain (or an equal metric) from *deleting* code is a `keep`.\n\nThe scheduler keeps two counters in memory across iterations: **`swings_taken`** (total swing iterations,\nexcludes the baseline) and **`consecutive_exploit`** (exploits since the last swing/merge; resets to 0 on\nany swing or merge).\n\nCopy this checklist each iteration and tick items off:\n- [ ] **1. Look at the state.** *branches*: `git log --oneline -5`. *snapshots*: confirm `iter/`\n doesn't exist. Read iter N-1's analysis summary and the two counters.\n- [ ] **2. Pick `move_type`** (iteration 1: SKIP — baseline). Apply the scheduler below, then record the\n move before touching any file.\n- [ ] **3. Form the hypothesis** (iteration 1: SKIP). State the move and why (cite the rule or the\n analysis), what you will do, and which `` it touches. See **The three moves**.\n- [ ] **4. Snapshot / commit, then apply the change.** *snapshots*: create\n `iter/{code_snapshot,analysis,results}/`, copy every `` into `code_snapshot/`,\n copy `loop.run.yaml` to `iter/`, then apply. *branches*: apply, then\n `git commit -am \": \"`.\n- [ ] **5. Run the experiment**, redirecting everything (never `tee`):\n ` > /iter/ 2>&1` (or `run_with_timeout.sh` when time-gated).\n If it overruns, kill it and treat as a crash.\n- [ ] **6. Read the metric**: `grep '^:' /iter/`. If empty,\n `tail -n 50 `, read the trace, attempt one trivial fix (typo/import); if fundamentally\n broken, log `crash` and continue.\n- [ ] **7. Analyse the results** — MANDATORY, produces real artifact files. See **Analysing**.\n- [ ] **8. Update `approaches.md`** (swing and merge moves only). See **The registry**.\n- [ ] **9. Log to `results.tsv`** (untracked — never commit). See **Ledger**.\n- [ ] **10. Keep or revert** (the change ran this iteration). Improved per `` → `keep`,\n update current-best. Equal/worse/crash → `discard`/`crash`; *branches* `git reset --hard HEAD~1`,\n *snapshots* restore `` from `iter/code_snapshot/`. Apply the simplicity criterion\n before logging `discard`. On a crash/OOM, fix with the *minimal* change that preserves the intent\n (OOM → smaller batch + grad-accum to hold effective batch) — never mutate the experiment.\n- [ ] **11. Update counters** (below) and go to step 1.\n\n### The scheduler (step 2 — this is the loop's identity)\nFollow the rules **exactly, in order** — they are hard constraints, not suggestions:\n```\nIF iter == 1 → baseline (run unmodified; no move)\nELIF swings_taken < → swing (forced exploration)\nELIF consecutive_exploit >= → swing OR merge (forced pivot — exploit BANNED)\nELSE → agent chooses: swing / merge / exploit\n```\nOn the free `ELSE` branch, let iter N-1's analysis decide:\n- **swing** if the current family has a fundamental ceiling — e.g. all top results share a failure mode.\n- **merge** if two+ `approaches.md` entries have distinct, non-overlapping strengths (prefer parents that\n changed *different axes* — they combine additively rather than interfere).\n- **exploit** if the current best has obvious analysis-suggested headroom not needing a new architecture.\n\n### Counter update (step 11)\n```\nif move_type in {swing, merge}: swings_taken += 1 (swing only); consecutive_exploit = 0\nelif move_type == exploit: consecutive_exploit += 1\n```\n\n### The three moves (step 3)\n- **Swing** — *fundamentally* different from every previous swing (not a tweak; the diff should look\n obviously different from the current best). Most people swing on architecture by reflex — fight that.\n These axes are equally valid and underexplored: **architectural family** (how information flows, depth\n vs width, skip connections, local vs global); **initialization** (magnitude-based, structure-preserving,\n input-statistics-driven, sparse — different early dynamics); **data pipeline** (ordering, sampling,\n determinism, coverage of the view space — not just augmentation flavours); **per-component LR\n decoupling** (early/late layers, norms, biases, heads each have their own optimal step); **evaluation**\n (single pass, multi-view, checkpoint averaging, calibration); **objective** (loss shape, target\n sharpness, auxiliary/consistency signals). A genuine swing explores one of these in a way not yet tried.\n- **Merge** — select two+ entries from `approaches.md` and name what is taken from each; the result is a\n new approach that is not a minor variant of either parent. Prefer components from *different axes*.\n- **Exploit** — a targeted, focused change to the current best, grounded in a specific analysis finding.\n One or two things at a time; **decouple the axes** (test a new optimizer and a new LR as separate\n iterations so you know which caused the result). Never a different architecture.\n\n### Analysing (step 7 — MANDATORY; produces real artifacts)\nThis is the spine that feeds the next move. Run whatever analysis most increases your understanding of\n*why* this result happened. Every analysis script goes in `iter/analysis/`; every output (plots, CSVs,\ntext) goes in `iter/results/`, redirecting stdout there. Do not proceed until the results exist —\nanalysis that wrote no file did not happen. Dimensions to draw from (choose what fits): gradient\nnorms/flow, activation stats/saturation, embeddings (PCA/CKA/collapse), error & confusion analysis, loss\ndynamics & **headroom** (was it still improving at cutoff?), weight/parameter stats, data profiling\n(often the highest-yield), compute profiling.\n\nWrite a concise **analysis summary** (3–8 bullets): what you examined, the single most important finding,\nand what it implies for the next move (whe","tagline":"Use when the user wants an autonomous ML research loop that explores the space broadly rather than hill-climbing one approach. A temperature scheduler replaces the usual hypothesis step: it forces several wild, diverse swings (full rewrites, different architectures/regimes) early","category":"research","tags":["agent-skill"],"author":"gaasher","verified":false,"attribution":{"status":"registry_indexed","statusLabel":"Registry indexed","shortLabel":"REGISTRY INDEXED","sourceLabel":"github fast track","sourceDetail":"gaasher/Agent-Loop-Skills","creatorName":"gaasher","creatorUrl":"https://github.com/gaasher","sourceUrl":"https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/exploratory-autoresearch","indexedBy":"OpenAgentSkill community index","claimUrl":"https://www.openagentskill.com/skills/gaasher-exploratory-autoresearch#claim-this-skill","claimCta":"Claim this skill","trustNote":"This listing was indexed from public sources and is not marked official until a maintainer claim is approved.","publicNote":"Attribution links to the public repository or creator profile. Creators can claim the listing to update ownership signals."},"stats":{"stars":163,"forks":19,"verified_installs":0,"successful_runs":0,"total_outcomes":0,"rating":0,"review_count":0,"quality_score":35.6},"quality":{"score":63,"tier":"promising","label":"Promising","summary":"Useful candidate, but compare it with alternatives before adopting.","signals":[{"label":"GitHub stars","value":"163","tone":"neutral"},{"label":"Freshness","value":"2mo ago","tone":"positive"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"MIT","tone":"neutral"}],"warnings":[]},"trust":{"version":"trust-score-v5","score":67,"base_score":75,"outcome_confidence":0,"tier":"review","label":"Sandbox only","summary":"Useful candidate with missing or mixed trust signals. Keep it in an isolated workspace until the outcome loop proves task fit.","recommendedAction":"Run only in a sandbox and compare close alternatives before using it for real work.","decision":{"install_policy":"human_review_before_install","auto_install_allowed":false,"human_review_required":true,"sandbox_first":true,"agent_action":"Compare alternatives before installing.","reasoning":["67/100 Trust Score v5","75/100 Trust Score v4 baseline","Needs more real agent outcomes before unattended install","Install path is available","Review before production"],"review_required_when":["The workspace contains production secrets, payments, private customer data, or irreversible actions.","The install command requests shell, network, credential, database, or broad filesystem access.","Outcome evidence is missing, recently failed, or required human review.","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"]},"dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":62,"weight":0.13,"status":"info","detail":"163 GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":57,"weight":0.08,"status":"warn","detail":"163 stars, 19 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":88,"weight":0.14,"status":"pass","detail":"2mo since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"MIT"},{"id":"documentation","label":"README/SKILL.md completeness","score":86,"weight":0.14,"status":"pass","detail":"Metadata includes enough usage and workflow context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":72,"weight":0.12,"status":"info","detail":"credential or environment access"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add gaasher/Agent-Loop-Skills --skill exploratory-autoresearch"},{"id":"install_safety","label":"Install command safety","score":92,"weight":0.1,"status":"pass","detail":"standard package or runtime install path"},{"id":"permission_surface","label":"Permission surface","score":36,"weight":0.07,"status":"fail","detail":"secrets or environment access, shell or command execution"},{"id":"repository","label":"Repository evidence","score":86,"weight":0.04,"status":"pass","detail":"https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/exploratory-autoresearch"},{"id":"review_status","label":"Review status","score":88,"weight":0.05,"status":"pass","detail":"AI review data available"},{"id":"agent_outcomes","label":"Agent Proven outcomes","score":54,"weight":0.13,"status":"info","detail":"No agent outcome data yet"}],"checks":[{"status":"info","label":"GitHub adoption","detail":"163 GitHub stars"},{"status":"warn","label":"Stars/forks activity","detail":"163 stars, 19 forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"2mo since push"},{"status":"pass","label":"License clarity","detail":"MIT"},{"status":"pass","label":"README/SKILL.md completeness","detail":"Metadata includes enough usage and workflow context"},{"status":"info","label":"Dependency/runtime risk","detail":"credential or environment access"},{"status":"pass","label":"Install availability","detail":"npx skills add gaasher/Agent-Loop-Skills --skill exploratory-autoresearch"},{"status":"pass","label":"Install command safety","detail":"standard package or runtime install path"},{"status":"fail","label":"Permission surface","detail":"secrets or environment access, shell or command execution"},{"status":"pass","label":"Repository evidence","detail":"https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/exploratory-autoresearch"},{"status":"pass","label":"Review status","detail":"AI review data available"},{"status":"info","label":"Agent Proven outcomes","detail":"No agent outcome data yet"},{"status":"warn","label":"Ownership","detail":"No approved owner claim yet"},{"status":"info","label":"OpenAgentSkill usage","detail":"No local usage activity yet"},{"status":"info","label":"Agent outcomes","detail":"No agent outcome data yet"}],"strengths":["AI review approved","Install path is available","Repository evidence is available","Recently maintained repository","Install command has no obvious high-risk pattern","Outcome loop is ready but needs first real agent run"],"warnings":["Financial research output is not financial advice; require human review before any live investment decision.","Quality score needs review","Permission surface needs review: secrets or environment access, shell or command execution","Stars/forks activity: 163 stars, 19 forks; issue activity unavailable in current metadata","Permission surface: secrets or environment access, shell or command execution","No real agent outcome reports yet","Human review required before unattended installation"],"evidence":{"stars":"163 GitHub stars","repoActivity":"163 stars, 19 forks","lastPushed":"2mo since push","license":"MIT","repository":"https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/exploratory-autoresearch","install":"npx skills add gaasher/Agent-Loop-Skills --skill exploratory-autoresearch","installSafety":"standard package or runtime install path","permissionSurface":"secrets or environment access, shell or command execution","documentation":"Strong README/SKILL.md context","agentOutcomes":"No agent outcome data yet","agentProvenScore":0,"outcomeConfidence":"0%","installPolicy":"human_review_before_install"},"installReadiness":{"ready":true,"command":"npx skills add gaasher/Agent-Loop-Skills --skill exploratory-autoresearch","policy":"human_review_before_install","label":"Human review before install","notes":["Install path is available","Repository evidence is available","License is declared","No Agent Proven outcome evidence yet","2mo since push","Financial domain: human review is required before use in a live investment workflow.","Trust Score v5 requires review or sandbox-only use before install."]},"agentCompatibility":["Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["Financial research output is not financial advice; require human review before any live investment decision.","Quality score needs review","Permission surface needs review: secrets or environment access, shell or command execution","Stars/forks activity: 163 stars, 19 forks; issue activity unavailable in current metadata","Permission surface: secrets or environment access, shell or command execution"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":false,"sandboxRequired":true,"policy":"human_review_before_install","reason":"Compare alternatives before installing."},"outcome_loop":{"version":"openagentskill-agent-outcome-v4","required_after_install":true,"endpoint":"/api/agent/outcome","method":"POST","event_id_source":"feedback.event_id, install_receipt.resolve_event_id, or decision_packet.outcome_feedback.event_id","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"required_fields":["event_id","skill_slug","task"],"quality_fields":["task_success","output_quality","error_type","human_review_required","used_in_production","workspace","evidence_url","time_to_useful_ms","source_version"],"ranking_inputs_updated":["Trust Score v5 outcome confidence","Agent Proven Score","Resolve ranking task-fit evidence","Skill detail machine-readable metadata","Outcome leaderboard"]},"agent_contract":{"suited_tasks":["research","agent-skill"],"suited_agents":["Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"install_command":"npx skills add gaasher/Agent-Loop-Skills --skill exploratory-autoresearch","trust_score":67,"trust_version":"trust-score-v5","risk_level":"medium","do_not_use_when":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace","Autonomous investment, trading, tax, or suitability decisions without a qualified human review"],"before_install":["Read the audit page and machine-readable metadata.","Confirm the install command, license, and permission surface fit the workspace.","Get explicit human approval or choose an alternative before installing."],"after_run":["Report the outcome to /api/agent/outcome using the resolve event id.","Include output_quality, workspace, human_review_required, and evidence_url when available.","Re-resolve before broad production rollout."]},"bestFor":["research","agent-skill"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace","Autonomous investment, trading, tax, or suitability decisions without a qualified human review"],"knownRisks":["Financial research output is not financial advice; require human review before any live investment decision.","Quality score needs review","Permission surface needs review: secrets or environment access, shell or command execution","Stars/forks activity: 163 stars, 19 forks; issue activity unavailable in current metadata","Permission surface: secrets or environment access, shell or command execution"],"backward_compatible":{"trust_score_v4":{"version":"trust-score-v4","score":75,"tier":"strong","label":"Strong shortlist","summary":"Good trust signals with a few areas worth checking before rollout."}}},"trust_score_v5":{"version":"trust-score-v5","score":67,"base_score":75,"outcome_confidence":0,"tier":"review","label":"Sandbox only","summary":"Useful candidate with missing or mixed trust signals. Keep it in an isolated workspace until the outcome loop proves task fit.","recommendedAction":"Run only in a sandbox and compare close alternatives before using it for real work.","decision":{"install_policy":"human_review_before_install","auto_install_allowed":false,"human_review_required":true,"sandbox_first":true,"agent_action":"Compare alternatives before installing.","reasoning":["67/100 Trust Score v5","75/100 Trust Score v4 baseline","Needs more real agent outcomes before unattended install","Install path is available","Review before production"],"review_required_when":["The workspace contains production secrets, payments, private customer data, or irreversible actions.","The install command requests shell, network, credential, database, or broad filesystem access.","Outcome evidence is missing, recently failed, or required human review.","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"]},"dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":62,"weight":0.13,"status":"info","detail":"163 GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":57,"weight":0.08,"status":"warn","detail":"163 stars, 19 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":88,"weight":0.14,"status":"pass","detail":"2mo since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"MIT"},{"id":"documentation","label":"README/SKILL.md completeness","score":86,"weight":0.14,"status":"pass","detail":"Metadata includes enough usage and workflow context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":72,"weight":0.12,"status":"info","detail":"credential or environment access"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add gaasher/Agent-Loop-Skills --skill exploratory-autoresearch"},{"id":"install_safety","label":"Install command safety","score":92,"weight":0.1,"status":"pass","detail":"standard package or runtime install path"},{"id":"permission_surface","label":"Permission surface","score":36,"weight":0.07,"status":"fail","detail":"secrets or environment access, shell or command execution"},{"id":"repository","label":"Repository evidence","score":86,"weight":0.04,"status":"pass","detail":"https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/exploratory-autoresearch"},{"id":"review_status","label":"Review status","score":88,"weight":0.05,"status":"pass","detail":"AI review data available"},{"id":"agent_outcomes","label":"Agent Proven outcomes","score":54,"weight":0.13,"status":"info","detail":"No agent outcome data yet"}],"checks":[{"status":"info","label":"GitHub adoption","detail":"163 GitHub stars"},{"status":"warn","label":"Stars/forks activity","detail":"163 stars, 19 forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"2mo since push"},{"status":"pass","label":"License clarity","detail":"MIT"},{"status":"pass","label":"README/SKILL.md completeness","detail":"Metadata includes enough usage and workflow context"},{"status":"info","label":"Dependency/runtime risk","detail":"credential or environment access"},{"status":"pass","label":"Install availability","detail":"npx skills add gaasher/Agent-Loop-Skills --skill exploratory-autoresearch"},{"status":"pass","label":"Install command safety","detail":"standard package or runtime install path"},{"status":"fail","label":"Permission surface","detail":"secrets or environment access, shell or command execution"},{"status":"pass","label":"Repository evidence","detail":"https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/exploratory-autoresearch"},{"status":"pass","label":"Review status","detail":"AI review data available"},{"status":"info","label":"Agent Proven outcomes","detail":"No agent outcome data yet"},{"status":"warn","label":"Ownership","detail":"No approved owner claim yet"},{"status":"info","label":"OpenAgentSkill usage","detail":"No local usage activity yet"},{"status":"info","label":"Agent outcomes","detail":"No agent outcome data yet"}],"strengths":["AI review approved","Install path is available","Repository evidence is available","Recently maintained repository","Install command has no obvious high-risk pattern","Outcome loop is ready but needs first real agent run"],"warnings":["Financial research output is not financial advice; require human review before any live investment decision.","Quality score needs review","Permission surface needs review: secrets or environment access, shell or command execution","Stars/forks activity: 163 stars, 19 forks; issue activity unavailable in current metadata","Permission surface: secrets or environment access, shell or command execution","No real agent outcome reports yet","Human review required before unattended installation"],"evidence":{"stars":"163 GitHub stars","repoActivity":"163 stars, 19 forks","lastPushed":"2mo since push","license":"MIT","repository":"https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/exploratory-autoresearch","install":"npx skills add gaasher/Agent-Loop-Skills --skill exploratory-autoresearch","installSafety":"standard package or runtime install path","permissionSurface":"secrets or environment access, shell or command execution","documentation":"Strong README/SKILL.md context","agentOutcomes":"No agent outcome data yet","agentProvenScore":0,"outcomeConfidence":"0%","installPolicy":"human_review_before_install"},"installReadiness":{"ready":true,"command":"npx skills add gaasher/Agent-Loop-Skills --skill exploratory-autoresearch","policy":"human_review_before_install","label":"Human review before install","notes":["Install path is available","Repository evidence is available","License is declared","No Agent Proven outcome evidence yet","2mo since push","Financial domain: human review is required before use in a live investment workflow.","Trust Score v5 requires review or sandbox-only use before install."]},"agentCompatibility":["Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["Financial research output is not financial advice; require human review before any live investment decision.","Quality score needs review","Permission surface needs review: secrets or environment access, shell or command execution","Stars/forks activity: 163 stars, 19 forks; issue activity unavailable in current metadata","Permission surface: secrets or environment access, shell or command execution"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":false,"sandboxRequired":true,"policy":"human_review_before_install","reason":"Compare alternatives before installing."},"outcome_loop":{"version":"openagentskill-agent-outcome-v4","required_after_install":true,"endpoint":"/api/agent/outcome","method":"POST","event_id_source":"feedback.event_id, install_receipt.resolve_event_id, or decision_packet.outcome_feedback.event_id","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"required_fields":["event_id","skill_slug","task"],"quality_fields":["task_success","output_quality","error_type","human_review_required","used_in_production","workspace","evidence_url","time_to_useful_ms","source_version"],"ranking_inputs_updated":["Trust Score v5 outcome confidence","Agent Proven Score","Resolve ranking task-fit evidence","Skill detail machine-readable metadata","Outcome leaderboard"]},"agent_contract":{"suited_tasks":["research","agent-skill"],"suited_agents":["Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"install_command":"npx skills add gaasher/Agent-Loop-Skills --skill exploratory-autoresearch","trust_score":67,"trust_version":"trust-score-v5","risk_level":"medium","do_not_use_when":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace","Autonomous investment, trading, tax, or suitability decisions without a qualified human review"],"before_install":["Read the audit page and machine-readable metadata.","Confirm the install command, license, and permission surface fit the workspace.","Get explicit human approval or choose an alternative before installing."],"after_run":["Report the outcome to /api/agent/outcome using the resolve event id.","Include output_quality, workspace, human_review_required, and evidence_url when available.","Re-resolve before broad production rollout."]},"bestFor":["research","agent-skill"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace","Autonomous investment, trading, tax, or suitability decisions without a qualified human review"],"knownRisks":["Financial research output is not financial advice; require human review before any live investment decision.","Quality score needs review","Permission surface needs review: secrets or environment access, shell or command execution","Stars/forks activity: 163 stars, 19 forks; issue activity unavailable in current metadata","Permission surface: secrets or environment access, shell or command execution"],"backward_compatible":{"trust_score_v4":{"version":"trust-score-v4","score":75,"tier":"strong","label":"Strong shortlist","summary":"Good trust signals with a few areas worth checking before rollout."}}},"trust_score_v4":{"version":"trust-score-v4","score":75,"tier":"strong","label":"Strong shortlist","summary":"Good trust signals with a few areas worth checking before rollout.","recommendedAction":"Test in a sandbox workflow and compare its install path with close alternatives.","dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":62,"weight":0.13,"status":"info","detail":"163 GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":57,"weight":0.08,"status":"warn","detail":"163 stars, 19 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":88,"weight":0.14,"status":"pass","detail":"2mo since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"MIT"},{"id":"documentation","label":"README/SKILL.md completeness","score":86,"weight":0.14,"status":"pass","detail":"Metadata includes enough usage and workflow context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":72,"weight":0.12,"status":"info","detail":"credential or environment access"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add gaasher/Agent-Loop-Skills --skill exploratory-autoresearch"},{"id":"install_safety","label":"Install command safety","score":92,"weight":0.1,"status":"pass","detail":"standard package or runtime install path"},{"id":"permission_surface","label":"Permission surface","score":36,"weight":0.07,"status":"fail","detail":"secrets or environment access, shell or command execution"},{"id":"repository","label":"Repository evidence","score":86,"weight":0.04,"status":"pass","detail":"https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/exploratory-autoresearch"},{"id":"review_status","label":"Review status","score":88,"weight":0.05,"status":"pass","detail":"AI review data available"},{"id":"agent_outcomes","label":"Agent Proven outcomes","score":54,"weight":0.13,"status":"info","detail":"No agent outcome data yet"}],"checks":[{"status":"info","label":"GitHub adoption","detail":"163 GitHub stars"},{"status":"warn","label":"Stars/forks activity","detail":"163 stars, 19 forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"2mo since push"},{"status":"pass","label":"License clarity","detail":"MIT"},{"status":"pass","label":"README/SKILL.md completeness","detail":"Metadata includes enough usage and workflow context"},{"status":"info","label":"Dependency/runtime risk","detail":"credential or environment access"},{"status":"pass","label":"Install availability","detail":"npx skills add gaasher/Agent-Loop-Skills --skill exploratory-autoresearch"},{"status":"pass","label":"Install command safety","detail":"standard package or runtime install path"},{"status":"fail","label":"Permission surface","detail":"secrets or environment access, shell or command execution"},{"status":"pass","label":"Repository evidence","detail":"https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/exploratory-autoresearch"},{"status":"pass","label":"Review status","detail":"AI review data available"},{"status":"info","label":"Agent Proven outcomes","detail":"No agent outcome data yet"},{"status":"warn","label":"Ownership","detail":"No approved owner claim yet"},{"status":"info","label":"OpenAgentSkill usage","detail":"No local usage activity yet"},{"status":"info","label":"Agent outcomes","detail":"No agent outcome data yet"}],"strengths":["AI review approved","Install path is available","Repository evidence is available","Recently maintained repository","Install command has no obvious high-risk pattern"],"warnings":["Financial research output is not financial advice; require human review before any live investment decision.","Quality score needs review","Permission surface needs review: secrets or environment access, shell or command execution","Stars/forks activity: 163 stars, 19 forks; issue activity unavailable in current metadata","Permission surface: secrets or environment access, shell or command execution"],"evidence":{"stars":"163 GitHub stars","repoActivity":"163 stars, 19 forks","lastPushed":"2mo since push","license":"MIT","repository":"https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/exploratory-autoresearch","install":"npx skills add gaasher/Agent-Loop-Skills --skill exploratory-autoresearch","installSafety":"standard package or runtime install path","permissionSurface":"secrets or environment access, shell or command execution","documentation":"Strong README/SKILL.md context","agentOutcomes":"No agent outcome data yet"},"installReadiness":{"ready":true,"command":"npx skills add gaasher/Agent-Loop-Skills --skill exploratory-autoresearch","policy":"human_review_before_install","label":"Human review before install","notes":["Install path is available","Repository evidence is available","License is declared","No Agent Proven outcome evidence yet","2mo since push","Financial domain: human review is required before use in a live investment workflow."]},"agentCompatibility":["Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["Financial research output is not financial advice; require human review before any live investment decision.","Quality score needs review","Permission surface needs review: secrets or environment access, shell or command execution","Stars/forks activity: 163 stars, 19 forks; issue activity unavailable in current metadata","Permission surface: secrets or environment access, shell or command execution"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":false,"sandboxRequired":true,"policy":"human_review_before_install","reason":"Human review or sandbox validation is required before automatic installation."},"bestFor":["research","agent-skill"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace","Autonomous investment, trading, tax, or suitability decisions without a qualified human review"],"knownRisks":["Financial research output is not financial advice; require human review before any live investment decision.","Quality score needs review","Permission surface needs review: secrets or environment access, shell or command execution","Stars/forks activity: 163 stars, 19 forks; issue activity unavailable in current metadata","Permission surface: secrets or environment access, shell or command execution"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"outcome_stats":null,"safety":{"score":32,"level":"avoid_auto_install","label":"Avoid automatic install","safety_tier":{"tier":"blocked","label":"Blocked for auto-install","badge":"BLOCKED","summary":"This skill should not be selected by an agent without explicit human security review.","recommended_action":"Do not auto-install. Inspect the source, dependencies, and permission surface first.","auto_install_policy":"block","reasons":["Metadata combines secrets access with shell or command execution","High-risk permission hints: Shell or command execution, Secrets or environment access"]},"auto_install_allowed":false,"human_review_required":true,"blocked":true,"audit_risk":"needs_review","permission_hints":[{"id":"shell","label":"Shell or command execution","reason":"Skill metadata references terminal, CLI, shell, subprocess, or command execution workflows.","severity":"high"},{"id":"browser","label":"Browser automation","reason":"Skill may drive a browser or interact with web pages.","severity":"medium"},{"id":"network","label":"Network access","reason":"Skill likely fetches remote pages, APIs, repositories, or external services.","severity":"medium"},{"id":"filesystem","label":"Filesystem access","reason":"Skill may read or write project files, documents, generated artifacts, or local workspace state.","severity":"medium"},{"id":"secrets","label":"Secrets or environment access","reason":"Skill metadata references credentials, tokens, environment variables, or secret-bearing workflows.","severity":"high"}],"policy_warnings":["High-risk permission hints: Shell or command execution, Secrets or environment access","Permission surface may require sandboxing"],"constraints_applied":{"max_risk":"medium","needs_install_command":true,"min_stars":0}},"safety_gate":{"tier":"blocked","label":"Blocked for auto-install","badge":"BLOCKED","auto_install_policy":"block","auto_install_allowed":false,"blocked":true,"human_review_required":true,"recommended_action":"Do not auto-install. Inspect the source, dependencies, and permission surface first.","reasons":["Metadata combines secrets access with shell or command execution","High-risk permission hints: Shell or command execution, Secrets or environment access"]},"eval":{"version":"openagentskill-skill-eval-v1","status":"failed","score":65,"risk_level":"high","decision":{"recommendation":"do_not_auto_install","reason":"Agent safety gate: This skill should not be selected by an agent without explicit human security review.","auto_install_allowed":false,"policy":"block","human_review_required":true},"blockers":["Agent safety gate: This skill should not be selected by an agent without explicit human security review.","Permission surface: secrets or environment access, shell or command execution"],"warnings":["Trust score: Good trust signals with a few areas worth checking before rollout.","Audit score: Needs review","High-risk permission hints: Shell or command execution, Secrets or environment access","Permission surface may require sandboxing","Financial research output is not financial advice; require human review before any live investment decision","Financial research output is not financial advice; require human review before any live investment decision.","Quality score needs review","Permission surface needs review: secrets or environment access, shell or command execution","Stars/forks activity: 163 stars, 19 forks; issue activity unavailable in current metadata","Permission surface: secrets or environment access, shell or command execution"],"validation_plan":["Inspect repository, README/SKILL.md, license, and recent commits before production use.","Install in an isolated workspace or sandbox with no production secrets available.","Run the smallest representative task and record files touched, commands run, network access, and outputs.","Compare the selected skill against at least one alternative when the eval status is review or failed.","Promote only after the agent reports a successful verification result and unresolved warnings are accepted."],"checks":[{"id":"task_fit","label":"Task fit","status":"pass","score":94,"required_for_auto_install":true,"detail":"Task wording matches this skill metadata.","evidence":["Evaluate exploratory-autoresearch before installing it in an agent workflow","research","Research agents workflows; Claude Code teams; builders willing to evaluate younger projects"]},{"id":"install_path","label":"Install path","status":"pass","score":92,"required_for_auto_install":true,"detail":"Install handoff is available.","evidence":["npx skills add gaasher/Agent-Loop-Skills --skill exploratory-autoresearch"]},{"id":"install_safety","label":"Install command safety","status":"pass","score":92,"required_for_auto_install":true,"detail":"standard package or runtime install path","evidence":["npx skills add gaasher/Agent-Loop-Skills --skill exploratory-autoresearch"]},{"id":"trust_score","label":"Trust score","status":"warn","score":75,"required_for_auto_install":true,"detail":"Good trust signals with a few areas worth checking before rollout.","evidence":["Strong shortlist","163 GitHub stars","MIT"]},{"id":"audit_score","label":"Audit score","status":"warn","score":76,"required_for_auto_install":true,"detail":"Needs review","evidence":["Permission surface may require sandboxing"]},{"id":"agent_safety_gate","label":"Agent safety gate","status":"fail","score":32,"required_for_auto_install":true,"detail":"This skill should not be selected by an agent without explicit human security review.","evidence":["Do not auto-install. Inspect the source, dependencies, and permission surface first.","Metadata combines secrets access with shell or command execution"]},{"id":"readme_skillmd_completeness","label":"README/SKILL.md completeness","status":"pass","score":86,"required_for_auto_install":false,"detail":"Metadata includes enough usage and workflow context","evidence":["Strong README/SKILL.md context"]},{"id":"license_clarity","label":"License clarity","status":"pass","score":86,"required_for_auto_install":true,"detail":"MIT","evidence":["MIT"]},{"id":"recent_maintenance","label":"Recent maintenance","status":"pass","score":88,"required_for_auto_install":false,"detail":"2mo since push","evidence":["2mo since push"]},{"id":"permission_surface","label":"Permission surface","status":"fail","score":36,"required_for_auto_install":true,"detail":"secrets or environment access, shell or command execution","evidence":["Shell or command execution: high","Browser automation: medium","Network access: medium"]},{"id":"alternatives","label":"Alternatives available","status":"info","score":55,"required_for_auto_install":false,"detail":"No close alternatives were found in the current shortlist.","evidence":[]}],"endpoints":{"web":"https://www.openagentskill.com/skills/gaasher-exploratory-autoresearch/evals","api":"/api/agent/evals?slug=gaasher-exploratory-autoresearch","text":"/api/agent/evals?slug=gaasher-exploratory-autoresearch&format=text"}},"agent_readable_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"gaasher-exploratory-autoresearch","name":"exploratory-autoresearch","description":"Use when the user wants an autonomous ML research loop that explores the space broadly rather than hill-climbing one approach. A temperature scheduler replaces the usual hypothesis step: it forces several wild, diverse swings (full rewrites, different architectures/regimes) early, then enters an adaptive phase that picks swing / merge / exploit per iteration — with a hard stagnation guard that bans further small-step exploits once they run too long, forcing a pivot back to a swing or merge. Tracks an approaches.md registry and a move_type per iteration; analyses every run before the next move. One change per iteration; loops forever until interrupted. Not for the standard analysis-first ml-autoresearch (which lets analysis alone choose each change), one-off training runs, or sweeps.","category":"research","url":"https://www.openagentskill.com/skills/gaasher-exploratory-autoresearch","repository":"https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/exploratory-autoresearch","github_repo":"gaasher/Agent-Loop-Skills"},"suited_tasks":["Research agents workflows","Claude Code teams","builders willing to evaluate younger projects","Search sources","Extract claims","Synthesize findings","Move data between tools","Transform files"],"suited_agents":["Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add gaasher/Agent-Loop-Skills --skill exploratory-autoresearch","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.3.0/openagentskill-0.3.0.tgz add gaasher-exploratory-autoresearch"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"exploratory-autoresearch\" agent skill from https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/exploratory-autoresearch. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: Use when the user wants an autonomous ML research loop that explores the space broadly rather than hill-climbing one approach. A temperature scheduler replaces the usual hypothesis step: it forces several wild, diverse swings (full rewrites, different architectures/regimes) early, then enters an adaptive phase that picks swing / merge / exploit per iteration — with a hard stagnation guard that bans further small-step exploits once they run too long, forcing a pivot back to a swing or merge. Tracks an approaches.md registry and a move_type per iteration; analyses every run before the next move. One change per iteration; loops forever until interrupted. Not for the standard analysis-first ml-autoresearch (which lets analysis alone choose each change), one-off training runs, or sweeps. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_\",\"skill_slug\":\"gaasher-exploratory-autoresearch\",\"task\":\"Install exploratory-autoresearch\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"exploratory-autoresearch\" as a Claude Code skill from https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/exploratory-autoresearch. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: Use when the user wants an autonomous ML research loop that explores the space broadly rather than hill-climbing one approach. A temperature scheduler replaces the usual hypothesis step: it forces several wild, diverse swings (full rewrites, different architectures/regimes) early, then enters an adaptive phase that picks swing / merge / exploit per iteration — with a hard stagnation guard that bans further small-step exploits once they run too long, forcing a pivot back to a swing or merge. Tracks an approaches.md registry and a move_type per iteration; analyses every run before the next move. One change per iteration; loops forever until interrupted. Not for the standard analysis-first ml-autoresearch (which lets analysis alone choose each change), one-off training runs, or sweeps. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_\",\"skill_slug\":\"gaasher-exploratory-autoresearch\",\"task\":\"Install exploratory-autoresearch\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"exploratory-autoresearch\" from https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/exploratory-autoresearch into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: Use when the user wants an autonomous ML research loop that explores the space broadly rather than hill-climbing one approach. A temperature scheduler replaces the usual hypothesis step: it forces several wild, diverse swings (full rewrites, different architectures/regimes) early, then enters an adaptive phase that picks swing / merge / exploit per iteration — with a hard stagnation guard that bans further small-step exploits once they run too long, forcing a pivot back to a swing or merge. Tracks an approaches.md registry and a move_type per iteration; analyses every run before the next move. One change per iteration; loops forever until interrupted. Not for the standard analysis-first ml-autoresearch (which lets analysis alone choose each change), one-off training runs, or sweeps. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_\",\"skill_slug\":\"gaasher-exploratory-autoresearch\",\"task\":\"Install exploratory-autoresearch\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."}],"handoff_url":"https://www.openagentskill.com/api/skills/gaasher-exploratory-autoresearch/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/gaasher-exploratory-autoresearch"},"trust":{"score":75,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"163 GitHub stars","repoActivity":"163 stars, 19 forks","lastPushed":"2mo since push","license":"MIT","repository":"https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/exploratory-autoresearch","install":"npx skills add gaasher/Agent-Loop-Skills --skill exploratory-autoresearch","installSafety":"standard package or runtime install path","permissionSurface":"secrets or environment access, shell or command execution","documentation":"Strong README/SKILL.md context","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":false,"sandbox_required":true,"reason":"Human review or sandbox validation is required before automatic installation."},"best_for":["research","agent-skill"],"known_risks":["Financial research output is not financial advice; require human review before any live investment decision.","Quality score needs review","Permission surface needs review: secrets or environment access, shell or command execution","Stars/forks activity: 163 stars, 19 forks; issue activity unavailable in current metadata","Permission surface: secrets or environment access, shell or command execution"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":76,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Permission surface may require sandboxing","Financial research output is not financial advice; require human review before any live investment decision","Financial research output is not financial advice; require human review before any live investment decision.","Quality score needs review","Permission surface needs review: secrets or environment access, shell or command execution","Stars/forks activity: 163 stars, 19 forks; issue activity unavailable in current metadata","Permission surface: secrets or environment access, shell or command execution"]},"safety_gate":{"tier":"blocked","label":"Blocked for auto-install","auto_install_policy":"block","auto_install_allowed":false,"human_review_required":true,"blocked":true,"recommended_action":"Do not auto-install. Inspect the source, dependencies, and permission surface first."},"quality":{"score":63,"label":"Promising"},"supply":{"track":"Research and knowledge work","scenario":"Research agents","maintenance":"2mo since push","risk":"Needs review"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","High-risk permission hints: Shell or command execution, Secrets or environment access","Permission surface may require sandboxing","Financial research output is not financial advice; require human review before any live investment decision","Financial research output is not financial advice; require human review before any live investment decision.","Quality score needs review"],"agent_contract":{"task_input":"Use exploratory-autoresearch in an agent workflow","recommended_action":"Do not auto-install. Inspect the source, dependencies, and permission surface first.","install_policy":"block","minimum_review_before_use":["Trust: 75/100 Strong shortlist","Audit: 76/100 Needs review","Safety: 32/100 Avoid automatic install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"gaasher-exploratory-autoresearch (exploratory-autoresearch)","install_command":"npx skills add gaasher/Agent-Loop-Skills --skill exploratory-autoresearch","risk_summary":"Needs review; Blocked for auto-install; Review before production","verification_result":"Report the smallest successful task, files touched, warnings, and any missing setup."}},"outcome_feedback":{"endpoint":"https://www.openagentskill.com/api/agent/outcome","method":"POST","requires_resolve_event_id":true,"event_id_source":"Use install_receipt.outcome_feedback.event_id or feedback.event_id returned by /api/agent/resolve for the current task.","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"payload_template":{"event_id":"","skill_slug":"gaasher-exploratory-autoresearch","task":"Use exploratory-autoresearch in an agent workflow","agent":"codex","outcome":"success","install_used":true,"risk_blocked":false,"setup_required":false,"task_success":true,"output_quality":4,"error_type":null,"human_review_required":false,"workspace":"sandbox","time_to_useful_ms":120000,"notes":"Report the smallest successful task, setup friction, files touched, and risk notes."}},"endpoints":{"web":"https://www.openagentskill.com/skills/gaasher-exploratory-autoresearch","api":"https://www.openagentskill.com/api/agent/skills/gaasher-exploratory-autoresearch","audit":"https://www.openagentskill.com/skills/gaasher-exploratory-autoresearch/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=gaasher-exploratory-autoresearch&task=Use%20exploratory-autoresearch%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20exploratory-autoresearch%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20exploratory-autoresearch%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/gaasher-exploratory-autoresearch/install","manifest":"https://www.openagentskill.com/api/registry/manifest/gaasher-exploratory-autoresearch"}},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"gaasher-exploratory-autoresearch","name":"exploratory-autoresearch","description":"Use when the user wants an autonomous ML research loop that explores the space broadly rather than hill-climbing one approach. A temperature scheduler replaces the usual hypothesis step: it forces several wild, diverse swings (full rewrites, different architectures/regimes) early, then enters an adaptive phase that picks swing / merge / exploit per iteration — with a hard stagnation guard that bans further small-step exploits once they run too long, forcing a pivot back to a swing or merge. Tracks an approaches.md registry and a move_type per iteration; analyses every run before the next move. One change per iteration; loops forever until interrupted. Not for the standard analysis-first ml-autoresearch (which lets analysis alone choose each change), one-off training runs, or sweeps.","category":"research","url":"https://www.openagentskill.com/skills/gaasher-exploratory-autoresearch","repository":"https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/exploratory-autoresearch","github_repo":"gaasher/Agent-Loop-Skills"},"suited_tasks":["Research agents workflows","Claude Code teams","builders willing to evaluate younger projects","Search sources","Extract claims","Synthesize findings","Move data between tools","Transform files"],"suited_agents":["Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add gaasher/Agent-Loop-Skills --skill exploratory-autoresearch","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.3.0/openagentskill-0.3.0.tgz add gaasher-exploratory-autoresearch"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"exploratory-autoresearch\" agent skill from https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/exploratory-autoresearch. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: Use when the user wants an autonomous ML research loop that explores the space broadly rather than hill-climbing one approach. A temperature scheduler replaces the usual hypothesis step: it forces several wild, diverse swings (full rewrites, different architectures/regimes) early, then enters an adaptive phase that picks swing / merge / exploit per iteration — with a hard stagnation guard that bans further small-step exploits once they run too long, forcing a pivot back to a swing or merge. Tracks an approaches.md registry and a move_type per iteration; analyses every run before the next move. One change per iteration; loops forever until interrupted. Not for the standard analysis-first ml-autoresearch (which lets analysis alone choose each change), one-off training runs, or sweeps. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_\",\"skill_slug\":\"gaasher-exploratory-autoresearch\",\"task\":\"Install exploratory-autoresearch\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"exploratory-autoresearch\" as a Claude Code skill from https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/exploratory-autoresearch. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: Use when the user wants an autonomous ML research loop that explores the space broadly rather than hill-climbing one approach. A temperature scheduler replaces the usual hypothesis step: it forces several wild, diverse swings (full rewrites, different architectures/regimes) early, then enters an adaptive phase that picks swing / merge / exploit per iteration — with a hard stagnation guard that bans further small-step exploits once they run too long, forcing a pivot back to a swing or merge. Tracks an approaches.md registry and a move_type per iteration; analyses every run before the next move. One change per iteration; loops forever until interrupted. Not for the standard analysis-first ml-autoresearch (which lets analysis alone choose each change), one-off training runs, or sweeps. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_\",\"skill_slug\":\"gaasher-exploratory-autoresearch\",\"task\":\"Install exploratory-autoresearch\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"exploratory-autoresearch\" from https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/exploratory-autoresearch into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: Use when the user wants an autonomous ML research loop that explores the space broadly rather than hill-climbing one approach. A temperature scheduler replaces the usual hypothesis step: it forces several wild, diverse swings (full rewrites, different architectures/regimes) early, then enters an adaptive phase that picks swing / merge / exploit per iteration — with a hard stagnation guard that bans further small-step exploits once they run too long, forcing a pivot back to a swing or merge. Tracks an approaches.md registry and a move_type per iteration; analyses every run before the next move. One change per iteration; loops forever until interrupted. Not for the standard analysis-first ml-autoresearch (which lets analysis alone choose each change), one-off training runs, or sweeps. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_\",\"skill_slug\":\"gaasher-exploratory-autoresearch\",\"task\":\"Install exploratory-autoresearch\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."}],"handoff_url":"https://www.openagentskill.com/api/skills/gaasher-exploratory-autoresearch/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/gaasher-exploratory-autoresearch"},"trust":{"score":75,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"163 GitHub stars","repoActivity":"163 stars, 19 forks","lastPushed":"2mo since push","license":"MIT","repository":"https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/exploratory-autoresearch","install":"npx skills add gaasher/Agent-Loop-Skills --skill exploratory-autoresearch","installSafety":"standard package or runtime install path","permissionSurface":"secrets or environment access, shell or command execution","documentation":"Strong README/SKILL.md context","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":false,"sandbox_required":true,"reason":"Human review or sandbox validation is required before automatic installation."},"best_for":["research","agent-skill"],"known_risks":["Financial research output is not financial advice; require human review before any live investment decision.","Quality score needs review","Permission surface needs review: secrets or environment access, shell or command execution","Stars/forks activity: 163 stars, 19 forks; issue activity unavailable in current metadata","Permission surface: secrets or environment access, shell or command execution"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":76,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Permission surface may require sandboxing","Financial research output is not financial advice; require human review before any live investment decision","Financial research output is not financial advice; require human review before any live investment decision.","Quality score needs review","Permission surface needs review: secrets or environment access, shell or command execution","Stars/forks activity: 163 stars, 19 forks; issue activity unavailable in current metadata","Permission surface: secrets or environment access, shell or command execution"]},"safety_gate":{"tier":"blocked","label":"Blocked for auto-install","auto_install_policy":"block","auto_install_allowed":false,"human_review_required":true,"blocked":true,"recommended_action":"Do not auto-install. Inspect the source, dependencies, and permission surface first."},"quality":{"score":63,"label":"Promising"},"supply":{"track":"Research and knowledge work","scenario":"Research agents","maintenance":"2mo since push","risk":"Needs review"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","High-risk permission hints: Shell or command execution, Secrets or environment access","Permission surface may require sandboxing","Financial research output is not financial advice; require human review before any live investment decision","Financial research output is not financial advice; require human review before any live investment decision.","Quality score needs review"],"agent_contract":{"task_input":"Use exploratory-autoresearch in an agent workflow","recommended_action":"Do not auto-install. Inspect the source, dependencies, and permission surface first.","install_policy":"block","minimum_review_before_use":["Trust: 75/100 Strong shortlist","Audit: 76/100 Needs review","Safety: 32/100 Avoid automatic install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"gaasher-exploratory-autoresearch (exploratory-autoresearch)","install_command":"npx skills add gaasher/Agent-Loop-Skills --skill exploratory-autoresearch","risk_summary":"Needs review; Blocked for auto-install; Review before production","verification_result":"Report the smallest successful task, files touched, warnings, and any missing setup."}},"outcome_feedback":{"endpoint":"https://www.openagentskill.com/api/agent/outcome","method":"POST","requires_resolve_event_id":true,"event_id_source":"Use install_receipt.outcome_feedback.event_id or feedback.event_id returned by /api/agent/resolve for the current task.","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"payload_template":{"event_id":"","skill_slug":"gaasher-exploratory-autoresearch","task":"Use exploratory-autoresearch in an agent workflow","agent":"codex","outcome":"success","install_used":true,"risk_blocked":false,"setup_required":false,"task_success":true,"output_quality":4,"error_type":null,"human_review_required":false,"workspace":"sandbox","time_to_useful_ms":120000,"notes":"Report the smallest successful task, setup friction, files touched, and risk notes."}},"endpoints":{"web":"https://www.openagentskill.com/skills/gaasher-exploratory-autoresearch","api":"https://www.openagentskill.com/api/agent/skills/gaasher-exploratory-autoresearch","audit":"https://www.openagentskill.com/skills/gaasher-exploratory-autoresearch/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=gaasher-exploratory-autoresearch&task=Use%20exploratory-autoresearch%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20exploratory-autoresearch%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20exploratory-autoresearch%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/gaasher-exploratory-autoresearch/install","manifest":"https://www.openagentskill.com/api/registry/manifest/gaasher-exploratory-autoresearch"}},"supply_profile":{"track":{"slug":"research","label":"Research and knowledge work","shortLabel":"Research","description":"Deep research, source comparison, literature review, RAG, knowledge search, and reports."},"scenario":{"label":"Research agents","description":"I need my agent to research a topic, compare sources, and produce a concise report.","useCases":[{"slug":"research-agents","title":"Research agents"},{"slug":"workflow-automation","title":"Workflow automation"},{"slug":"rag-knowledge","title":"RAG and knowledge"}]},"applicableAgents":["Claude Code","CLI","Codex","Cursor"],"install":{"ready":true,"command":"npx skills add gaasher/Agent-Loop-Skills --skill exploratory-autoresearch","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":163,"starsLabel":"163","forks":19,"license":"MIT","qualityScore":63,"trustScore":75,"auditScore":76},"maintenance":{"status":"active","label":"2mo since push","daysSincePush":68,"lastPushedAt":"2026-06-30T04:03:49+00:00"},"risk":{"level":"needs_review","label":"Needs review","requiresReview":true,"notes":["Permission surface may require sandboxing","Financial research output is not financial advice; require human review before any live investment decision","Financial research output is not financial advice; require human review before any live investment decision.","Quality score needs review","Permission surface needs review: secrets or environment access, shell or command execution"]},"coverageTags":["Research","Research agents","agent-skill"]},"audit":{"audit_score":76,"risk_level":"needs_review","risk_label":"Needs review","quality_score":63,"trust_score":75,"maintenance_score":88,"security_score":81,"install_score":92,"warnings":["Permission surface may require sandboxing","Financial research output is not financial advice; require human review before any live investment decision","Financial research output is not financial advice; require human review before any live investment decision.","Quality score needs review","Permission surface needs review: secrets or environment access, shell or command execution","Stars/forks activity: 163 stars, 19 forks; issue activity unavailable in current metadata","Permission surface: secrets or environment access, shell or command execution"]},"quality_signals":{"model":"v2","star_score":15.5,"usage_score":0,"review_score":5.1,"metadata_score":3,"freshness_score":12},"platforms":["Claude Code"],"use_cases":[{"slug":"research-agents","title":"Research agents","url":"https://www.openagentskill.com/use-cases/research-agents"},{"slug":"workflow-automation","title":"Workflow automation","url":"https://www.openagentskill.com/use-cases/workflow-automation"},{"slug":"rag-knowledge","title":"RAG and knowledge","url":"https://www.openagentskill.com/use-cases/rag-knowledge"},{"slug":"browser-automation","title":"Browser automation","url":"https://www.openagentskill.com/use-cases/browser-automation"}],"stacks":[{"slug":"research-report-agent","title":"Research report agent","url":"https://www.openagentskill.com/collections/research-report-agent"},{"slug":"rag-knowledge-base","title":"RAG knowledge base","url":"https://www.openagentskill.com/collections/rag-knowledge-base"},{"slug":"browser-qa-agent","title":"Browser QA agent","url":"https://www.openagentskill.com/collections/browser-qa-agent"}],"install":"npx skills add gaasher/Agent-Loop-Skills --skill exploratory-autoresearch","install_targets":[{"id":"openagentskill-cli","label":"CLI","title":"OpenAgentSkill CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.3.0/openagentskill-0.3.0.tgz add gaasher-exploratory-autoresearch","description":"Resolve policy, run the source installer safely, and report a verified install receipt.","copyLabel":"Copy command"},{"id":"codex","label":"Codex","title":"Codex install prompt","kind":"agent-prompt","value":"Install the \"exploratory-autoresearch\" agent skill from https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/exploratory-autoresearch. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: Use when the user wants an autonomous ML research loop that explores the space broadly rather than hill-climbing one approach. A temperature scheduler replaces the usual hypothesis step: it forces several wild, diverse swings (full rewrites, different architectures/regimes) early, then enters an adaptive phase that picks swing / merge / exploit per iteration — with a hard stagnation guard that bans further small-step exploits once they run too long, forcing a pivot back to a swing or merge. Tracks an approaches.md registry and a move_type per iteration; analyses every run before the next move. One change per iteration; loops forever until interrupted. Not for the standard analysis-first ml-autoresearch (which lets analysis alone choose each change), one-off training runs, or sweeps. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_\",\"skill_slug\":\"gaasher-exploratory-autoresearch\",\"task\":\"Install exploratory-autoresearch\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Give Codex a repo-aware install prompt when the skill is not available through a local CLI.","copyLabel":"Copy prompt"},{"id":"claude-code","label":"Claude Code","title":"Claude Code skill prompt","kind":"agent-prompt","value":"Add \"exploratory-autoresearch\" as a Claude Code skill from https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/exploratory-autoresearch. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: Use when the user wants an autonomous ML research loop that explores the space broadly rather than hill-climbing one approach. A temperature scheduler replaces the usual hypothesis step: it forces several wild, diverse swings (full rewrites, different architectures/regimes) early, then enters an adaptive phase that picks swing / merge / exploit per iteration — with a hard stagnation guard that bans further small-step exploits once they run too long, forcing a pivot back to a swing or merge. Tracks an approaches.md registry and a move_type per iteration; analyses every run before the next move. One change per iteration; loops forever until interrupted. Not for the standard analysis-first ml-autoresearch (which lets analysis alone choose each change), one-off training runs, or sweeps. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_\",\"skill_slug\":\"gaasher-exploratory-autoresearch\",\"task\":\"Install exploratory-autoresearch\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Use this prompt to ask Claude Code to add the skill and explain the local activation steps.","copyLabel":"Copy prompt"},{"id":"cursor","label":"Cursor","title":"Cursor rule prompt","kind":"agent-prompt","value":"Turn \"exploratory-autoresearch\" from https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/exploratory-autoresearch into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: Use when the user wants an autonomous ML research loop that explores the space broadly rather than hill-climbing one approach. A temperature scheduler replaces the usual hypothesis step: it forces several wild, diverse swings (full rewrites, different architectures/regimes) early, then enters an adaptive phase that picks swing / merge / exploit per iteration — with a hard stagnation guard that bans further small-step exploits once they run too long, forcing a pivot back to a swing or merge. Tracks an approaches.md registry and a move_type per iteration; analyses every run before the next move. One change per iteration; loops forever until interrupted. Not for the standard analysis-first ml-autoresearch (which lets analysis alone choose each change), one-off training runs, or sweeps. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_\",\"skill_slug\":\"gaasher-exploratory-autoresearch\",\"task\":\"Install exploratory-autoresearch\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Use this when installing as Cursor project rules or reusable agent instructions.","copyLabel":"Copy prompt"}],"repository":"https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/exploratory-autoresearch","github_repo":"gaasher/Agent-Loop-Skills","version":"1.0.0","license":"MIT","urls":{"web":"https://www.openagentskill.com/skills/gaasher-exploratory-autoresearch","repository":"https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/exploratory-autoresearch","api":"/api/agent/skills/gaasher-exploratory-autoresearch","install_api":"/api/skills/gaasher-exploratory-autoresearch/install"},"meta":{"created_at":"2026-09-04T05:11:21.841977+00:00","updated_at":"2026-09-04T05:11:21.933859+00:00","agent_friendly":true}}