{"slug":"k-dense-ai-arbor","name":"arbor","description":"Autonomously improve a real artifact (code, training recipe, agent harness, data pipeline, prompt) against an objective and an evaluator, using Hypothesis Tree Refinement (HTR) from the Arbor paper. Use this whenever someone wants to iteratively optimize something over many experiments without overfitting — e.g. \"get my model's eval score up\", \"improve this agent/harness\", \"tune this pipeline\", \"beat the baseline on this benchmark\", \"run a search over approaches and keep the best\", \"do an MLE-bench / Kaggle-style optimization\", or any long-horizon \"make this artifact better and don't just memorize the dev set\" task. Trigger it even when the user doesn't say \"Arbor\" or \"hypothesis tree\" but describes repeated experiment-and-evaluate loops, branching exploration of competing ideas, or worries about a dev/test gap. Runs Claude itself as the coordinator with subagent executors in isolated git worktrees; for the standalone `arbor` CLI tool see references/arbor-upstream.md.","long_description":"---\nname: arbor\ndescription: Autonomously improve a real artifact (code, training recipe, agent harness, data pipeline, prompt) against an objective and an evaluator, using Hypothesis Tree Refinement (HTR) from the Arbor paper. Use this whenever someone wants to iteratively optimize something over many experiments without overfitting — e.g. \"get my model's eval score up\", \"improve this agent/harness\", \"tune this pipeline\", \"beat the baseline on this benchmark\", \"run a search over approaches and keep the best\", \"do an MLE-bench / Kaggle-style optimization\", or any long-horizon \"make this artifact better and don't just memorize the dev set\" task. Trigger it even when the user doesn't say \"Arbor\" or \"hypothesis tree\" but describes repeated experiment-and-evaluate loops, branching exploration of competing ideas, or worries about a dev/test gap. Runs Claude itself as the coordinator with subagent executors in isolated git worktrees; for the standalone `arbor` CLI tool see references/arbor-upstream.md.\nallowed-tools: Read Write Edit Bash Agent\nlicense: MIT license\nmetadata:\n  version: \"1.1\"\n  skill-author: K-Dense Inc.\n---\n\n# Arbor — Autonomous Optimization via Hypothesis Tree Refinement\n\n## Overview\n\nThis skill runs an **Autonomous Optimization (AO)** loop: starting from an existing artifact and a measurable objective, improve it through many rounds of experiment and evaluation — without step-by-step human supervision and without overfitting to the feedback signal. It's the right tool when the bottleneck isn't writing one good change, but *organizing dozens of trials* so that lessons accumulate instead of evaporating.\n\nIt implements **Hypothesis Tree Refinement (HTR)** from *Arbor* (Jin et al., 2026). The key idea: keep the research state in a persistent **hypothesis tree** rather than in conversation history. Each node binds a hypothesis, the distilled insight it produced, and a pointer to the artifact version that realizes it. You play the long-lived **coordinator** that owns this tree and decides where to search; short-lived **executor** subagents test one hypothesis each in isolated git worktrees and report back. A **held-out merge gate** admits a change only when it improves on a *test* evaluator the search never optimized against. This is what turns trial-and-error into cumulative, auditable research.\n\nUse the `scripts/tree.py` state manager for all the bookkeeping (creating nodes, writing evidence, propagating insights, pruning, the merge gate, the Observe projection). It keeps the state consistent and frees you to spend judgment on what the evidence *means*.\n\n## When to use this skill\n\nReach for Arbor when the task is **iterative improvement of a concrete artifact under an evaluator**:\n- Model training: optimizer/architecture/recipe changes to lower loss or hit a target in fewer steps.\n- Harness/agent engineering: raising pass rate or accuracy of an agent loop, search harness, or tool-use scaffold.\n- Data synthesis: improving a generation/filtering pipeline judged by downstream model behavior.\n- Benchmark optimization: MLE-bench / Kaggle-style \"improve the submission\" tasks.\n- Prompt/system optimization where you can score outputs automatically.\n\nThe distinguishing signals: there's an **artifact you can modify**, an **objective**, a way to **score** candidates, and you expect to run **many experiments**. If the user only wants a single fix or a one-shot answer, this is overkill — just do the work directly. If they want open-ended ideation with no evaluator, use `hypothesis-generation` or `scientific-brainstorming` instead.\n\n## The AO setup — pin this down first\n\nBefore any experiments, establish the task tuple `(M_0, O, E_dev, E_test)`. Getting this right matters more than any later decision, so confirm it explicitly:\n\n- **M_0 — initial material**: the artifact to improve (a repo, a script, a config, a prompt). Make sure it's under git and currently runs.\n- **O — objective**: the natural-language goal and the metric *direction* (maximize accuracy? minimize loss/steps?).\n- **E_dev — development evaluator**: a command you can run freely during search to score a candidate. Fast, repeatable.\n- **E_test — held-out test evaluator**: a *separate* evaluator (different seeds, different split, or a larger run) used only at the merge gate. It must not be used as a search oracle — that's the whole point.\n\nIf the user hasn't given you a clean dev/test split, **construct one and say so**. The dev/test separation is the mechanism that catches overfitting: a candidate that wins on dev but not on test isn't a success, it's a warning that you're exploiting the feedback signal. Without it, autonomous search reliably overfits.\n\nInitialize the run:\n\n```bash\npython scripts/tree.py init \\\n  --objective \"Improve BrowseComp answer accuracy on the search harness\" \\\n  --dev-eval \"python eval.py --split dev --n 50\" \\\n  --test-eval \"python eval.py --split test --n 300\" \\\n  --material \".\" --metric-direction max --branching 3 --max-depth 2 --budget 12\n```\n\n`--branching` is how many sibling hypotheses you propose per parent; `--max-depth 2` keeps directions at depth 1 and concrete interventions at depth 2 (the paper's default); `--budget` is the number of coordinator cycles. Start small (10–20 cycles) — structured search beats brute force, and you can extend if progress is still being made.\n\n## The coordinator loop\n\nYou run repeated cycles of six steps. This is the heart of HTR; do not collapse it into ad-hoc editing. Run `python scripts/tree.py cycle` once per cycle to track the budget.\n\n### 1. Observe\nBegin every cycle by re-grounding in the tree, not in your memory of the conversation:\n\n```bash\npython scripts/tree.py observe\n```\n\nThis prints the objective, global insights, the active frontier (selectable hypotheses), executed nodes with their evidence, pruned lessons (negative constraints), and the current best artifact. Treating the tree as the source of truth is what keeps you coherent over a long run, after context compression has thrown away the details.\n\n### 2. Ideate\nPick a promising parent and propose a few child hypotheses under it. **Condition on the tree's evidence** — this is the difference between Arbor and random search:\n- Validated insights are assumptions you can build on.\n- Pruned nodes are dead ends to avoid.\n- A \"half-right\" result is a *starting point for a sharper hypothesis*, not a reason to abandon the direction.\n\nEach hypothesis should be a **falsifiable claim about how changing the artifact will move the metric**, not a vague intention. Depth-1 nodes are broad directions (\"the search harness loses correct answers it already retrieved\"); depth-2 nodes are concrete, executable interventions (\"run K=5 independent rollouts and aggregate by evidence dossier instead of majority vote\").\n\n```bash\npython scripts/tree.py add-node --parent n0 --hypothesis \"Verification, not retrieval, is the bottleneck: candidates are found but discarded\"\npython scripts/tree.py add-node --parent n4 --hypothesis \"Decompose the question into atomic constraints and verify each independently\"\n```\n\n### 3. Select\nChoose which pending leaves to run next. **Selection is not pure score-maximization** — pick a hypothesis because it has strong prior evidence, because it would resolve an ambiguity its siblings exposed, or because its failure would clarify an important assumption. Frontier control under delayed feedback rewards informative experiments, not just promising ones.\n\n### 4. Dispatch\nRun each selected hypothesis as an **executor subagent in an isolated worktree** (use the Agent tool with `isolation: \"worktree\"`, or have the executor create one with `git worktree add`). Isolation matters: parallel experiments must not clobber each other or the current best, and exploratory changes stay quarantined until they pass the merge gate.\n\nDispatch siblings **in parallel** (multiple Agent calls in one message) when they're independent — comparative evidence within one direction is exactly what makes later pruning and abstraction possible.\n\nGive each executor a tight, **hypothesis-bound** brief. See `references/executor-brief.md` for the full template. The contract that makes HTR work: **the executor may not change the hypothesis when the metric stalls.** It repairs its own code and reruns, but `h_n` is fixed — otherwise the returned score is no longer evidence about the assigned node and the tree's semantics break. The executor returns exactly four things:\n- **dev_score** — the dev evaluator result (for selection);\n- **result** — a factual summary of what happened;\n- **insight** — the distilled, reusable lesson (*why* the result supports, weakens, or bounds the hypothesis);\n- **branch_ref** — the git branch/commit/worktree path holding the artifact.\n\nMark a node `running` before dispatch (`tree.py set-status --node n5 --status running`) so the Observe projection stays accurate.\n\n### 5. Backpropagate\nWhen an executor returns, write its report into the node, then **abstract the lesson upward**:\n\n```bash\npython scripts/tree.py set-evidence --node n5 --dev-score 70.0 \\\n  --result \"K=5 dossier aggregation recovers answers in minority rollouts\" \\\n  --insight \"Correct answers often appear in a minority of rollouts; aggregation beats majority vote\" \\\n  --branch-ref \"wt/n5\"\n\npython scripts/tree.py propagate --node n5 \\\n  --insight \"Candidate coverage, not verification, limits this direction\" --to-root\n```\n\nThis is the step that makes the tree more than a log. A leaf-level observation (\"data-interface mismatch\") should become a direction-level constraint and, if it generalizes, a global prior that shapes future ideation. **Insight propagation is the component that drives most of HTR's gains** — in the paper's MLE-Bench Lite ablation, a tree *without* insight feedback scored even lower than a flat experiment queue with no tree at all (54.5% vs. 63.6% any-medal, against 81.8% for the full system). Hierarchy alone isn't enough: the semantic memory is what matters. So spend real thought on the abstraction; don't just copy the leaf insight upward verbatim.\n\n### 6. Decide\nDecide what to do with the new evidence: keep expanding a direction, prune a falsified subtree, or attempt to merge a candidate.\n\n- **Prune** dead ends, recording *why* — the reason becomes a negative constraint:\n  ```bash\n  python scripts/tree.py prune --node n7 --reason \"search-augmented judge overfits dev questions; no test transfer\"\n  ```\n- **Merge gate** — promote a candidate to the new best **only if it improves on `E_test`**. Run the test evaluator in a *fresh* worktree (not the dev worktree, to avoid leakage), then:\n  ```bash\n  python scripts/tree.py merge --node n5 --test-score 67.67 --branch-ref \"wt/n5\"\n  ```\n  If the gate rejects it, that's informative: a high-dev / low-test candidate is evidence the direction may be exploiting the dev signal rather than producing a transferable improvement. Record that lesson; don't quietly promote it anyway.\n\nRepeat until the budget is spent, the frontier is exhausted, or progress has clearly stalled.\n\n## Finishing the run\n\nWhen you stop, produce a short report (see `references/report-template.md`) covering:\n- the final best artifact, its test score, and its delta over `M_0`;\n- the tree (`python scripts/tree.py status`) as the audit trail of what was tried;\n- the main hypothesis shifts — how task understanding deepened across the run (early nodes test broad mechanisms; later nodes find their limits; ancestor insights compress these into the constraints behind the final design);\n- merged vs. explored: many nodes improve dev, far fewer pass the test gate — report that gap honestly rather than overstating dev wins.\n\nAlways leave `M_best` as a real, runnable artifact on a named branch, and tell the user how to check it out.\n\n## Principles that make this work (not rote rules)\n\nThese come from the paper's analysis; understanding *why* matters more than following them mechanically.\n\n- **The tree is the memory; conversatio","tagline":"Autonomously improve a real artifact (code, training recipe, agent harness, data pipeline, prompt) against an objective and an evaluator, using Hypothesis Tree Refinement (HTR) from the Arbor paper. Use this whenever someone wants to iteratively optimize something over many exper","category":"research","tags":["agent-skill"],"author":"K-Dense-AI","verified":false,"attribution":{"status":"registry_indexed","statusLabel":"Registry indexed","shortLabel":"REGISTRY INDEXED","sourceLabel":"recursive skill source sync","sourceDetail":"K-Dense-AI/scientific-agent-skills","creatorName":"K-Dense-AI","creatorUrl":"https://github.com/K-Dense-AI","sourceUrl":"https://github.com/K-Dense-AI/scientific-agent-skills/tree/main/skills/arbor","indexedBy":"OpenAgentSkill community index","claimUrl":"https://www.openagentskill.com/skills/k-dense-ai-arbor#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":33974,"forks":3307,"verified_installs":0,"successful_runs":0,"total_outcomes":0,"rating":0,"review_count":0,"quality_score":55.12},"quality":{"score":92,"tier":"excellent","label":"Excellent","summary":"High-confidence pick with strong adoption and healthy maintenance signals.","signals":[{"label":"GitHub stars","value":"34K","tone":"positive"},{"label":"Freshness","value":"2d ago","tone":"positive"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"MIT license","tone":"neutral"}],"warnings":[]},"trust":{"version":"trust-score-v5","score":79,"base_score":84,"outcome_confidence":0,"tier":"strong","label":"Review then install","summary":"Good shortlist signal, but the agent should review audit notes, install policy, and outcome evidence before running it.","recommendedAction":"Use as the primary candidate after human or sandbox review.","decision":{"install_policy":"human_review_before_install","auto_install_allowed":false,"human_review_required":true,"sandbox_first":true,"agent_action":"Ask for approval or run a sandbox-only trial before installing.","reasoning":["79/100 Trust Score v5","84/100 Trust Score v4 baseline","Needs more real agent outcomes before unattended install","Install path is available","Low metadata risk"],"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":100,"weight":0.13,"status":"pass","detail":"34K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":97,"weight":0.08,"status":"pass","detail":"34K stars, 3.3K forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":100,"weight":0.14,"status":"pass","detail":"2d since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"MIT license"},{"id":"documentation","label":"README/SKILL.md completeness","score":76,"weight":0.14,"status":"info","detail":"Public metadata needs stronger README/SKILL.md context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":72,"weight":0.12,"status":"info","detail":"command execution surface"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add K-Dense-AI/scientific-agent-skills --skill arbor"},{"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":62,"weight":0.07,"status":"info","detail":"shell or command execution, filesystem or document access"},{"id":"repository","label":"Repository evidence","score":86,"weight":0.04,"status":"pass","detail":"https://github.com/K-Dense-AI/scientific-agent-skills/tree/main/skills/arbor"},{"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":"pass","label":"GitHub adoption","detail":"34K GitHub stars"},{"status":"pass","label":"Stars/forks activity","detail":"34K stars, 3.3K forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"2d since push"},{"status":"pass","label":"License clarity","detail":"MIT license"},{"status":"info","label":"README/SKILL.md completeness","detail":"Public metadata needs stronger README/SKILL.md context"},{"status":"info","label":"Dependency/runtime risk","detail":"command execution surface"},{"status":"pass","label":"Install availability","detail":"npx skills add K-Dense-AI/scientific-agent-skills --skill arbor"},{"status":"pass","label":"Install command safety","detail":"standard package or runtime install path"},{"status":"info","label":"Permission surface","detail":"shell or command execution, filesystem or document access"},{"status":"pass","label":"Repository evidence","detail":"https://github.com/K-Dense-AI/scientific-agent-skills/tree/main/skills/arbor"},{"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":"pass","label":"OpenAgentSkill usage","detail":"19 views, 0 install copies"},{"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","Large GitHub adoption signal","Install command has no obvious high-risk pattern","Outcome loop is ready but needs first real agent run"],"warnings":["No real agent outcome reports yet","Human review required before unattended installation"],"evidence":{"stars":"34K GitHub stars","repoActivity":"34K stars, 3.3K forks","lastPushed":"2d since push","license":"MIT license","repository":"https://github.com/K-Dense-AI/scientific-agent-skills/tree/main/skills/arbor","install":"npx skills add K-Dense-AI/scientific-agent-skills --skill arbor","installSafety":"standard package or runtime install path","permissionSurface":"shell or command execution, filesystem or document access","documentation":"Usable metadata, review docs","agentOutcomes":"No agent outcome data yet","agentProvenScore":0,"outcomeConfidence":"0%","installPolicy":"human_review_before_install"},"installReadiness":{"ready":true,"command":"npx skills add K-Dense-AI/scientific-agent-skills --skill arbor","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","2d since push","Trust Score v5 requires review or sandbox-only use before install."]},"agentCompatibility":["Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"low","label":"Low metadata risk","notes":["No major trust warnings detected from available metadata"]},"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":"Ask for approval or run a sandbox-only trial before installing."},"outcome_loop":{"version":"openagentskill-agent-outcome-v3","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"],"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 K-Dense-AI/scientific-agent-skills --skill arbor","trust_score":79,"trust_version":"trust-score-v5","risk_level":"low","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"],"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"],"knownRisks":[],"backward_compatible":{"trust_score_v4":{"version":"trust-score-v4","score":84,"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":79,"base_score":84,"outcome_confidence":0,"tier":"strong","label":"Review then install","summary":"Good shortlist signal, but the agent should review audit notes, install policy, and outcome evidence before running it.","recommendedAction":"Use as the primary candidate after human or sandbox review.","decision":{"install_policy":"human_review_before_install","auto_install_allowed":false,"human_review_required":true,"sandbox_first":true,"agent_action":"Ask for approval or run a sandbox-only trial before installing.","reasoning":["79/100 Trust Score v5","84/100 Trust Score v4 baseline","Needs more real agent outcomes before unattended install","Install path is available","Low metadata risk"],"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":100,"weight":0.13,"status":"pass","detail":"34K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":97,"weight":0.08,"status":"pass","detail":"34K stars, 3.3K forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":100,"weight":0.14,"status":"pass","detail":"2d since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"MIT license"},{"id":"documentation","label":"README/SKILL.md completeness","score":76,"weight":0.14,"status":"info","detail":"Public metadata needs stronger README/SKILL.md context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":72,"weight":0.12,"status":"info","detail":"command execution surface"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add K-Dense-AI/scientific-agent-skills --skill arbor"},{"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":62,"weight":0.07,"status":"info","detail":"shell or command execution, filesystem or document access"},{"id":"repository","label":"Repository evidence","score":86,"weight":0.04,"status":"pass","detail":"https://github.com/K-Dense-AI/scientific-agent-skills/tree/main/skills/arbor"},{"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":"pass","label":"GitHub adoption","detail":"34K GitHub stars"},{"status":"pass","label":"Stars/forks activity","detail":"34K stars, 3.3K forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"2d since push"},{"status":"pass","label":"License clarity","detail":"MIT license"},{"status":"info","label":"README/SKILL.md completeness","detail":"Public metadata needs stronger README/SKILL.md context"},{"status":"info","label":"Dependency/runtime risk","detail":"command execution surface"},{"status":"pass","label":"Install availability","detail":"npx skills add K-Dense-AI/scientific-agent-skills --skill arbor"},{"status":"pass","label":"Install command safety","detail":"standard package or runtime install path"},{"status":"info","label":"Permission surface","detail":"shell or command execution, filesystem or document access"},{"status":"pass","label":"Repository evidence","detail":"https://github.com/K-Dense-AI/scientific-agent-skills/tree/main/skills/arbor"},{"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":"pass","label":"OpenAgentSkill usage","detail":"19 views, 0 install copies"},{"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","Large GitHub adoption signal","Install command has no obvious high-risk pattern","Outcome loop is ready but needs first real agent run"],"warnings":["No real agent outcome reports yet","Human review required before unattended installation"],"evidence":{"stars":"34K GitHub stars","repoActivity":"34K stars, 3.3K forks","lastPushed":"2d since push","license":"MIT license","repository":"https://github.com/K-Dense-AI/scientific-agent-skills/tree/main/skills/arbor","install":"npx skills add K-Dense-AI/scientific-agent-skills --skill arbor","installSafety":"standard package or runtime install path","permissionSurface":"shell or command execution, filesystem or document access","documentation":"Usable metadata, review docs","agentOutcomes":"No agent outcome data yet","agentProvenScore":0,"outcomeConfidence":"0%","installPolicy":"human_review_before_install"},"installReadiness":{"ready":true,"command":"npx skills add K-Dense-AI/scientific-agent-skills --skill arbor","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","2d since push","Trust Score v5 requires review or sandbox-only use before install."]},"agentCompatibility":["Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"low","label":"Low metadata risk","notes":["No major trust warnings detected from available metadata"]},"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":"Ask for approval or run a sandbox-only trial before installing."},"outcome_loop":{"version":"openagentskill-agent-outcome-v3","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"],"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 K-Dense-AI/scientific-agent-skills --skill arbor","trust_score":79,"trust_version":"trust-score-v5","risk_level":"low","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"],"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"],"knownRisks":[],"backward_compatible":{"trust_score_v4":{"version":"trust-score-v4","score":84,"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":84,"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":100,"weight":0.13,"status":"pass","detail":"34K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":97,"weight":0.08,"status":"pass","detail":"34K stars, 3.3K forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":100,"weight":0.14,"status":"pass","detail":"2d since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"MIT license"},{"id":"documentation","label":"README/SKILL.md completeness","score":76,"weight":0.14,"status":"info","detail":"Public metadata needs stronger README/SKILL.md context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":72,"weight":0.12,"status":"info","detail":"command execution surface"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add K-Dense-AI/scientific-agent-skills --skill arbor"},{"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":62,"weight":0.07,"status":"info","detail":"shell or command execution, filesystem or document access"},{"id":"repository","label":"Repository evidence","score":86,"weight":0.04,"status":"pass","detail":"https://github.com/K-Dense-AI/scientific-agent-skills/tree/main/skills/arbor"},{"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":"pass","label":"GitHub adoption","detail":"34K GitHub stars"},{"status":"pass","label":"Stars/forks activity","detail":"34K stars, 3.3K forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"2d since push"},{"status":"pass","label":"License clarity","detail":"MIT license"},{"status":"info","label":"README/SKILL.md completeness","detail":"Public metadata needs stronger README/SKILL.md context"},{"status":"info","label":"Dependency/runtime risk","detail":"command execution surface"},{"status":"pass","label":"Install availability","detail":"npx skills add K-Dense-AI/scientific-agent-skills --skill arbor"},{"status":"pass","label":"Install command safety","detail":"standard package or runtime install path"},{"status":"info","label":"Permission surface","detail":"shell or command execution, filesystem or document access"},{"status":"pass","label":"Repository evidence","detail":"https://github.com/K-Dense-AI/scientific-agent-skills/tree/main/skills/arbor"},{"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":"pass","label":"OpenAgentSkill usage","detail":"19 views, 0 install copies"},{"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","Large GitHub adoption signal","Install command has no obvious high-risk pattern"],"warnings":[],"evidence":{"stars":"34K GitHub stars","repoActivity":"34K stars, 3.3K forks","lastPushed":"2d since push","license":"MIT license","repository":"https://github.com/K-Dense-AI/scientific-agent-skills/tree/main/skills/arbor","install":"npx skills add K-Dense-AI/scientific-agent-skills --skill arbor","installSafety":"standard package or runtime install path","permissionSurface":"shell or command execution, filesystem or document access","documentation":"Usable metadata, review docs","agentOutcomes":"No agent outcome data yet"},"installReadiness":{"ready":true,"command":"npx skills add K-Dense-AI/scientific-agent-skills --skill arbor","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","2d since push"]},"agentCompatibility":["Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"low","label":"Low metadata risk","notes":["No major trust warnings detected from available metadata"]},"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"],"knownRisks":[]},"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":61,"level":"review_before_install","label":"Review before install","safety_tier":{"tier":"reviewed","label":"Reviewed with permission notes","badge":"REVIEWED","summary":"Usable candidate, but the agent should surface permission and audit notes before installation.","recommended_action":"Require human approval before installing into a real workspace.","auto_install_policy":"review","reasons":["High-risk permission hints: Shell or command execution","61/100 agent safety score"]},"auto_install_allowed":false,"human_review_required":true,"blocked":false,"audit_risk":"safe_to_try","permission_hints":[{"id":"shell","label":"Shell or command execution","reason":"Skill metadata references terminal, CLI, shell, subprocess, or command execution workflows.","severity":"high"},{"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"}],"policy_warnings":["High-risk permission hints: Shell or command execution"],"constraints_applied":{"max_risk":"medium","needs_install_command":true,"min_stars":0}},"safety_gate":{"tier":"reviewed","label":"Reviewed with permission notes","badge":"REVIEWED","auto_install_policy":"review","auto_install_allowed":false,"blocked":false,"human_review_required":true,"recommended_action":"Require human approval before installing into a real workspace.","reasons":["High-risk permission hints: Shell or command execution","61/100 agent safety score"]},"eval":{"version":"openagentskill-skill-eval-v1","status":"review","score":82,"risk_level":"medium","decision":{"recommendation":"manual_review","reason":"Require human approval before installing into a real workspace.","auto_install_allowed":false,"policy":"review","human_review_required":true},"blockers":[],"warnings":["Agent safety gate: Usable candidate, but the agent should surface permission and audit notes before installation.","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context","Permission surface: shell or command execution, filesystem or document access","High-risk permission hints: 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":84,"required_for_auto_install":true,"detail":"Task wording matches this skill metadata.","evidence":["Evaluate arbor before installing it in an agent workflow","research","Research agents workflows; Claude Code teams; teams that value GitHub adoption signals"]},{"id":"install_path","label":"Install path","status":"pass","score":92,"required_for_auto_install":true,"detail":"Install handoff is available.","evidence":["npx skills add K-Dense-AI/scientific-agent-skills --skill arbor"]},{"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 K-Dense-AI/scientific-agent-skills --skill arbor"]},{"id":"trust_score","label":"Trust score","status":"pass","score":84,"required_for_auto_install":true,"detail":"Good trust signals with a few areas worth checking before rollout.","evidence":["Strong shortlist","34K GitHub stars","MIT license"]},{"id":"audit_score","label":"Audit score","status":"pass","score":89,"required_for_auto_install":true,"detail":"Safe to try","evidence":["No major audit warning from metadata."]},{"id":"agent_safety_gate","label":"Agent safety gate","status":"warn","score":61,"required_for_auto_install":true,"detail":"Usable candidate, but the agent should surface permission and audit notes before installation.","evidence":["Require human approval before installing into a real workspace.","High-risk permission hints: Shell or command execution"]},{"id":"readme_skillmd_completeness","label":"README/SKILL.md completeness","status":"warn","score":76,"required_for_auto_install":false,"detail":"Public metadata needs stronger README/SKILL.md context","evidence":["Usable metadata, review docs"]},{"id":"license_clarity","label":"License clarity","status":"pass","score":86,"required_for_auto_install":true,"detail":"MIT license","evidence":["MIT license"]},{"id":"recent_maintenance","label":"Recent maintenance","status":"pass","score":100,"required_for_auto_install":false,"detail":"2d since push","evidence":["2d since push"]},{"id":"permission_surface","label":"Permission surface","status":"warn","score":62,"required_for_auto_install":true,"detail":"shell or command execution, filesystem or document access","evidence":["Shell or command execution: high","Network access: medium","Filesystem 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/k-dense-ai-arbor/evals","api":"/api/agent/evals?slug=k-dense-ai-arbor","text":"/api/agent/evals?slug=k-dense-ai-arbor&format=text"}},"agent_readable_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"k-dense-ai-arbor","name":"arbor","description":"Autonomously improve a real artifact (code, training recipe, agent harness, data pipeline, prompt) against an objective and an evaluator, using Hypothesis Tree Refinement (HTR) from the Arbor paper. Use this whenever someone wants to iteratively optimize something over many experiments without overfitting — e.g. \"get my model's eval score up\", \"improve this agent/harness\", \"tune this pipeline\", \"beat the baseline on this benchmark\", \"run a search over approaches and keep the best\", \"do an MLE-bench / Kaggle-style optimization\", or any long-horizon \"make this artifact better and don't just memorize the dev set\" task. Trigger it even when the user doesn't say \"Arbor\" or \"hypothesis tree\" but describes repeated experiment-and-evaluate loops, branching exploration of competing ideas, or worries about a dev/test gap. Runs Claude itself as the coordinator with subagent executors in isolated git worktrees; for the standalone `arbor` CLI tool see references/arbor-upstream.md.","category":"research","url":"https://www.openagentskill.com/skills/k-dense-ai-arbor","repository":"https://github.com/K-Dense-AI/scientific-agent-skills/tree/main/skills/arbor","github_repo":"K-Dense-AI/scientific-agent-skills"},"suited_tasks":["Research agents workflows","Claude Code teams","teams that value GitHub adoption signals","Search sources","Extract claims","Synthesize findings","Chunk documents","Create embeddings"],"suited_agents":["Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add K-Dense-AI/scientific-agent-skills --skill arbor","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install k-dense-ai-arbor"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"arbor\" agent skill from https://github.com/K-Dense-AI/scientific-agent-skills/tree/main/skills/arbor. 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: Autonomously improve a real artifact (code, training recipe, agent harness, data pipeline, prompt) against an objective and an evaluator, using Hypothesis Tree Refinement (HTR) from the Arbor paper. Use this whenever someone wants to iteratively optimize something over many experiments without overfitting — e.g. \"get my model's eval score up\", \"improve this agent/harness\", \"tune this pipeline\", \"beat the baseline on this benchmark\", \"run a search over approaches and keep the best\", \"do an MLE-bench / Kaggle-style optimization\", or any long-horizon \"make this artifact better and don't just memorize the dev set\" task. Trigger it even when the user doesn't say \"Arbor\" or \"hypothesis tree\" but describes repeated experiment-and-evaluate loops, branching exploration of competing ideas, or worries about a dev/test gap. Runs Claude itself as the coordinator with subagent executors in isolated git worktrees; for the standalone `arbor` CLI tool see references/arbor-upstream.md. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"k-dense-ai-arbor\",\"task\":\"Install arbor\",\"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 \"arbor\" as a Claude Code skill from https://github.com/K-Dense-AI/scientific-agent-skills/tree/main/skills/arbor. 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: Autonomously improve a real artifact (code, training recipe, agent harness, data pipeline, prompt) against an objective and an evaluator, using Hypothesis Tree Refinement (HTR) from the Arbor paper. Use this whenever someone wants to iteratively optimize something over many experiments without overfitting — e.g. \"get my model's eval score up\", \"improve this agent/harness\", \"tune this pipeline\", \"beat the baseline on this benchmark\", \"run a search over approaches and keep the best\", \"do an MLE-bench / Kaggle-style optimization\", or any long-horizon \"make this artifact better and don't just memorize the dev set\" task. Trigger it even when the user doesn't say \"Arbor\" or \"hypothesis tree\" but describes repeated experiment-and-evaluate loops, branching exploration of competing ideas, or worries about a dev/test gap. Runs Claude itself as the coordinator with subagent executors in isolated git worktrees; for the standalone `arbor` CLI tool see references/arbor-upstream.md. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"k-dense-ai-arbor\",\"task\":\"Install arbor\",\"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 \"arbor\" from https://github.com/K-Dense-AI/scientific-agent-skills/tree/main/skills/arbor 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: Autonomously improve a real artifact (code, training recipe, agent harness, data pipeline, prompt) against an objective and an evaluator, using Hypothesis Tree Refinement (HTR) from the Arbor paper. Use this whenever someone wants to iteratively optimize something over many experiments without overfitting — e.g. \"get my model's eval score up\", \"improve this agent/harness\", \"tune this pipeline\", \"beat the baseline on this benchmark\", \"run a search over approaches and keep the best\", \"do an MLE-bench / Kaggle-style optimization\", or any long-horizon \"make this artifact better and don't just memorize the dev set\" task. Trigger it even when the user doesn't say \"Arbor\" or \"hypothesis tree\" but describes repeated experiment-and-evaluate loops, branching exploration of competing ideas, or worries about a dev/test gap. Runs Claude itself as the coordinator with subagent executors in isolated git worktrees; for the standalone `arbor` CLI tool see references/arbor-upstream.md. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"k-dense-ai-arbor\",\"task\":\"Install arbor\",\"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/k-dense-ai-arbor/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/k-dense-ai-arbor"},"trust":{"score":84,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"34K GitHub stars","repoActivity":"34K stars, 3.3K forks","lastPushed":"2d since push","license":"MIT license","repository":"https://github.com/K-Dense-AI/scientific-agent-skills/tree/main/skills/arbor","install":"npx skills add K-Dense-AI/scientific-agent-skills --skill arbor","installSafety":"standard package or runtime install path","permissionSurface":"shell or command execution, filesystem or document access","documentation":"Usable metadata, review docs","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":[]},"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":89,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":[]},"safety_gate":{"tier":"reviewed","label":"Reviewed with permission notes","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Require human approval before installing into a real workspace."},"quality":{"score":92,"label":"Excellent"},"supply":{"track":"Research and knowledge work","scenario":"Research agents","maintenance":"2d since push","risk":"Safe to try"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No major risk signals from current metadata","High-risk permission hints: Shell or command execution","No major trust warnings detected from available metadata","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"],"agent_contract":{"task_input":"Use arbor in an agent workflow","recommended_action":"Require human approval before installing into a real workspace.","install_policy":"review","minimum_review_before_use":["Trust: 84/100 Strong shortlist","Audit: 89/100 Safe to try","Safety: 61/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"k-dense-ai-arbor (arbor)","install_command":"npx skills add K-Dense-AI/scientific-agent-skills --skill arbor","risk_summary":"Safe to try; Reviewed with permission notes; Low metadata risk","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":"<install_receipt.outcome_feedback.event_id or feedback.event_id from /api/agent/resolve>","skill_slug":"k-dense-ai-arbor","task":"Use arbor 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/k-dense-ai-arbor","api":"https://www.openagentskill.com/api/agent/skills/k-dense-ai-arbor","audit":"https://www.openagentskill.com/skills/k-dense-ai-arbor/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=k-dense-ai-arbor&task=Use%20arbor%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20arbor%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20arbor%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/k-dense-ai-arbor/install","manifest":"https://www.openagentskill.com/api/registry/manifest/k-dense-ai-arbor"}},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"k-dense-ai-arbor","name":"arbor","description":"Autonomously improve a real artifact (code, training recipe, agent harness, data pipeline, prompt) against an objective and an evaluator, using Hypothesis Tree Refinement (HTR) from the Arbor paper. Use this whenever someone wants to iteratively optimize something over many experiments without overfitting — e.g. \"get my model's eval score up\", \"improve this agent/harness\", \"tune this pipeline\", \"beat the baseline on this benchmark\", \"run a search over approaches and keep the best\", \"do an MLE-bench / Kaggle-style optimization\", or any long-horizon \"make this artifact better and don't just memorize the dev set\" task. Trigger it even when the user doesn't say \"Arbor\" or \"hypothesis tree\" but describes repeated experiment-and-evaluate loops, branching exploration of competing ideas, or worries about a dev/test gap. Runs Claude itself as the coordinator with subagent executors in isolated git worktrees; for the standalone `arbor` CLI tool see references/arbor-upstream.md.","category":"research","url":"https://www.openagentskill.com/skills/k-dense-ai-arbor","repository":"https://github.com/K-Dense-AI/scientific-agent-skills/tree/main/skills/arbor","github_repo":"K-Dense-AI/scientific-agent-skills"},"suited_tasks":["Research agents workflows","Claude Code teams","teams that value GitHub adoption signals","Search sources","Extract claims","Synthesize findings","Chunk documents","Create embeddings"],"suited_agents":["Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add K-Dense-AI/scientific-agent-skills --skill arbor","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install k-dense-ai-arbor"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"arbor\" agent skill from https://github.com/K-Dense-AI/scientific-agent-skills/tree/main/skills/arbor. 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: Autonomously improve a real artifact (code, training recipe, agent harness, data pipeline, prompt) against an objective and an evaluator, using Hypothesis Tree Refinement (HTR) from the Arbor paper. Use this whenever someone wants to iteratively optimize something over many experiments without overfitting — e.g. \"get my model's eval score up\", \"improve this agent/harness\", \"tune this pipeline\", \"beat the baseline on this benchmark\", \"run a search over approaches and keep the best\", \"do an MLE-bench / Kaggle-style optimization\", or any long-horizon \"make this artifact better and don't just memorize the dev set\" task. Trigger it even when the user doesn't say \"Arbor\" or \"hypothesis tree\" but describes repeated experiment-and-evaluate loops, branching exploration of competing ideas, or worries about a dev/test gap. Runs Claude itself as the coordinator with subagent executors in isolated git worktrees; for the standalone `arbor` CLI tool see references/arbor-upstream.md. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"k-dense-ai-arbor\",\"task\":\"Install arbor\",\"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 \"arbor\" as a Claude Code skill from https://github.com/K-Dense-AI/scientific-agent-skills/tree/main/skills/arbor. 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: Autonomously improve a real artifact (code, training recipe, agent harness, data pipeline, prompt) against an objective and an evaluator, using Hypothesis Tree Refinement (HTR) from the Arbor paper. Use this whenever someone wants to iteratively optimize something over many experiments without overfitting — e.g. \"get my model's eval score up\", \"improve this agent/harness\", \"tune this pipeline\", \"beat the baseline on this benchmark\", \"run a search over approaches and keep the best\", \"do an MLE-bench / Kaggle-style optimization\", or any long-horizon \"make this artifact better and don't just memorize the dev set\" task. Trigger it even when the user doesn't say \"Arbor\" or \"hypothesis tree\" but describes repeated experiment-and-evaluate loops, branching exploration of competing ideas, or worries about a dev/test gap. Runs Claude itself as the coordinator with subagent executors in isolated git worktrees; for the standalone `arbor` CLI tool see references/arbor-upstream.md. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"k-dense-ai-arbor\",\"task\":\"Install arbor\",\"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 \"arbor\" from https://github.com/K-Dense-AI/scientific-agent-skills/tree/main/skills/arbor 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: Autonomously improve a real artifact (code, training recipe, agent harness, data pipeline, prompt) against an objective and an evaluator, using Hypothesis Tree Refinement (HTR) from the Arbor paper. Use this whenever someone wants to iteratively optimize something over many experiments without overfitting — e.g. \"get my model's eval score up\", \"improve this agent/harness\", \"tune this pipeline\", \"beat the baseline on this benchmark\", \"run a search over approaches and keep the best\", \"do an MLE-bench / Kaggle-style optimization\", or any long-horizon \"make this artifact better and don't just memorize the dev set\" task. Trigger it even when the user doesn't say \"Arbor\" or \"hypothesis tree\" but describes repeated experiment-and-evaluate loops, branching exploration of competing ideas, or worries about a dev/test gap. Runs Claude itself as the coordinator with subagent executors in isolated git worktrees; for the standalone `arbor` CLI tool see references/arbor-upstream.md. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"k-dense-ai-arbor\",\"task\":\"Install arbor\",\"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/k-dense-ai-arbor/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/k-dense-ai-arbor"},"trust":{"score":84,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"34K GitHub stars","repoActivity":"34K stars, 3.3K forks","lastPushed":"2d since push","license":"MIT license","repository":"https://github.com/K-Dense-AI/scientific-agent-skills/tree/main/skills/arbor","install":"npx skills add K-Dense-AI/scientific-agent-skills --skill arbor","installSafety":"standard package or runtime install path","permissionSurface":"shell or command execution, filesystem or document access","documentation":"Usable metadata, review docs","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":[]},"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":89,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":[]},"safety_gate":{"tier":"reviewed","label":"Reviewed with permission notes","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Require human approval before installing into a real workspace."},"quality":{"score":92,"label":"Excellent"},"supply":{"track":"Research and knowledge work","scenario":"Research agents","maintenance":"2d since push","risk":"Safe to try"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No major risk signals from current metadata","High-risk permission hints: Shell or command execution","No major trust warnings detected from available metadata","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"],"agent_contract":{"task_input":"Use arbor in an agent workflow","recommended_action":"Require human approval before installing into a real workspace.","install_policy":"review","minimum_review_before_use":["Trust: 84/100 Strong shortlist","Audit: 89/100 Safe to try","Safety: 61/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"k-dense-ai-arbor (arbor)","install_command":"npx skills add K-Dense-AI/scientific-agent-skills --skill arbor","risk_summary":"Safe to try; Reviewed with permission notes; Low metadata risk","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":"<install_receipt.outcome_feedback.event_id or feedback.event_id from /api/agent/resolve>","skill_slug":"k-dense-ai-arbor","task":"Use arbor 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/k-dense-ai-arbor","api":"https://www.openagentskill.com/api/agent/skills/k-dense-ai-arbor","audit":"https://www.openagentskill.com/skills/k-dense-ai-arbor/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=k-dense-ai-arbor&task=Use%20arbor%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20arbor%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20arbor%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/k-dense-ai-arbor/install","manifest":"https://www.openagentskill.com/api/registry/manifest/k-dense-ai-arbor"}},"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":"rag-knowledge","title":"RAG and knowledge"},{"slug":"browser-automation","title":"Browser automation"}]},"applicableAgents":["Claude Code","CLI","Codex","Cursor"],"install":{"ready":true,"command":"npx skills add K-Dense-AI/scientific-agent-skills --skill arbor","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":33974,"starsLabel":"34K","forks":3307,"license":"MIT license","qualityScore":92,"trustScore":84,"auditScore":89},"maintenance":{"status":"fresh","label":"2d since push","daysSincePush":2,"lastPushedAt":"2026-08-20T13:03:17+00:00"},"risk":{"level":"safe_to_try","label":"Safe to try","requiresReview":false,"notes":["No major risk signals from available metadata"]},"coverageTags":["Research","Research agents","agent-skill"]},"audit":{"audit_score":89,"risk_level":"safe_to_try","risk_label":"Safe to try","quality_score":92,"trust_score":84,"maintenance_score":100,"security_score":83,"install_score":92,"warnings":[]},"quality_signals":{"model":"v2","star_score":31.72,"usage_score":0,"review_score":5.4,"metadata_score":3,"freshness_score":15},"platforms":["Claude Code"],"use_cases":[{"slug":"research-agents","title":"Research agents","url":"https://www.openagentskill.com/use-cases/research-agents"},{"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"},{"slug":"github-automation","title":"GitHub automation","url":"https://www.openagentskill.com/use-cases/github-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 K-Dense-AI/scientific-agent-skills --skill arbor","install_targets":[{"id":"openagentskill-cli","label":"CLI","title":"OpenAgentSkill CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install k-dense-ai-arbor","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 \"arbor\" agent skill from https://github.com/K-Dense-AI/scientific-agent-skills/tree/main/skills/arbor. 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: Autonomously improve a real artifact (code, training recipe, agent harness, data pipeline, prompt) against an objective and an evaluator, using Hypothesis Tree Refinement (HTR) from the Arbor paper. Use this whenever someone wants to iteratively optimize something over many experiments without overfitting — e.g. \"get my model's eval score up\", \"improve this agent/harness\", \"tune this pipeline\", \"beat the baseline on this benchmark\", \"run a search over approaches and keep the best\", \"do an MLE-bench / Kaggle-style optimization\", or any long-horizon \"make this artifact better and don't just memorize the dev set\" task. Trigger it even when the user doesn't say \"Arbor\" or \"hypothesis tree\" but describes repeated experiment-and-evaluate loops, branching exploration of competing ideas, or worries about a dev/test gap. Runs Claude itself as the coordinator with subagent executors in isolated git worktrees; for the standalone `arbor` CLI tool see references/arbor-upstream.md. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"k-dense-ai-arbor\",\"task\":\"Install arbor\",\"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 \"arbor\" as a Claude Code skill from https://github.com/K-Dense-AI/scientific-agent-skills/tree/main/skills/arbor. 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: Autonomously improve a real artifact (code, training recipe, agent harness, data pipeline, prompt) against an objective and an evaluator, using Hypothesis Tree Refinement (HTR) from the Arbor paper. Use this whenever someone wants to iteratively optimize something over many experiments without overfitting — e.g. \"get my model's eval score up\", \"improve this agent/harness\", \"tune this pipeline\", \"beat the baseline on this benchmark\", \"run a search over approaches and keep the best\", \"do an MLE-bench / Kaggle-style optimization\", or any long-horizon \"make this artifact better and don't just memorize the dev set\" task. Trigger it even when the user doesn't say \"Arbor\" or \"hypothesis tree\" but describes repeated experiment-and-evaluate loops, branching exploration of competing ideas, or worries about a dev/test gap. Runs Claude itself as the coordinator with subagent executors in isolated git worktrees; for the standalone `arbor` CLI tool see references/arbor-upstream.md. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"k-dense-ai-arbor\",\"task\":\"Install arbor\",\"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 \"arbor\" from https://github.com/K-Dense-AI/scientific-agent-skills/tree/main/skills/arbor 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: Autonomously improve a real artifact (code, training recipe, agent harness, data pipeline, prompt) against an objective and an evaluator, using Hypothesis Tree Refinement (HTR) from the Arbor paper. Use this whenever someone wants to iteratively optimize something over many experiments without overfitting — e.g. \"get my model's eval score up\", \"improve this agent/harness\", \"tune this pipeline\", \"beat the baseline on this benchmark\", \"run a search over approaches and keep the best\", \"do an MLE-bench / Kaggle-style optimization\", or any long-horizon \"make this artifact better and don't just memorize the dev set\" task. Trigger it even when the user doesn't say \"Arbor\" or \"hypothesis tree\" but describes repeated experiment-and-evaluate loops, branching exploration of competing ideas, or worries about a dev/test gap. Runs Claude itself as the coordinator with subagent executors in isolated git worktrees; for the standalone `arbor` CLI tool see references/arbor-upstream.md. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"k-dense-ai-arbor\",\"task\":\"Install arbor\",\"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/K-Dense-AI/scientific-agent-skills/tree/main/skills/arbor","github_repo":"K-Dense-AI/scientific-agent-skills","version":"1.0.0","license":"MIT license","urls":{"web":"https://www.openagentskill.com/skills/k-dense-ai-arbor","repository":"https://github.com/K-Dense-AI/scientific-agent-skills/tree/main/skills/arbor","api":"/api/agent/skills/k-dense-ai-arbor","install_api":"/api/skills/k-dense-ai-arbor/install"},"meta":{"created_at":"2026-08-20T13:23:03.593529+00:00","updated_at":"2026-08-20T13:23:03.593529+00:00","agent_friendly":true}}