OpenAgentSkill Resolve API Task: find the right skill Policy: human_review_required Recommendation: Best skill: pathfinder (thedotmack-pathfinder) URL: https://www.openagentskill.com/skills/thedotmack-pathfinder Repository: https://github.com/thedotmack/claude-mem/tree/main/plugin/skills/pathfinder Install: npx skills add thedotmack/claude-mem --skill pathfinder Install policy: review Trust Score v5: 77/100 Review then install Trust decision: Ask for approval or run a sandbox-only trial before installing. Risk: Safe to try; Reviewed; 85/100 Strong shortlist Why: - Matches task terms: find - Strong GitHub adoption: 93,016 stars - Install handoff is available - Repository freshness signal is available - Registry match score 30 - Primary pick for Security and compliance - 77/100 OpenAgentSkill Trust Score v5 - 91/100 audit score Agent instruction: Use pathfinder for: find the right skill Review audit: https://www.openagentskill.com/skills/thedotmack-pathfinder/audit Ask for human approval before installing: npx skills add thedotmack/claude-mem --skill pathfinder If the audit or policy warnings are unacceptable, choose one of the alternatives. Agent contract: - Version: openagentskill-resolve-contract-v2 - Install policy: review - Auto-install allowed: no - Human review required: yes - Audit URL: https://www.openagentskill.com/skills/thedotmack-pathfinder/audit - Do not use when: - teams that need a vendor-supported SLA - high-compliance environments without internal security review - No OpenAgentSkill engagement data yet - Documentation summary is thin Feedback: Event ID: resolve_b6917ec3-8541-4fe5-addb-9c2340e2a856 Outcome API: https://www.openagentskill.com/api/agent/outcome CLI: npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.3.0/openagentskill-0.3.0.tgz outcome "resolve_b6917ec3-8541-4fe5-addb-9c2340e2a856" --skill "thedotmack-pathfinder" --task "find the right skill" --agent "auto" --outcome success Agent Feedback Loop: Version: openagentskill-agent-feedback-loop-v3 Dry run: supported Expected outcomes: success, failed, not_relevant, blocked_by_risk, setup_required Error types: install_failed, runtime_error, not_relevant, permission_blocked, risk_blocked, setup_required, low_quality_output, missing_dependency, timeout, other Workspaces: sandbox, local, ci, production, unknown Updates: Trust Score v5 outcome confidence; Resolve ranking outcome evidence; Skill detail outcome signal block; Outcome leaderboard Install Receipt: OpenAgentSkill Install Receipt Version: openagentskill-install-receipt-v2 Receipt ID: receipt_b6917ec3-8541-4fe5-addb-9c2340e2a856 Resolve event: resolve_b6917ec3-8541-4fe5-addb-9c2340e2a856 Generated: 2026-09-17T04:27:48.886Z Task: find the right skill Agent: auto Selected skill: pathfinder (thedotmack-pathfinder) URL: https://www.openagentskill.com/skills/thedotmack-pathfinder Repository: https://github.com/thedotmack/claude-mem/tree/main/plugin/skills/pathfinder Source version: 1.0.0 Source commit: e5b6719fb9b39c6f2f041c9058a21a79e52d5f1c Source content SHA-256: a3e17bf66e7c2eb198f4b04c06adaff29bf62b7cbd09005c7c234cdcf4ad796b Audit: https://www.openagentskill.com/skills/thedotmack-pathfinder/audit Eval: https://www.openagentskill.com/api/agent/evals?slug=thedotmack-pathfinder&task=find%20the%20right%20skill&max_risk=medium Install: npx skills add thedotmack/claude-mem --skill pathfinder Install policy: review Auto-install allowed: no Human review required: yes Sandbox first: yes Trust: 77/100 Review then install Agent Proven: 0/100 Needs first agent run Audit: 91/100 Safe to try Safety: 79/100 Reviewed Outcome signal: No agent outcome data yet Why selected: - Matches task terms: find - Strong GitHub adoption: 93,016 stars - Install handoff is available - Repository freshness signal is available - Registry match score 30 - Primary pick for Security and compliance - 77/100 Trust Score - 0/100 Agent Proven Score Do not use when: - teams that need a vendor-supported SLA - high-compliance environments without internal security review - No OpenAgentSkill engagement data yet - Documentation summary is thin - README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context - 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 Alternatives: - find-skills (cherryhq-find-skills): npx skills add CherryHQ/cherry-studio --skill find-skills - using-superpowers (obra-using-superpowers): npx skills add obra/superpowers --skill using-superpowers - mem-search (thedotmack-mem-search): npx skills add thedotmack/claude-mem --skill mem-search - smart-explore (thedotmack-smart-explore): npx skills add thedotmack/claude-mem --skill smart-explore Outcome feedback: Endpoint: POST https://www.openagentskill.com/api/agent/outcome Event ID: resolve_b6917ec3-8541-4fe5-addb-9c2340e2a856 CLI: npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.3.0/openagentskill-0.3.0.tgz outcome "resolve_b6917ec3-8541-4fe5-addb-9c2340e2a856" --skill "thedotmack-pathfinder" --task "find the right skill" --agent "auto" --outcome success Next steps: 1. Read the audit page: https://www.openagentskill.com/skills/thedotmack-pathfinder/audit 2. Fetch the pre-install eval: https://www.openagentskill.com/api/agent/evals?slug=thedotmack-pathfinder&task=find%20the%20right%20skill&max_risk=medium 3. Do not auto-install yet. Ask for human review before running: npx skills add thedotmack/claude-mem --skill pathfinder 4. Run one narrow task with no production secrets or irreversible side effects. 5. Report the result to https://www.openagentskill.com/api/agent/outcome using event_id resolve_b6917ec3-8541-4fe5-addb-9c2340e2a856. Decision Packet: Version: openagentskill-agent-decision-packet-v1 Selected: pathfinder (thedotmack-pathfinder) Install: npx skills add thedotmack/claude-mem --skill pathfinder Policy: review Trust: 77/100 Review then install Trust decision: Ask for approval or run a sandbox-only trial before installing. Risk: Safe to try; Reviewed Outcome endpoint: https://www.openagentskill.com/api/agent/outcome Outcome event: resolve_b6917ec3-8541-4fe5-addb-9c2340e2a856 Do not use when: - teams that need a vendor-supported SLA - high-compliance environments without internal security review - No OpenAgentSkill engagement data yet - Documentation summary is thin Alternatives: - find-skills: npx skills add CherryHQ/cherry-studio --skill find-skills - using-superpowers: npx skills add obra/superpowers --skill using-superpowers - mem-search: npx skills add thedotmack/claude-mem --skill mem-search Selected: pathfinder (thedotmack-pathfinder) Match: 30 Supply: Legal / Security and compliance Maintenance: 14d since push Risk: Safe to try Safety: 79/100 Review before install Safety tier: Reviewed Auto-install policy: review Audit: 91/100 Safe to try Install: npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.3.0/openagentskill-0.3.0.tgz add thedotmack-pathfinder URL: https://www.openagentskill.com/skills/thedotmack-pathfinder Why: Matches task terms: find; Strong GitHub adoption: 93,016 stars; Install handoff is available; Repository freshness signal is available; Registry match score 30 Agent Decision: Recommended skill: pathfinder Install command: npx skills add thedotmack/claude-mem --skill pathfinder Safety gate: Reviewed (review) Why recommended: - Matches task terms: find - Strong GitHub adoption: 93,016 stars - Install handoff is available - Repository freshness signal is available - Registry match score 30 - Primary pick for Security and compliance Risk summary: Safe to try; Reviewed; 79/100 Review before install; 85/100 Strong shortlist Risk notes: - Documentation summary is thin - README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context Next steps: - Read the audit URL before installing. - Ask for human approval before installing. - Use install command: npx skills add thedotmack/claude-mem --skill pathfinder - After one narrow task, report the outcome with: npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.3.0/openagentskill-0.3.0.tgz outcome "resolve_b6917ec3-8541-4fe5-addb-9c2340e2a856" --skill "thedotmack-pathfinder" --task "find the right skill" --agent "auto" --outcome success - Summarize output, warnings, files touched, and whether setup or human review was required. Agent Workflow: Action: Review the audit page, then allow agent install in a sandboxed workflow. Install API: https://www.openagentskill.com/api/skills/thedotmack-pathfinder/install Command: npx skills add thedotmack/claude-mem --skill pathfinder Prompt: Task: find the right skill Use pathfinder from https://www.openagentskill.com/skills/thedotmack-pathfinder. Review the audit first: https://www.openagentskill.com/skills/thedotmack-pathfinder/audit Review the eval first: https://www.openagentskill.com/api/agent/evals?slug=thedotmack-pathfinder&task=find%20the%20right%20skill&max_risk=medium Install handoff: https://www.openagentskill.com/api/skills/thedotmack-pathfinder/install Install command: npx skills add thedotmack/claude-mem --skill pathfinder If audit or policy warnings look unsafe for this workspace, use one of the alternatives instead. Review checklist: - Safety tier: Reviewed - Safety score: 79/100 Review before install - Audit score: 91/100 Safe to try - Trust score: 77/100 Review then install - Readiness: 100/100 Production-ready - Documentation summary is thin - Documentation summary is thin - README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context Agent Handoff: Version: openagentskill-agent-handoff-v1 Mode: resolve_compare_review_install Selected skill: pathfinder (thedotmack-pathfinder) Install policy: review Auto-install allowed: no Human review required: yes Platform templates: - Codex: use copy_prompt from agent_handoff.platform_templates.codex - Claude Code: use copy_prompt from agent_handoff.platform_templates.claude-code - Cursor: use copy_prompt from agent_handoff.platform_templates.cursor Blocked actions: - Do not install when safety_gate.blocked is true. - Do not install when the audit or eval reports unacceptable workspace risk. - Do not execute shell commands, access secrets, or call external services without user approval. - Do not keep the skill as an always-on instruction if it only fits a narrow task. Alternatives: 2. find-skills (cherryhq-find-skills) — Reviewed, safety 79/100, audit 91/100 3. using-superpowers (obra-using-superpowers) — Reviewed, safety 79/100, audit 91/100 4. mem-search (thedotmack-mem-search) — Reviewed, safety 75/100, audit 91/100 5. smart-explore (thedotmack-smart-explore) — Reviewed with permission notes, safety 60/100, audit 88/100 Review candidates (not installation recommendations): No review candidates Blocked for auto-install: No blocked candidates