Skill audit report
想法群聊室 — 调研员角色。被 idea-team 主编排器调用，或用户单独说"调研一下 X"、"X 的现状/竞品/数据"、"找 2026 数据"、"事实底"时触发。**用 WebSearch 拉真实 2026 数据、列竞品、引来源——只给事实，不评判，不建议**。Do NOT use when 用户要评价想法好坏（那是反方）、或要跨界启示（那是类比者）、或已有 PRD 在跑（不需要这种调研）。插件内 skill 会由 `idea-coach` namespace 路由；catalog 用户直接按 skill 名调用。
OpenAgentSkill Trust Score
The Trust Score helps an agent decide whether a skill is safe enough to shortlist before installation.
GitHub adoption
INFO62
265 GitHub stars
Stars/forks activity
WARN57
265 stars, 26 forks; issue activity unavailable in current metadata
Recent maintenance
PASS100
16d since push
License clarity
PASS86
MIT
README/SKILL.md completeness
INFO76
Public metadata needs stronger README/SKILL.md context
Dependency/runtime risk
PASS90
no major dependency risk hints in public metadata
Install availability
PASS92
npx skills add majiayu000/spellbook --skill idea-research
Install command safety
PASS92
standard package or runtime install path
Permission surface
PASS100
no high-risk permission surface in public metadata
Repository evidence
PASS86
https://github.com/majiayu000/spellbook/tree/main/plugins/idea-coach/skills/idea-research
Review status
PASS88
AI review data available
Agent Proven outcomes
INFO54
No agent outcome data yet
Checks
Install path
92
npx skills add majiayu000/spellbook --skill idea-research
Repository
88
https://github.com/majiayu000/spellbook/tree/main/plugins/idea-coach/skills/idea-research
License
86
MIT
Maintenance
100
16d since push
AI review
88
Approved with no listed issues
README/SKILL.md completeness
84
Usable description available
Dependency risk
90
no major dependency risk hints in public metadata
Install command safety
92
standard package or runtime install path
Permission surface
100
no high-risk permission surface in public metadata
Stars/forks activity
57
265 stars, 26 forks; issue activity unavailable in current metadata
Adoption
68
265 GitHub stars
Warnings
Method
This report combines public metadata, AI review output, repository freshness, install readiness, OpenAgentSkill events, quality scoring, trust checks, and the agent safety gate. It is not a full source-code security review.