Skill audit report
提问驱动自主学习的归纳 skill（v0.9.7）。自动触发为主：每 3-5 次 skill 会话，postamble 自动跑一轮归纳——读 .learning/question-ledger.jsonl 增量，按"问题回家"原则聚类（问模型的问法反补 sm-model-check、问复盘的反补 sm-close-recap），过阈值（≥3 次 · ≥2 标的 · ≥2 天）与三重冲突检查后自动生效进试用期（每轮 ≤3 条），会话尾一行摘要告知，用户保留"撤销 L-xxx"否决权。手动触发用于：mentor 导入（"把这些问题学进去"）、审计（"看看学了什么"）、撤销/恢复、强制归纳（"归纳提问"）。绝不修改 harness 主库，绝不覆盖证据分级 / 合规 / 数据源硬约束。
The Trust Score helps an agent decide whether a skill is safe enough to shortlist before installation.
GitHub adoption
WARN48
25 GitHub stars
Stars/forks activity
WARN43
25 stars, 2 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 joansongjr/investor-harness --skill sm-learn
Install command safety
PASS92
standard package or runtime install path
Permission surface
PASS86
filesystem or document access
Repository evidence
PASS86
https://github.com/joansongjr/investor-harness/tree/main/skills/sm-learn
Review status
WARN46
AI review approval is missing
Agent Proven outcomes
INFO54
No agent outcome data yet
Checks
Install path
92
npx skills add joansongjr/investor-harness --skill sm-learn
Repository
88
https://github.com/joansongjr/investor-harness/tree/main/skills/sm-learn
License
86
MIT
Maintenance
100
16d since push
AI review
55
Review approval is missing
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
86
filesystem or document access
Stars/forks activity
43
25 stars, 2 forks; issue activity unavailable in current metadata
Adoption
42
25 GitHub stars
Financial decision safety
58
Research-only use: do not treat output as financial advice or execute a position without human approval.
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.
Compare nearby options