Skill audit report
Run a what-if social experiment — inject a policy, event, or information shock and observe how a simulated population responds. Use for hypothesis generation (not ground truth) on questions like "what if minimum wage doubled", "how would users react if we added feature X", "which demographics push back first". Triggers on 社会实验, 沙盒模拟, what-if, 如果 X 发生了会怎样, 反事实模拟, counterfactual experiment.
OpenAgentSkill Trust Score
The Trust Score helps an agent decide whether a skill is safe enough to shortlist before installation.
GitHub adoption
WARN48
34 GitHub stars
Stars/forks activity
WARN43
34 stars, 6 forks; issue activity unavailable in current metadata
Recent maintenance
PASS100
Pushed today
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 Yrzhe/claude-skills --skill social-sandbox
Install command safety
PASS92
standard package or runtime install path
Permission surface
PASS86
network or browser access
Repository evidence
PASS86
https://github.com/Yrzhe/claude-skills/tree/main/plugins/persona-sim/skills/social-sandbox
Review status
WARN46
AI review approval is missing
Agent Proven outcomes
INFO54
No agent outcome data yet
Checks
Install path
92
npx skills add Yrzhe/claude-skills --skill social-sandbox
Repository
88
https://github.com/Yrzhe/claude-skills/tree/main/plugins/persona-sim/skills/social-sandbox
License
86
MIT
Maintenance
100
Pushed today
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
network or browser access
Stars/forks activity
43
34 stars, 6 forks; issue activity unavailable in current metadata
Adoption
42
34 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
List, configure, authenticate, call, and inspect MCP servers/tools with mcporter over HTTP or stdio.
391K Stars · Audit report
>-
73K Stars · Audit report
Create a new skill in the current repository. Use when the user wants to create/add a new skill, or mentions creating a skill from scratch. This skill follows the workflow defined in .agents/skills/README.md and helps scaffold, validate, and sync new skills.
52K Stars · Audit report