Skill audit report
Speak Human Tw audit report.
A skill for AI agents (Claude Code, Codex, Cursor) that rewrites Traditional Chinese text to remove AI writing patterns, correct China-Taiwan localization, and fix punctuation.
OpenAgentSkill Trust Score
Stars, maintenance, license, docs, install safety, permission surface, and installability.
The Trust Score is OpenAgentSkill's adoption layer. It is designed to help an agent decide whether a skill is safe enough to shortlist before installation.
GitHub adoption
INFO76
691 GitHub stars
Stars/forks activity
INFO71
691 stars, 79 forks; issue activity unavailable in current metadata
Recent maintenance
PASS100
4d since push
License clarity
PASS86
MIT
README/SKILL.md completeness
PASS100
Metadata includes enough usage and workflow context
Dependency/runtime risk
PASS90
no major dependency risk hints in public metadata
Install availability
PASS92
npx skills add Raymondhou0917/speak-human-tw
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/Raymondhou0917/speak-human-tw
Review status
PASS88
AI review data available
Agent Proven outcomes
INFO54
No agent outcome data yet
Checks
Install and adoption review
Install path
92
npx skills add Raymondhou0917/speak-human-tw
Repository
88
https://github.com/Raymondhou0917/speak-human-tw
License
86
MIT
Maintenance
100
4d since push
AI review
88
Approved with no listed issues
README/SKILL.md completeness
100
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
71
691 stars, 79 forks; issue activity unavailable in current metadata
Adoption
88
691 GitHub stars
Warnings
No major warnings detected from available metadata.
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