Skill audit report
从 WorkBuddy、Claude Code 或其他本地 Agent 无头调用 Codex App Server，创建可见、命名、持久的 Codex Thread，并执行继续追问、状态查询、结果取回、取消和打开。用于复杂研究、跨项目取材、章节审校、确定性工程或重要决策；一次性格式检查和无需保留上下文的小提取继续用 codex exec --ephemeral，Codex 内部组队不走本 Skill。
OpenAgentSkill Trust Score
The Trust Score helps an agent decide whether a skill is safe enough to shortlist before installation.
GitHub adoption
INFO76
576 GitHub stars
Stars/forks activity
INFO71
576 stars, 61 forks; issue activity unavailable in current metadata
Recent maintenance
PASS100
3d since push
License clarity
PASS86
MIT
README/SKILL.md completeness
INFO76
Public metadata needs stronger README/SKILL.md context
Dependency/runtime risk
INFO72
command execution surface
Install availability
PASS92
npx skills add zjp1997720/zhijian-skills --skill codex-external-handoff
Install command safety
PASS92
standard package or runtime install path
Permission surface
INFO62
shell or command execution, filesystem or document access
Repository evidence
PASS86
https://github.com/zjp1997720/zhijian-skills/tree/main/skills/codex-external-handoff
Review status
INFO66
AI review data available
Agent Proven outcomes
INFO54
No agent outcome data yet
Checks
Install path
92
npx skills add zjp1997720/zhijian-skills --skill codex-external-handoff
Repository
88
https://github.com/zjp1997720/zhijian-skills/tree/main/skills/codex-external-handoff
License
86
MIT
Maintenance
100
3d since push
AI review
55
The skill is primarily documented in Chinese; English users may need translation, but the core commands and structure are clear.
README/SKILL.md completeness
84
Usable description available
Dependency risk
72
command execution surface
Install command safety
92
standard package or runtime install path
Permission surface
62
shell or command execution, filesystem or document access
Stars/forks activity
71
576 stars, 61 forks; issue activity unavailable in current metadata
Adoption
88
576 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.