Skill audit report
Issue 池全生命周期管理(开发范式 v1 规划段)。核心是一条 issue 驱动的流程:用户随手丢想法,你把糊的 issue 变成能开工的 task——产出的是"问题定义",不是"解决方案实现";载体就是仓库根的 ISSUES.md 一个 markdown 文件,不引入看板或新格式。五个动作:记(原话入池 + 关联检查)、并(合并同源需求)、拆(讨论拆解,引导用户讲出方案背后的真需求)、转(落产出)、pending(聊两轮还糊就记下卡点放回池子,禁止编假 plan 交差)。转的判型标准只有一条"一个版本能不能交付完":能 → 简单 task,一段话 + 3~5 条验收点写在池子条目下;不能 → 复杂 plan,落 docs/plan/ 并按 references/plan-writing.md 七步写框架计划正文(讲"为什么做 / 做到什么程度算完 / 分几步走",不掺字段接口),尾巴必须留糊,交付一批回来再拆下一批。当用户说"记个 issue""新增/汇总 issue""拆 issue / 拆解 #N""过一遍池子""需求池""这个 issue 怎么做""写计划报告""框架计划""项目计划""v1.0 计划""版本路线""阶段方案"时触发。不负责:界面长什么样(用 design-exploration)、PRD/测试用例(用 prd-test-writer)、改一个已经上线跑着的功能(用 req-change-workflow)、写给别的 AI 自主执行的 goal contract(用 goal-setter)、非计划类的 HTML 长文/复盘/教程(用 readable-output)、写代码、开分支、发版打 tag(用 git-push)、定优先级。
OpenAgentSkill Trust Score
The Trust Score helps an agent decide whether a skill is safe enough to shortlist before installation.
GitHub adoption
INFO76
753 GitHub stars
Stars/forks activity
INFO71
753 stars, 107 forks; issue activity unavailable in current metadata
Recent maintenance
PASS100
29d since push
License clarity
PASS86
MIT
README/SKILL.md completeness
INFO76
Public metadata needs stronger README/SKILL.md context
Dependency/runtime risk
PASS82
network or browser surface
Install availability
PASS92
npx skills add yunshu0909/yunshu_skillshub --skill issue-pool
Install command safety
PASS92
standard package or runtime install path
Permission surface
PASS86
network or browser access
Repository evidence
PASS86
https://github.com/yunshu0909/yunshu_skillshub/tree/master/issue-pool
Review status
PASS88
AI review data available
Agent Proven outcomes
INFO54
No agent outcome data yet
Checks
Install path
92
npx skills add yunshu0909/yunshu_skillshub --skill issue-pool
Repository
88
https://github.com/yunshu0909/yunshu_skillshub/tree/master/issue-pool
License
86
MIT
Maintenance
100
29d since push
AI review
88
Approved with no listed issues
README/SKILL.md completeness
84
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
Guidance for distinctive, intentional UI design, typography, visual direction, and non-template-like product interfaces.
175K Stars · Audit report
Design and implementation guidance for distinctive landing pages, portfolios, product demos, and purposeful redesigns.
85K Stars · Audit report
Turn one topic into a narrated Vox-style paper-collage explainer or ad video, from script through captions.
1.8K Stars · Audit report
Usable description available
Dependency risk
82
network or browser surface
Install command safety
92
standard package or runtime install path
Permission surface
86
network or browser access
Stars/forks activity
71
753 stars, 107 forks; issue activity unavailable in current metadata
Adoption
88
753 GitHub stars
Agent safety v2
Good audit and safety signals with no high-risk permission hints in public metadata.
Review the audit page, then allow agent install in a sandboxed workflow.
Network access
mediumSkill likely fetches remote pages, APIs, repositories, or external services.
Filesystem access
mediumSkill may read or write project files, documents, generated artifacts, or local workspace state.