Agent skill · Security

devbooks-convergence-audit

devbooks-convergence-audit:以证据优先、声明存疑的原则评估 DevBooks 工作流收敛性,检测"西西弗斯反模式"和"假完成"。主动验证而非信任文档声明。用户说"评估收敛性/检查升级健康度/西西弗斯检测/工作流审计"等时使用。

majiayu000github.com/majiayu000GitHub ↗
claude-codecan modify filesMIT
Install
npx skills add majiayu000/claude-skill-registry --skill devbooks-convergence-audit --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 2
SKILL.md size: 1 KB
Bundled scripts: none
Allowed tools: -Glob-Grep-Read-Bash
Path: skills/analysis/devbooks-convergence-audit/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 534
Language: HTML

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

From the SKILL.md

# DevBooks:收敛性审计(Convergence Audit) ## 渐进披露 ### 基础层(必读) 目标:以证据优先审计收敛性,识别假完成、假绿与伪证据。 输入:变更包、verification.md、evidence/、tests/、代码与 git 历史。 输出:审计报告、可信度评分、需返工或补证据清单。 边界:不修改代码或 tests/;不替代实际测试执行;结论以可验证证据为准。 证据:报告引用的日志/命令输出路径或时间戳。 ### 进阶层(可选) 适用:需要具体检查脚本、评分规则或交叉验证策略时。 ### 扩展层(可选) 适用:需要定制输出模板或与现有闸门联动时。 ## 核心要点 - 原则:声明存疑、证据优先、交叉验证。 - 覆盖检查:Status/AC/任务完成度/证据有效性/git 历史/实时测试。 - 输出:收敛性审计报告 + 可信度评分。 ## 参考资料 - `skills/devbooks-convergence-audit/references/收敛性审计细则.md`:反迷惑原则、检查清单与脚本、评分算法、报告模板与完成状态。 ## 推荐 MCP 能力类型 - 代码检索(code-search) - 引用追踪(reference-tracking) - 影响分析(impact-analysis)

What's inside
Steps it walks through
  1. 渐进披露
  2. 基础层(必读)
  3. 进阶层(可选)
  4. 扩展层(可选)
  5. 核心要点
  6. 参考资料
  7. 推荐 MCP 能力类型
Ships with 1 file
  • metadata.json
More from claude-skill-registry
All skills →
About this skill
What does the devbooks-convergence-audit skill do?

devbooks-convergence-audit:以证据优先、声明存疑的原则评估 DevBooks 工作流收敛性,检测"西西弗斯反模式"和"假完成"。主动验证而非信任文档声明。用户说"评估收敛性/检查升级健康度/西西弗斯检测/工作流审计"等时使用。

How do I install it?

Run `npx skills add majiayu000/claude-skill-registry --skill devbooks-convergence-audit --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.

Where does this skill come from?

From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.

Is a popular skill a good skill?

Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.

Keep going