full-analysis
Skill8 starsChanged 17 days agoApache-2.0View on GitHub
按顺序编排完整分析流程：设计解构、代码审查、重复检测、问题侦测、定性评估。适用于对项目做全面体检并输出整体评估结论。
In this repository32 other files it gives its agents.
- AGENTS.mdAGENTS.md
- ast-grep-blockSkill
- code-deconstructSkill
- code-detect-dupSkill
- code-detect-problemSkill
- code-part-modificationSkill
- code-refactorSkill
- code-reviewSkill
- cpp-checkSkill
- cpp-clang-tidySkill
- cpp-tscancodeSkill
- gdb-heap-analysisSkill
- java-asprofSkill
- java-check-pmdSkill
- java-check-spotbugsSkill
- java-coverageSkill
- java-envSkill
- java-g2mSkill
- jmh-benchSkill
- lets-loopSkill
- long-term-taskSkill
- md2pdfSkill
- merge-agents-mdSkill
- qualitative-assessmentSkill
- requirement-collectSkill
- rust-clippySkill
- rust-flamegraphSkill
- shell-checkSkill
- sql-extractSkill
- sync-dev-specSkill
- sync-repo-docsSkill
- vbox-test-envSkill
The file
Files
完整分析流程
对目标项目执行一次端到端的全面分析，按固定顺序串联各专项技能。
适用场景
- 项目接手、交接前的整体体检
- 技术债盘点与改造决策
- 定期质量评估与基线建立
前置条件
- 确认目标项目根目录与源码范围。
- 确认是否已有历史分析产物；如有，按各技能的增量规则处理。
- 使用 skill
long-term-task连续执行，避免中途停顿。
执行顺序
各步骤存在依赖关系，不得调整顺序：
| 顺序 | 技能 | 主要输出 | 依赖 |
| 1 | code-deconstruct | docs/deconstruct/ | 无 |
| 2 | code-review | docs/review/ | 步骤 1 的模块与数据流 |
| 3 | code-detect-dup | docs/dup/ | 步骤 1 的模块划分 |
| 4 | code-detect-problem | docs/detect/ | 步骤 2、3 的结果 |
| 5 | qualitative-assessment | docs/assessment/ | 步骤 1 至 4 的全部输出 |
输出物
- 设计解构文档与图
- 代码审查报告
- 重复代码报告
- 问题评分与重构/重建方案
- 系统定性评估报告
完成标准
- 五个步骤均有产物且路径正确
- 后续步骤引用了前序产物，结论不相互矛盾
- 问题评分有明确依据，可从报告回溯到审查条目
- 定性评估覆盖设计、开发、运维、非功能维度
- 全部产物已 git 提交
注意事项
- 单个步骤失败时，记录失败原因与影响范围，不得跳过后续步骤的前提依赖。
- 分析结论必须可回溯到代码位置或量化数据，避免主观判断。
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.