ai-session-log-mining
Skill0 starsChanged 4 months agoNo licenceView on GitHub
解析本地 AI 编码工具（Claude Code、Codex、opencode）的会话日志，从中提取干过什么、token 用量、改了哪些文件，并把每次会话准确归属到「实际被改动的项目」。适用于用户要做 AI 使用统计/日报周报、想知道某天用 AI 做了什么、要按项目统计 AI 工作量、要解析 ~/.claude 或 ~/.codex 里的 jsonl/session 日志、要判断一次会话到底动了哪个项目的场景。Parse local AI coding-tool session logs (Claude Code JSONL, Codex session events, opencode sqlite) to extract work summaries, token usage and modified file paths, and attribute each session to the project it actually changed. 区别于 git 历史分析：本 skill 的数据源是 AI 工具自己的会话日志，能覆盖未提交/纯讨论的工作。
In this repository28 other files it gives its agents.
- api-integration-adapterSkill
- code-implementationSkill
- code-review-impact-analysisSkill
- code-scope-identificationSkill
- commitSkill
- delivery-summarySkill
- implementSkill
- jiancai-domainSkill
- launchd-automationSkill
- llm-batch-resilienceSkill
- mastergo-react-design-to-codeSkill
- mastergoSkill
- mastergo-ui-fidelity-reviewSkill
- paircoderSkill
- planningSkill
- platform-scaffoldSkill
- platform-uiSkill
- repo-publish-safetySkill
- req-reportSkill
- requirement-clarificationSkill
- requirement-to-code-pipelineSkill
- review-fix-loopSkill
- skill-controllerSkill
- skill-governanceSkill
- solution-boundary-reviewSkill
- task-planning-and-solution-designSkill
- verifySkill
- webview-touch-scroll-debugSkill
The file
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.