session-retro
Skill0 starsChanged 4 months agoNo licenceView on GitHub
Mine Claude Code session transcripts for reusable knowledge — analyze the current session, a named session, or all recent sessions, and propose what to capture as a new SKILL or an auto-memory entry. Extracts the human-typed prompts with jq instead of reading whole transcripts, filters out programmatic sdk-cli runs, clusters recurring asks, and checks every candidate against the existing skill library so it never proposes a duplicate. Use at the end of a working session, when you notice you keep re-asking for the same multi-step thing, or periodically to harvest the last day or two of sessions.
14 other projects use a version of this.
Adopted by
Most recently taken up by
- jatinmishra/claude-skills-monorepotheir own version, first seen Nov 8, 2026
- phntm7/skillstheir own version, first seen Nov 1, 2026
- momentmaker/kaijutsutheir own version, first seen Nov 1, 2026
- adeonir/agent-skillstheir own version, first seen Nov 1, 2026
- davisbuilds/dojotheir own version, first seen Nov 1, 2026
- TheAxeC/ordotheir own version, first seen Nov 1, 2026
Other versions14 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 14
- werf/werf★ 4.7ksame name
- Arman-Kudaibergenov/1c-ai-development-kit★ 163same name
- adeonir/agent-skills★ 8same name
- renzrollon/shippable-skills★ 7same name
- Zejnilovic/agd★ 5same name
- momentmaker/kaijutsu★ 3same name
- bbeny123/pragma★ 2same name
- Kwangseok-Seo/skills★ 2same name
- nhhthong/skills★ 1same name
- phntm7/skills★ 1same name
4 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository11 other files it gives its agents.
- adversarial-diff-reviewSkill
- backend-repo-bootstrapSkill
- doc-code-auditSkill
- gh-fork-safetySkill
- ios-app-bootstrapSkill
- ios-localizationSkill
- llm-prompt-i18nSkill
- llm-structured-outputs-hardeningSkill
- postgres-async-concurrencySkill
- python-library-bootstrapSkill
- task-handoff-specSkill
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.