x-autoreflection
Skill2 starsChanged 55 days agoNo licenceView on GitHub
Turn sessions into approved skill fixes — run `x-autoreflection <period>` (24h, 7d, 2w) to traverse every session of that window across every CLI, write one skill-health report (JSON truth + markdown read) and a fix plan, then ask whether an auto-heal session is wanted and, on yes, propose each fix as one multi-select option carrying the original issue, the proposed edit and the rate it should move, applying only what is picked with a revert-on-failure ledger. Without a period it reflects on one session instead (this one or an earlier one), extracting friction signals and quality anchors, verifying each against the real skill files, and routing evidence-backed proposals to a fix, a spec, or tasks. Use for "reflect on this session", "what went wrong above", "retro", "analyze my last week of sessions", "what has been failing across my skills", "heal the skills from that report", "improve the skills based on what happened".
In this repository30 other files it gives its agents.
- AGENTS.mdAGENTS.md
- x-analyzeSkill
- x-api-draftSkill
- x-api-swaggerSkill
- x-browserSkill
- x-commentsSkill
- x-commitSkill
- x-debugSkill
- x-decomposeSkill
- x-epicSkill
- x-essaySkill
- x-fixSkill
- x-humanizeSkill
- x-implementSkill
- x-investigateSkill
- x-migrateSkill
- x-parallelSkill
- x-planSkill
- x-refactorSkill
- x-reproduceSkill
- x-researchSkill
- x-reviewSkill
- x-roastSkill
- x-rollbackSkill
- x-searchSkill
- x-skill-lintSkill
- x-test-genSkill
- x-triageSkill
- x-uiSkill
- x-unbloatSkill
The file
We split this skill into the rules it gives an agent
10 rules. About 0 are common, 5 are distinctive, and 5 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈5
Distinctive · estimate
This author's own choices. Worth a look.
5
Very specific
Tied to their project's names, files or tools. Probably skip.
No licence file, so all rights are reserved — read it at the source. We count its rules but don't quote them. Read them on GitHub.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
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.