workflow-from-chats
Skill0 starsChanged 13 days agoMITView on GitHub
Extract durable working preferences from recent agent chats and convert them into skills, rules, or workflow docs. Use when asked to learn preferences, mine feedback, personalize workflows, or generate team/person-specific agent guidance.
2 other projects use a version of this, 2 of them edited.
Adopted by
Most recently taken up by
- dhanji4U/skillsedited, first seen Oct 2, 2026
- ElyzeSolutions/skillsedited, first seen Aug 6, 2026
Other versions2 projects use a version of this.
Word for word · 0
None found.
Edited · 2
- dhanji4U/skills★ 290% same
- ElyzeSolutions/skills★ 199% same
Wrote their own version · 0
None found.
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 repository19 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- check-compiler-errorsSkill
- control-cliSkill
- control-uiSkill
- deslopSkill
- fix-ciSkill
- fix-merge-conflictsSkill
- get-pr-commentsSkill
- loop-on-ciSkill
- make-pr-easy-to-reviewSkill
- new-branch-and-prSkill
- pr-review-canvasSkill
- review-and-shipSkill
- run-smoke-testsSkill
- thermo-nuclear-code-quality-reviewSkill
- verify-thisSkill
- weekly-reviewSkill
- what-did-i-get-doneSkill
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 12
Default to the last 7 days unless the user asks for a different window.
- Distinctive: line 13
Read parent transcripts and relevant subagent transcripts.
- Distinctive: line 14
Do not expose local transcript paths, secrets, customer data, private chat content, or credentials.
- Distinctive: line 39
No artifact: situational, stale, or low-confidence observation.
≈ “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.
Files
Workflow From Chats
Infer durable working preferences from recent chats. Do not summarize chats; extract reusable workflow guidance.
Scope
- Default to the last 7 days unless the user asks for a different window.
- Read parent transcripts and relevant subagent transcripts. Use subagent content as evidence, but cite only parent conversations.
- Do not expose local transcript paths, secrets, customer data, private chat content, or credentials.
Workflow
- State the target workflow or preference surface in one paragraph.
- Build an internal transcript inventory: title/topic, parent conversation ID, approximate date, completion state, relevant subagents, and why it may contain preference evidence.
- Scan for explicit preferences, corrections, and workflow markers such as "I prefer", "always", "never", "not what I asked", "stop", "review", "PR", "CI", "logs", and "skill".
- Extract preference atoms: trigger, workflow step, decision rule, quality bar, stop condition, evidence, and confidence.
- Rate confidence as strong, medium, weak, or contradicted.
- Cluster by workflow shape rather than transcript: shipping, review, simplification, debugging, capture, communication, delegation, or validation.
- Choose the artifact: new skill, skill edit, rule, workflow doc, or no artifact.
- Draft only the reusable guidance. Filter anecdotes that will not help future tasks.
Confidence
- Strong: explicit user preference, workflow-changing correction, repeated parent-chat pattern, or direct request to encode behavior.
- Medium: accepted workflow, repeated tool/model/validation preference, or subagent consensus that the parent used successfully.
- Weak: agent-chosen behavior with no user feedback, one ambiguous transcript, or a likely task-specific correction.
- Contradicted: evidence points in incompatible directions; ask the user before writing files.
Artifact Choice
- Skill: recurring multi-step workflow with clear triggers.
- Rule: general behavior that should apply broadly.
- Workflow doc: useful context that is not reliably triggerable.
- No artifact: situational, stale, or low-confidence observation.
Output
Return a concise synthesis first:
- Target workflow.
- Evidence corpus with parent conversation citations only.
- Preference profile.
- Adopt, consider, dismissed.
- Proposed artifacts.
- Open questions only if they block writing.
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.