skillify
Skill4 starsChanged 4 months agoMITView on GitHub
Codify a repeated behavior into a new qcobrain skill — but ONLY if it traces to a real, un-invalidated event (the provenance guard). Verifies the pattern actually happened ≥3 times against logs / decisions / sources, decides thinking vs runnable, scaffolds the SKILL.md from references/kernel.md (and registers a runnable in skills/INDEX.md), and records the justifying event. Trigger on "skillify this", "make this a skill", or spotting a task done 3+ times.
52 other projects use a version of this.
Adopted by
Most recently taken up by
- kratocz/skillstheir own version, first seen Nov 15, 2026
- fmind/dottheir own version, first seen Nov 15, 2026
- fmind/dotfilestheir own version, first seen Nov 15, 2026
- wolverin0/claude-skillstheir own version, first seen Nov 11, 2026
- Yeachan-Heo/oh-my-claudecodetheir own version, first seen Nov 9, 2026
- devjiwonchoi/skillstheir own version, first seen Nov 8, 2026
Used with
Projects with it also use plan-tune, ios-clean and 9 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
ShreyRaviSkillplan-tune
Self-tuning question sensitivity + developer psychographic for gstack (v1: observational). Review which AskUserQuestion prompts fire across gstack skills, set per-question preferences (never-ask / always-ask / ask-only-for-one-way), inspect the dual-track profile (what you declared vs what your behavior suggests), and enable/disable question tuning. Conversational interface — no CLI syntax required.
Also in 9 projects that use this
Saqlain-811Skillios-clean
Remove the DebugBridge SPM package and all #if DEBUG wiring from an iOS app. (gstack)
Also in 5 projects that use this
Saqlain-811Skillios-fix
Autonomous iOS bug fixer. (gstack)
Also in 5 projects that use this
ShreyRaviSkilllanding-report
Read-only queue dashboard for workspace-aware ship. Shows which VERSION slots are currently claimed by open PRs, which sibling Conductor workspaces have WIP work likely to ship soon, and what slot /ship would pick next. No mutations — just a snapshot. Use when asked to "landing report", "what's in the queue", "show me open PRs", or "which version do I claim next". (gstack)
Also in 8 projects that use this
timurgaleevSkilldocument-generate
Generate missing docs for a feature, module or project as tutorials, how-tos, reference and explanation.
Also in 7 projects that use this
bastosSkillios-design-review
Review iOS app UI/UX design quality using Apple's design principles and the Liquid Glass-era design language from WWDC25/26. Use when asked for a design review, UX critique, visual design assessment, or evaluation of an app's interface quality, design intent, alignment with the new Apple design system, or usability. Triggers: "design review", "UX review", "visual design critique", "review the UI", "does this design work", "evaluate this interface", "design feedback", "Liquid Glass review".
Also in 5 projects that use this
- +1 more from Saqlain-811
- +4 more from ShreyRavi
Other versions52 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 52
- garrytan/gstack★ 142ksame name
- Yeachan-Heo/oh-my-claudecode★ 41ksame name
- Yeachan-Heo/oh-my-claude-sisyphus★ 41ksame name
- garrytan/gbrain★ 33ksame name
- vudovn/ag-kit★ 8.2ksame name
- vudovn/antigravity-kit★ 8.2ksame name
- ZhangHanDong/harness-engineering-from-cc-to-ai-coding★ 1.5ksame name
- coreyhaines31/makerskills★ 916same name
- Surething-io/cockpit★ 48same name
- 0xMH/claude-skillify★ 45same name
42 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 repository16 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- llms-full.txtllms.txt
- llms.txtllms.txt
- agents-syncSkill
- call-agentSkill
- captureSkill
- context-restoreSkill
- context-saveSkill
- curatorSkill
- learnSkill
- onboardSkill
- recallSkill
- reviewSkill
- wiki-doctorSkill
- worklog-audioSkill
The file
We split this skill into the rules it gives an agent
1 rule. 0 are common, 1 is distinctive, and 0 are very specific to this project.
0
Common
Most of the 45 edited versions we read keep these.
1
Distinctive
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 54
Don't duplicate an existing skill — refine it.
“Common” is measured: kept by at least 6 in 10 of the 45 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Inherits references/kernel.md (the provenance contract). Reads references/wiki-spec.md for schema.
What this is
qcobrain's "skillify" move under its provenance discipline: a behavior becomes a codified skill
only when there is evidence it is real and recurring. A speculative skill is the skill-equivalent of an
unsourced wiki/ note — it rots the system. So skillify carries a provenance guard: no event, no skill.
The provenance guard (gate — do this FIRST, before scaffolding anything)
- It happened, and it recurs. Find ≥3 real occurrences traceable to evidence — entries in
log/build-log.md,runtime/review-log.md,runtime/learnings.md,decisions/log.md, or sourcedwiki/notes. List them with dates. No traceable evidence → refuse: "no traceable recurrence; not skillifying speculation." - It is un-invalidated. None of those occurrences has since been reversed or superseded (check
decisions/log.mdandstatus: supersedednotes). A pattern that was later abandoned is not skill-worthy. - It is not already a skill. Grep
skills/INDEX.mdand.claude/skills/so you refine an existing skill rather than fork a near-duplicate.
Decide the kind (the thinking-vs-runnable rule)
- A reasoning workflow (no deterministic script) → a thinking skill at
.claude/skills/<name>/SKILL.md. - A mechanical, scriptable task any model or human can execute → a runnable skill at
skills/<name>/withSKILL.md+ an entrypoint, registered inskills/INDEX.md.
Name it lowercase-kebab, prefer one word (naming conventions, spec §2).
Scaffold
- Thinking skill: frontmatter
name/description/requires: core, then the kernel-inheritance line, then## Execution+## Guardrails. Never restate the provenance rules — link toreferences/kernel.mdandreferences/wiki-spec.md. - Runnable skill: frontmatter
name/when_to_use/run/needs/status; a self-contained, parameterized entrypoint with a safe validation path; then add the mirror row toskills/INDEX.md. - Seed the new
descriptionwith the actual trigger phrases observed in the evidence, not invented ones.
Register + record
- Thinking skill: it is discovered by location; add it to any skill table that lists thinking skills.
- Runnable skill: add the registry row to
skills/INDEX.md. - Append a learning to
runtime/learnings.md(via/learn) noting which event justified the new skill — closing the provenance loop.
Guardrails (hard)
- No event, no skill. The guard is the point; refuse rather than codify a hunch.
- One behavior per skill (the one-idea-per-note rule, applied to skills).
- Don't duplicate an existing skill — refine it.
- A skill that automates a write must route that write through cite-or-refuse, not around it.
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.

