agentleFS
emiljuchnikowskiemiljuchnikowski/ai-os-template/.claude/skills/skill-builder/SKILL.md

skill-builder

Skill0 starsChanged 3 months agoMITView on GitHub

Builds a new skill by reverse-engineering a successful session, or forward from a goal. Use when a process/prompt has been repeated ≥2 times or the owner says "make this a skill".

75 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use contract-test, literature-research and 6 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.
  • squall-chuaSkill

    contract-test

    Test a running API against its own contract — OpenAPI, GraphQL, protobuf, or AsyncAPI — from the outside, and report every drift between what the contract promises and what the API does.

    Also in 3 projects that use this

  • nickjwellsSkill

    literature-research

    Search academic literature and perform deep research reviews. Use when user asks to search PubMed, find academic papers, or do literature reviews.

    Also in 3 projects that use this

  • nopandererSkill

    commit-and-push

    Automatically analyze git changes, generate Conventional Commits compliant commit messages, commit changes, and push to remote in a single automated workflow. Use when the user invokes /commit-and-push or explicitly requests to automatically commit and push changes following Conventional Commits format (feat:, fix:, docs:, etc.). This skill provides a fully automated git workflow without manual intervention.

    Also in 3 projects that use this

  • MicrosoftSkill

    skill-reviewer

    Review skill PRs with structured severity-rated feedback covering token budgets, routing conflicts, and repo conventions. WHEN: \"review skill\", \"review skill PR\", \"review skill changes\", \"check skill quality\", \"skill PR feedback\".

    Also in 3 projects that use this

  • MicrosoftSkill

    excalidraw-diagram

    Create Excalidraw diagram JSON files that make visual arguments. Use when the user wants to visualize workflows, architectures, or concepts.

    Also in 4 projects that use this

  • LangChainSkill

    file-organizer

    Intelligently organizes your files and folders across your computer by understanding context, finding duplicates, suggesting better structures, and automating cleanup tasks. Reduces cognitive load and keeps your digital workspace tidy without manual effort.

    Also in 3 projects that use this

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 66 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
  1. Distinctive:

    Treat the first use as a test — see trust phases below.

    line 12

“Common” is measured: kept by at least 6 in 10 of the 66 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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Skill-builder — session → skill

Mode A: reverse-engineering (preferred)

We just did something end-to-end and the result was good:

  1. Review the current conversation: what was the goal? what steps? which tools/connections? what questions did I ask the owner? what did we correct along the way?
  2. Save it as .claude/skills/<name>/SKILL.md — frontmatter with name and description (the description MUST say WHEN to use the skill; that's what it's found by). Skill directory names in English.
  3. Treat the first use as a test — see trust phases below.

Mode B: build it forward

The owner describes the goal and typical tools → you draft the skill → run it on a real case → iterate. A skill may need several attempts — that's not wasted time ("every use = training").

Trust phases (bike method — record the phase in SKILL.md)

  1. Phase 1 — hand-held: the skill only proposes; the owner approves every step.
  2. Phase 2 — assisted: the skill executes; the owner reviews the result before it's used.
  3. Phase 3 — autonomous: the skill runs unsupervised; only now is it a Cadence candidate. Phase promotion only by the owner's decision, after min. 3 successful uses. Skills with outbound actions (mail/messages/mutations) never exceed phase 2.

After every use of any skill

Owner feedback ("this was good, this was weak") goes into SKILL.md IMMEDIATELY — a skill evolves with every use. Commit: feat: add/update <name> skill.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.