agentleFS
farditafardita/ai-config/skills/skill-builder/SKILL.md

skill-builder

Skill1 starsChanged 3 months agoMITView on GitHub

Creates a new reusable agent skill from a plain-language description of what the user wants. Use when the user says "create a skill for X", "make me a skill that Y", "build a skill for Z", "generate a skill", "I want a skill that...", or otherwise asks to author a skill from their own words. Also use when the user wants to turn a recurring task or workflow into a shareable, self-contained skill.

74 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 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.
  • 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

  • SkillPilotCHSkill

    level-up

    Eine Automatisierung pro Woche finden, scopen, shippen. Output landet als proposed-Eintrag in cadence.md mit konkreten Implementations-Schritten.

    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

The file

We split this skill into the rules it gives an agent

10 rules. 0 are common, 6 are distinctive, and 4 are very specific to this project.

  • 0

    Common

    Most of the 65 edited versions we read keep these.

  • 6

    Distinctive

    This author's own choices. Worth a look.

  • 4

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Write to ~/.agents/skills/<name>/SKILL.md (plus optional supporting files in the same folder).

    line 23
  2. Very specific:

    If the task needs code, put it in a scripts/ subfolder and reference it relatively.

    line 48
  3. Distinctive:

    Prefer the simplest working version (YAGNI).

    line 49
  4. Distinctive:

    Do NOT add fabricated flags, dependencies, or tools the user didn't mention.

    line 50
  5. Distinctive:

    Read the user's request. Identify: goal, domain, input, output, trigger phrases.

    line 55
  6. Distinctive:

    Ask ONE clarifying question only if a decision materially changes the skill (language?

    line 56
  7. Very specific:

    Write ~/.agents/skills/<name>/SKILL.md with frontmatter + body.

    line 59
  8. Distinctive:

    If supporting scripts/templates are needed, write them under the same folder.

    line 60
  9. Very specific:

    Verify: confirm the file path and a one-line summary of what the skill does.

    line 61
  10. Distinctive:

    No secrets/absolute private paths hard-coded unless the user asked.

    line 80

“Common” is measured: kept by at least 6 in 10 of the 65 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

Turn the user's plain-language request into a complete, production-ready agent skill saved to the local skills directory.

Goal

Given a user description like "crea una skill che compone il mio CV markdown in PDF" or "a skill that lints my dockerfiles", produce a working skill the agent can load on demand.

Output

Write to ~/.agents/skills/<name>/SKILL.md (plus optional supporting files in the same folder). The name is derived from the description: lowercase, kebab-case, concise.

Structure of a Good Skill

A skill is a SKILL.md file with YAML frontmatter, plus optional companion files (scripts, references, templates) in the same directory.

  1. Frontmatter (required): name and description. The description must be specific enough that the agent can auto-trigger the skill later. Include concrete trigger phrases the user would say. Keep it under ~15 lines.
  2. Body: Markdown with clear sections:
    • # <Name> — human title.
    • ## When to Use — exact trigger conditions.
    • ## Workflow / steps — numbered, concrete, actionable.
    • Rules, gotchas, examples, verification steps.
    • Note any relative helper files (scripts/, references/).

Scaffolding Rules

  • Match the user's language (if they speak Italian, write the skill body in Italian unless they ask otherwise). Keep name and description in English for registry compatibility.
  • Reuse the user's existing conventions: read a sibling skill's SKILL.md first to mirror structure (frontmatter style, heading levels, tone).
  • If the task needs code, put it in a scripts/ subfolder and reference it relatively.
  • Prefer the simplest working version (YAGNI). Add only what the task actually needs.
  • Do NOT add fabricated flags, dependencies, or tools the user didn't mention. If unsure, ask one clarifying question before writing.

Procedure

  1. Read the user's request. Identify: goal, domain, input, output, trigger phrases.
  2. Ask ONE clarifying question only if a decision materially changes the skill (language? scope? strictness? output location?). Otherwise proceed.
  3. Derive name from the description.
  4. Write ~/.agents/skills/<name>/SKILL.md with frontmatter + body.
  5. If supporting scripts/templates are needed, write them under the same folder.
  6. Verify: confirm the file path and a one-line summary of what the skill does. Confirm it will be auto-discovered (it lives in ~/.agents/skills/).

Example Frontmatter

---
name: cv-to-pdf
description: >
  Composes the user's markdown CV into a styled PDF. Use when the user says
  "componi il mio cv in pdf", "create a PDF resume", "export my cv to pdf".
---

Quality Checks

  • name is present and kebab-case.
  • description contains trigger phrases and says when to use the skill.
  • Body is actionable (numbered steps) and self-contained.
  • No secrets/absolute private paths hard-coded unless the user asked.
  • Language matches the user's request.

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.