agentleFS
Sign inStart free
luanmorenommacielluanmorenommaciel/agentspec/.claude/skills/create-skill/SKILL.md

create-skill

Skill256 starsChanged 2 months agoMITView on GitHub

Repo-specific layer for adding a new Claude Code skill to this repository — naming conventions, where the skill lives (distributed, plugin-only, or repo-local), YAML frontmatter pitfalls, and the build/mirror/docs checklist a skill must pass before it ships in the plugin. For the general craft of writing skills (structure, descriptions, progressive disclosure, evals) it defers to the upstream skill-creator skill when that is installed. Use when the user wants to add a skill to this repository, turn a recurring workflow into a repo skill, or asks what conventions a new skill here must follow. Do not use for creating agents or knowledge bases — those have their own workflows — or for general skill-writing guidance outside this repository (use skill-creator directly).

142 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use review-bugbot, migrate-to-skills and 10 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.
  • 0mlkrizzz655335vSkill

    review-bugbot

    缺陷导向代码审查。用 Bugbot 子代理找 bug。

    Also in 5 projects that use this

  • 32103210Skill

    migrate-to-skills

    Convert 'Applied intelligently' Cursor rules (.cursor/rules/*.mdc) and slash commands (.cursor/commands/*.md) to Agent Skills format (.cursor/skills/). Use when you want to migrate rules or commands to skills, convert .mdc rules to SKILL.md format, or consolidate commands into the skills directory.

    Also in 8 projects that use this

  • 32103210Skill

    update-cursor-settings

    Modify Cursor/VSCode user settings in settings.json. Use when you want to change editor settings, preferences, configuration, themes, font size, tab size, format on save, auto save, keybindings, or any settings.json values.

    Also in 8 projects that use this

  • PandelisZSkill

    update-cli-config

    View and modify Cursor CLI configuration settings in ~/.cursor/cli-config.json. Use when the user wants to change CLI settings, configure permissions, switch approval mode, enable vim mode, toggle display options, configure sandbox, or manage any CLI preferences.

    Also in 7 projects that use this

  • yawningwhaleAISkill

    build-premium-website

    Build a premium, animated marketing website (React + Vite + Tailwind + GSAP) for any industry. Use when the user asks to "build a website", "make a landing page for [business]", "build a marketing site", or wants a high-end animated company website. Adapts color, copy, services, and signature animation to the industry.

    Also in 6 projects that use this

  • yawningwhaleAISkill

    instantly-campaign

    Create a new Instantly cold-email campaign in the proven 5-email structure of the user's top-performing campaign (~16% reply rate). Use when the user wants to launch a new outbound campaign, write a cold email sequence, create an Instantly campaign, draft outreach for a new service or niche, or set up a sales sequence.

    Also in 5 projects that use this

  • +1 more from 32103210

The file

We split this skill into the rules it gives an agent

3 rules. 0 are common, 1 is distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 132 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

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

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

    Before authoring anything, confirm a skill is the right layer: run the component-model skill (canonical model: …

    line 20
  2. Very specific:

    When skill-creator is not installed, fall back in order:

    line 29
  3. Distinctive:

    Every new skill passes this before review:

    line 46

“Common” is measured: kept by at least 6 in 10 of the 132 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

Create a Skill (repo conventions)

Author the skill itself with Anthropic's upstream skill-creator skill where it is installed — it owns the general methodology (structure, description writing, progressive disclosure, packaging, evals). This skill carries only what skill-creator cannot know: this repository's conventions and build pipeline. Do not duplicate the upstream methodology here or in the skills you write.

Before authoring anything, confirm a skill is the right layer: run the component-model skill (canonical model: .claude/kb/shared/component-model.md). Many "new skill" asks turn out to be commands, KB content, or a thin agent plus an existing skill.

Division of labor

ConcernOwner
Skill structure, description craft, progressive disclosure, packaging, evalsskill-creator (upstream) — invoke it when available, fetch it when not
Naming, placement, frontmatter pitfalls, ship checklistthis skill

When skill-creator is not installed, fall back in order:

  1. Fetch the upstream methodology directly — it is public. Retrieve https://raw.githubusercontent.com/anthropics/skills/main/skills/skill-creator/SKILL.md (web fetch or curl) and follow it as if the skill were installed; it references sibling files under the same directory that can be fetched the same way when needed.
  2. Offline as well? Three principles carry most of its weight: one skill = one capability (split when triggers stop being related); the description is the entire trigger mechanism (what it does + when to use it + one "do not use for" boundary, third person, ≤1024 chars); keep SKILL.md under ~500 lines and push detail into references/ (read on demand), scripts/ (deterministic helpers), and assets/ (files used in output).

Repo conventions

  1. Naming. Kebab-case, at least one hyphen, name field == folder name. Prefer domain-verb or domain-noun compounds (kb-build, github-post-issue, meeting-analysis). Avoid noise words (helper, tool, utils, a -skill suffix) and avoid -er agent-style names for skills — those read as agent roles.
  2. Placement. Three tiers:
    • Distributed skill → .claude/skills/<name>/; the build mirrors it into plugin/skills/.
    • Plugin-only skill → plugin-extras/skills/<name>/; merged in at build, absent from .claude/.
    • Repo-local skill (for contributors of this repository, not distributed) → .claude/skills/<name>/ plus an entry in the REPO_LOCAL_SKILLS exclusion list in build-plugin.sh.
  3. Frontmatter. Only supported keys (name, description, optionally license, allowed-tools, metadata, compatibility). YAML traps that fail silently: a # inside an unquoted value truncates it; a : inside an unquoted value breaks parsing; write multi-line descriptions as a literal block (|). Never invent keys — there is no triggers: field; the description IS the trigger.
  4. Internal paths. Reference .claude/kb/..., .claude/skills/..., .claude/agents/... normally — the build rewrites them to plugin paths. .claude/sdd/ workspace paths (drafts/, features/, reports/, archive/) are preserved as-is by design.

Ship checklist

Every new skill passes this before review:

#CheckHow
1Structure validname matches folder and ^[a-z0-9]+(-[a-z0-9]+)+$; description ≤1024 chars with triggers and a negative boundary; every referenced supporting file exists
2Mirror in syncrun ./build-plugin.sh, then commit the regenerated plugin/ tree together with the skill; verify locally with git diff --exit-code plugin/ .claude-plugin/ after a fresh rebuild — CI rebuilds the plugin and validates the fresh tree, so a stale committed mirror is caught at the latest in review
3Docs updatedCHANGELOG [Unreleased]; skill counts and catalogs in CLAUDE.md, README.md, plugin/README.md, docs/README.md, docs/reference/README.md
4No template residueif the skill renders {{PLACEHOLDER}} templates, grep output for \{\{[A-Z_]+\}\} — zero hits

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.

Check your setup, free