agentleFS
brennantimbrennantim/claude-skills/create-skill/SKILL.md

create-skill

Skill0 starsChanged 9 months agoMITView on GitHub

Create a new Claude Code skill from a description. Use when the user asks to create, build, or make a skill, command, or capability for Claude Code.

  • Reads credentials
  • Installs packages

148 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

Show its rules and text

We split this skill into the rules it gives an agent

18 rules. 0 are common, 15 are distinctive, and 3 are very specific to this project.

  • 0

    Common

    Most of the 138 edited versions we read keep these.

  • 15

    Distinctive

    This author's own choices. Worth a look.

  • 3

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Create Claude Code skills that follow established patterns and best practices.

    line 9
  2. Distinctive:

    When should it trigger? (description keywords)

    line 17
  3. Distinctive:

    If the user's request is clear enough, skip unnecessary questions.

    line 21
  4. Distinctive:

    If the skill involves external APIs, libraries, or unfamiliar domains:

    line 25
  5. Distinctive:

    Use WebSearch to find current documentation and approaches

    line 26
  6. Distinctive:

    Look for Python stdlib solutions before adding dependencies

    line 28
  7. Distinctive:

    When to use it

    line 39
  8. Distinctive:

    Default (both user and model) for reference/utility skills

    line 43
  9. Distinctive:

    Only grant what's necessary

    line 46
  10. Very specific:

    Use patterns like Bash(python3 ~/.claude/skills/SKILL_NAME/scripts/*.py *)

    line 47
  11. Distinctive:

    Use scripts for: API calls, file manipulation, deterministic operations

    line 50
  12. Distinctive:

    Use instructions for: decision-making, interpretation, flexible workflows

    line 51
  13. Very specific:

    Create the skill at ~/.claude/skills/{skill-name}/:

    line 55
  14. Distinctive:

    No pip install required

    line 99
  15. Very specific:

    Keep SKILL.md lean, put details in references

    line 105
  16. Distinctive:

    After creating the skill:

    line 109
  17. Distinctive:

    Verify the skill appears in available skills

    line 110
  18. Distinctive:

    Test invocation with a simple case

    line 111

“Common” is measured: kept by at least 6 in 10 of the 138 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 Creator

Create Claude Code skills that follow established patterns and best practices.

Process

1. Clarify Requirements

Ask the user:

  • What should the skill do? (core functionality)
  • When should it trigger? (description keywords)
  • What inputs does it need? (arguments, files, environment variables)
  • What outputs does it produce? (files, terminal output, side effects)

If the user's request is clear enough, skip unnecessary questions.

2. Research (if needed)

If the skill involves external APIs, libraries, or unfamiliar domains:

  • Use WebSearch to find current documentation and approaches
  • Favor recent sources (last 2-3 months)
  • Look for Python stdlib solutions before adding dependencies

3. Design the Skill

Determine the skill structure:

Name: lowercase, hyphenated (e.g., generate-report, sync-notes)

Description: The trigger mechanism. Include:

  • What the skill does
  • Keywords that should activate it
  • When to use it

Invocation mode:

  • disable-model-invocation: true for skills with side effects (sending, deploying, deleting)
  • Default (both user and model) for reference/utility skills

Tools needed (allowed-tools):

  • Only grant what's necessary
  • Use patterns like Bash(python3 ~/.claude/skills/SKILL_NAME/scripts/*.py *)

Script vs instructions:

  • Use scripts for: API calls, file manipulation, deterministic operations
  • Use instructions for: decision-making, interpretation, flexible workflows

4. Create Files

Create the skill at ~/.claude/skills/{skill-name}/:

SKILL.md (required):

---
name: skill-name
description: Clear description including trigger keywords and when to use.
argument-hint: [arg1] [--flag value]
allowed-tools: Bash(python3 ~/.claude/skills/skill-name/scripts/*.py *)
disable-model-invocation: true  # if has side effects
---

# Skill Title

Brief overview of what this skill does.

## Usage

How to use the skill with example commands.

## Options

| Flag | Description | Default |
|------|-------------|---------|
| `--flag` | What it does | Default value |

## Examples

Concrete examples showing common use cases.

## Interpreting user requests

How to translate natural language into skill invocations:
1. Extract key information from the request
2. Map to appropriate flags/arguments
3. Handle edge cases

## Environment setup

Any required environment variables or configuration.

scripts/ (if needed):

  • Python scripts using only stdlib when possible
  • No pip install required
  • Load API keys from environment or .env files
  • Clear error messages with setup instructions

references/ (if needed):

  • Additional documentation Claude should reference
  • Keep SKILL.md lean, put details in references

5. Test the Skill

After creating the skill:

  1. Verify the skill appears in available skills
  2. Test invocation with a simple case
  3. Confirm outputs match expectations

Reference

See skill-patterns.md for:

  • Frontmatter field reference
  • Established patterns from existing skills
  • Best practices from official docs

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.