skill-creator — Skills — getagentictools

What it does

Body (Markdown): Instructions and guidance for using the skill. Only loaded AFTER the skill triggers (if at all).

When to include: When the same code is being rewritten repeatedly or deterministic reliability is needed

Example: scripts/rotatepdf.py for PDF rotation tasks

Benefits: Token efficient, deterministic, may be executed without loading into context

Note: Scripts may still need to be read by Claude for patching or environment-specific adjustments

When to include: For documentation that Claude should reference while working

Use cases: Database schemas, API documentation, domain knowledge, company policies, detailed workflow guides

Requirements & configuration

The context window is a public good. Skills share the context window with everything else Claude needs: system prompt, conversation history, other Skills' metadata, and the actual user request.

Think of Claude as exploring a path: a narrow bridge with cliffs needs specific guardrails (low freedom), while an open field allows many routes (high freedom).

Executable code (Python/Bash/etc.) for tasks that require deterministic reliability or are repeatedly rewritten.

Benefits: Token efficient, deterministic, may be executed without loading into context

Note: Scripts may still need to be read by Claude for patching or environment-specific adjustments

skill creator

Source

Repository: https://github.com/composiohq/skills

skill-creator FAQ

What does the skill-creator skill do?

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations. Body (Markdown): Instructions and guidance for using the skill. Only loaded AFTER the skill triggers (if at all). When to include: When the same code is being rewritten repeatedly or deterministic reliability is needed

What does skill-creator require?

The context window is a public good. Skills share the context window with everything else Claude needs: system prompt, conversation history, other Skills' metadata, and the actual user request. Think of Claude as exploring a path: a narrow bridge with cliffs needs specific guardrails (low freedom), while an open field allows many routes (high freedom). Executable code (Python/Bash/etc.) for tasks that require deterministic reliability or are repeatedly rewritten. Benefits: Token efficient, deterministic, may be executed without loading into context Note: Scripts may still need to be read by Claude for patching or environment-specific adjustments

How do I install skill-creator?

Run: npx -y skills add https://github.com/composiohq/skills --skill skill-creator --agent claude-code — the source lives at github.com/composiohq/skills.

Maintain skill-creator?

Let people know it's listed here — add the badge (live metrics, light/dark aware) or a plain link to your README or docs.

[skill-creator on getagentictools](https://getagentictools.com/skills/composiohq-skills-skill-creator?ref=badge)

npx agentictools info skills/composiohq-skills-skill-creator

The second line is the CLI lookup for this page — handy in READMEs and docs.