AI agent skill

Writing Skills

Edit, tighten, and verify SKILL.md files so they trigger reliably and stay short enough for progressive disclosure.

·

When to use this skill

Use Writing Skills when a skill exists but misfires, never loads, or dumps too much context. It encodes the authoring rules: third-person instructions, trigger-focused descriptions, and one job per file.

When not to use it

If you do not have a skill yet, start with Skill Creator. If the failure is an install path or filename, use the troubleshooting guide instead of rewriting the prose.

How to install

  1. Personal install: create ~/.claude/skills/writing-skills/SKILL.md (and any bundled scripts) so Claude Code, Claude Desktop, and compatible agents can load it in every project.
  2. Project install: commit the same folder at .claude/skills/writing-skills/ so teammates get the skill with the repo.
  3. Restart the agent session after copying files so it re-scans the skills directory, then ask for the task in words that match the skill description.

Full install guide for Claude, Cursor, and Codex

What this skill does

Most broken skills are description problems, not runtime problems. Claude only reads name + description until it decides to load the body.

Writing Skills reviews that description against the words users type, cuts filler from the body, and checks that bundled files are referenced instead of inlined.

Intended uses

  • Fix a skill that never triggers
  • Shorten a SKILL.md that blows the context window
  • Review a teammate skill before merging

Related skills

Related skills in this directory, for comparison before you install another skill.

coding

Skill Creator

Scaffold a new AI agent skill from a plain-language job description: folder, SKILL.md frontmatter, trigger description, and a first draft of the instructions.

View skill

coding

MCP Builder

Design and implement Model Context Protocol servers so an agent can call external tools with typed schemas instead of stuffing API docs into a skill.

View skill

coding

Systematic Debugging

A root-cause debugging loop for coding agents: reproduce, isolate, hypothesize, then change one thing — instead of shotgun patches.

View skill

Ranked Claude skills