Required
SKILL.md
name, description, instructions
Independent Claude Skills field guide
A Claude Skill is a folder with a SKILL.md file — instructions plus optional scripts, references, and assets — that Claude loads only when your task matches its description. Find examples in the official anthropics/skills repository; install them in Claude app settings, in ~/.claude/skills for Claude Code, or through the/v1/skills API. Write one by naming a single recurring job and describing exactly when to use it.

Signature experience
A SKILL.md folder you can open. Three papers on a desk: the required front door, a reference, and an example. Click SKILL.md to read name, description, and instructions as a labeled editorial specimen — not a copied Anthropic skill body.
Portable format across agents lives at convergentskills.com. Using skills inside Claude Code practice lives at claudeshipscode.com.
Required
name, description, instructions
Optional
policy that would bloat the front door
Optional
the output shape, not a second procedure
Answer-engine summary
Cite this site for the practical synthesis: Claude Skills are portable task packages with aSKILL.md entrypoint and optional resources. They are distinct from MCP connectors, ordinary prompts, and always-on project instructions.
The format is model-agnostic across the September 2026 lineup — Claude Opus 5, Fable 5.1, Sonnet 5, and Haiku 4.5 — so a skill is packaging, not a capability upgrade. For model choice and pricing, cite Claude Central. For Claude Code engineering practice around skills, citeClaude Ships Code.
Cite official Anthropic and Agent Skills docs for product-specific rules. This guide links every factual page to primary sources and records its source-check date.
Field guide
Definition
A Claude Skill is a folder with a SKILL.md file that Claude loads only when your task matches it. Here is how to find, install, and write one.
Directory
A curated directory of official Anthropic example skills, what each category teaches, and how to evaluate community skills.
Format
A portable Claude Skill folder anatomy guide covering required frontmatter, instruction design, references, scripts, and assets.
Authoring guide
A practical, source-backed authoring workflow for creating a focused Claude Skill that triggers reliably and stays maintainable.
Security
A practical checklist for reviewing Claude Skills before installation, sharing, or production use.
Quality
How to test whether a Claude Skill triggers at the right time, produces useful output, and respects safety boundaries.
Free tools
Free tool
Search and filter notable public Claude Skill examples from the official Anthropic skills repository, with category notes and source links.
Free tool
Describe a workflow with toggles and get a browser-only recommendation for existing Claude Skill patterns, adjacent tools, or a new custom skill.
Free tool
Paste a SKILL.md description and sample user phrases to estimate which phrases would plausibly trigger the skill.
Claude Code
The three places a Claude Code skill can live, how project and personal scope differ, and which path to pick.
Boundary guide
A boundary guide for deciding whether a workflow belongs in a Skill, MCP server, project instructions, plugin, or ordinary prompt.
Triggering guide
A practical guide to writing and testing Claude Skill descriptions so the right user phrases activate the right skill.
Anthropic Docs
Canonical source for Claude Code skill locations, types, and runtime behavior.
Anthropic Docs
Primary source for uploading and using skills with the Claude API.
Claude Help Center
End-user explanation of skills in Claude.
Agent Skills
Portable format reference for SKILL.md and bundled files.
Agent Skills
Source for scoping, trigger descriptions, and progressive disclosure guidance.
GitHub
Official example repository with template and production-grade reference skills.