Agent skill · Anthropic Agent Skills
/skill-creator Create, test and tune your own agent skills
skill-creator helps you write a new skill or improve an existing one through a loop of drafting, testing and revising. Claude runs the draft against realistic sample prompts, shows you the results for review, and can benchmark the skill and refine its description so it triggers on the right requests.
Works with
- Claude Code
Used forBuilding skills and MCP
When to use it
- You want to turn a workflow you just did with Claude into a reusable skill
- An existing skill gives uneven results and you want measured improvements
- A skill rarely triggers, or triggers on the wrong requests, and its description needs tuning
How it works
- 1Capture intent
Claude clarifies what the skill should do, when it should fire and what good output looks like.
- 2Draft the skill
It writes a SKILL.md and any supporting scripts or reference files.
- 3Run test prompts
It runs a few realistic prompts with the skill and presents outputs and metrics for your review.
- 4Revise and repeat
Your feedback and benchmark results drive rewrites until the results hold up.
- 5Optimize the description
An optional loop scores trigger accuracy on a train and held-out query set and picks the best description.
What it steers the agent away from
- Shipping a skill that has never been tried on real prompts
- Vague descriptions that cause a skill to be skipped or to fire on unrelated tasks
- Overfitting a description to the same queries used to tune it
Install this skill
It installs with the Anthropic Agent Skills pack.
Claude CodeAdds the repo as a plugin marketplace, then installs the document set and the example set separately.
/plugin marketplace add anthropics/skills
/plugin install document-skills@anthropic-agent-skills
/plugin install example-skills@anthropic-agent-skillsCommands come from the author’s README; check it for changes before you run them.
Questions
Do I have to run formal evaluations?
No. The skill is meant to adapt to where you are, and it can work informally if you just want help drafting and iterating.
Does it work outside Claude Code?
Yes, with reduced features. In Claude.ai there are no subagents, so tests run one at a time and quantitative benchmarking is skipped.
More guides from Anthropic Agent Skills
/mcp-builderBuild MCP servers that connect agents to external APIsPlans, builds and evaluates MCP servers in TypeScript or Python that wrap external APIs.Read the guide →/pdfWork with PDF files: extract, merge, fill and createReads, creates, merges, splits, fills and otherwise processes PDF files with Python and CLI tools.Read the guide →
Also in this pack
/academy-guideSuggests a matching Claude Academy course or tutorial after answering how-to questions about Claude.↗/algorithmic-artCreates original generative art in p5.js with seeded randomness and adjustable parameters.↗/brand-guidelinesApplies Anthropic's brand colors and typography to documents, slides and other artifacts.↗/canvas-designProduces original static visual designs such as posters as PNG or PDF files.↗/claude-apiGuides building applications on the Claude API and official Anthropic SDKs across languages.↗/discernment-nudgeAdds two or three follow-up questions that help users check facts and assumptions.↗/docxCreates, reads and edits Word documents, including tracked changes and comments.↗/frontend-designSteers new or reworked user interfaces toward deliberate, non-templated visual design choices.↗/internal-commsDrafts internal communications such as status reports, leadership updates and incident reports.↗/pptxCreates, reads and edits PowerPoint decks and templates, including layouts and speaker notes.↗/slack-gif-creatorMakes small animated GIFs sized and validated for use in Slack.↗/theme-factoryApplies one of ten preset color and font themes, or a new one, to an artifact.↗
Summary by trendhub. The skill itself lives in anthropics/skills/skills/skill-creator by Anthropic (Apache-2.0); read the full, current text there.