Learning from Claude Skill Examples: anthropics/skills Patterns

Practical patterns from Anthropic's public example skills (anthropics/skills): representative examples like webapp-testing and doc-coauthoring, SKILL.md vs references/, staged workflows, and authoring principles — per official material.

If you want to build good skills, the fastest path is to read Anthropic's published official example skills. The anthropics/skills repo holds patterns that are actually used in production. Rather than explaining concepts, this guide distills practical patterns and authoring principles you can learn from the examples, based on official material. (As of June 2026.)

Official example skills (anthropics/skills)Dev & technicalwebapp-testing · mcp-builder · frontend-designDocument creationpdf · docx · xlsx · pptx (document-skills/)Creative & designcanvas-design · algorithmic-art · theme-factoryWork & collaborationdoc-coauthoring · internal-comms · brand-guidelines

What official example skills exist

The repo's example skills (mostly Apache 2.0 open source) span creative, technical, and work tasks. Representative ones by category:

  • Dev & technical: webapp-testing (verify local web-app UI via Playwright), mcp-builder (generate MCP servers), frontend-design
  • Document creation: pdf, docx, xlsx, pptx — the skills that actually power Claude's document creation, under the repo's document-skills/.
  • Creative & design: canvas-design, algorithmic-art, theme-factory
  • Work & collaboration: doc-coauthoring, internal-comms, brand-guidelines, plus the meta-skill skill-creator

When starting out, use the repo's template-skill as a starting point.

Core in SKILL.md, details in references/SKILL.mdOnly core instructions (always loaded)references/Detailed docs/schemas split out (linked, loaded on demand)scripts/ · assets/Bundled scripts & resources (optional)Three-level progressive disclosure that saves context

Pattern 1 — core in SKILL.md, details in references/

Well-built example skills keep SKILL.md lean with just core instructions. Detailed docs and schemas go in a references/ directory, linked from the main file. For instance, skill-creator moves JSON structures for evals/grading into references/schemas.md. This makes progressive disclosure work properly — normally only the short core loads, and details enter only when needed. Executable scripts and resources are bundled in scripts/ and assets/ (optional).

Example: doc-coauthoring's 3-stage workflow1. Gather contextClaude asks questions tocapture scope & tone2. Refine & structureBrainstorm/edit eachsection iteratively3. Reader testingFresh Claude (nocontext) catches blind spots

Pattern 2 — design the workflow as stages (doc-coauthoring example)

A good skill guides a task through clear stages. The doc-coauthoring skill runs collaborative writing in three: ① gather context (Claude asks questions to capture background, scope, and tone) → ② refine & structure (iterate brainstorm/edit per section) → ③ reader testing (validate the doc with a fresh, context-free Claude to find blind spots obvious to authors but confusing to others). When sub-agents are available, it poses 5–10 likely reader questions to a fresh Claude and checks automatically. Baking a "stage → test → iterate" structure into a skill stabilizes output quality.

Authoring principles learned from examplesDoClear, slightly 'pushy' descriptionCore in SKILL.md, details in references/Let it auto-activate when the trigger matchesTell users where output files are savedAvoidVague description ('runs a query')Cramming everything into SKILL.mdShipping without testingSkipping security checks on risky actions

Authoring principles from the examples

The principles running through the example skills:

  • Clear, slightly "pushy" description: skill-creator recommends an assertive description that makes when to use it obvious, rather than a vague one ("a dashboard that shows internal data"). The description isn't human documentation — it's the key signal Claude uses to pick a skill.
  • Core in SKILL.md, details in references/
  • Auto-activate when the trigger matches (direct invocation also works)
  • Tell users where output files are saved: for files users must inspect (.docx, .xlsx), state the save location

Note: The example skills' concrete implementations are for demonstration/education, and official docs note the behavior you get from Claude may differ from those implementations. Also, the document-skills/ are source-available (not open source).

The basics and SKILL.md structure: Claude Code skills guide; step-by-step building: create a custom skill; use cases: skills by use case.

Disclaimer: This article is based on Anthropic's public repo (anthropics/skills) and official skills docs (accessed June 2026). The repo's skill list and structure may change. This site is not affiliated with Anthropic.

Keep reading

Have a question or want to share how you use Claude?

Join the community to share tips with other users, or explore more guides.