Documents, Development & Creative Skills

Use Anthropic's doc-coauthoring skill to run a disciplined writing workflow instead of freeform drafting. The agent gathers missing context, iterates section by section, and pressure-tests the final document with reader-style review before teammates see it.

Use the Anthropic docx skill when an agent needs to produce or repair a real .docx deliverable with headings, tables, numbering, tracked changes, or layout constraints. It frames the work as a document-building workflow with validation and packaging rules, not as a generic document library listing.

Use the Anthropic xlsx skill when an agent needs to create, clean up, or modify .xlsx, .xlsm, .csv, or .tsv files as spreadsheet deliverables, not just inspect tabular data. It pushes the agent toward formula-safe edits, workbook validation, and recalculation instead of hardcoded outputs or one-off scripts.

Use Anthropic's internal-comms skill to turn raw project notes into company-ready status reports, 3P updates, FAQs, leadership notes, and incident writeups.

Use the Anthropic algorithmic-art skill when an agent should turn a creative brief into executable generative art, not into a static image prompt or a generic design suggestion. It directs the agent toward a repeatable p5.js workflow with seeded randomness, parameter controls, and an explicit creative philosophy.

Use Anthropic's slack-gif-creator skill to build animated GIFs that stay inside Slack's practical size, duration, and dimension constraints. It gives an agent a bounded GIF-production workflow, not a generic image library or chat sticker listing.

Safely introduce external Git repositories as reference materials. Responsible for managing the reference directory, ensuring external code is read-only and does not pollute the project's version control.

Use Anthropic's web-artifacts-builder skill to scaffold a React artifact project, build a richer interface with state or routing, and bundle everything into one shareable HTML file. It is for artifact-delivery workflows, not for listing React or Tailwind as standalone products.

Build high-quality Agent Skills for Claude following official Anthropic best practices. Covers SKILL.md structure, frontmatter, description writing, progressive disclosure, testing, patterns, troubleshooting, and distribution across all surfaces (Claude.ai, Claude Code, API, Agent SDK). Use when creating new skills, reviewing skill quality, debugging skill triggering, structuring skill directories, writing skill descriptions, or improving existing skills. Triggers on "build a skill", "create a skill", "skill structure", "SKILL.md", "skill best practices", "skill not triggering", "skill quality".

Use Anthropic's webapp-testing skill to spin up one or more local servers, wait for them to become reachable, and run native Playwright checks against the rendered app. It is for agent-led verification and UI debugging of local web apps, not for listing Playwright as a generic browser framework.