All Agent Skills
41,263 results
- Canvas DesignAnthropicOfficialCreates posters, art pieces and other static designs as .png or .pdf files from a design philosophy, without copying existing artists' work.
- Claude APIAnthropicOfficialGives Claude current reference material, SDK docs and best practices for the Claude API and Managed Agents in eight languages; bundled with Claude Code.
- Doc CoauthoringAnthropicOfficialStructured workflow for co-authoring proposals, technical specs and decision docs, covering context transfer, iterative refinement and checks from the reader's view.
- DOCXAnthropicOfficialAnthropic's Word skill for creating, reading and editing .docx and .dotx files, including tables of contents, page numbers, tracked changes and comments.
- Frontend DesignAnthropicOfficialVisual design guidance for building new UI or reshaping existing UI, covering aesthetic direction and typography to avoid templated defaults.
- MCP BuilderAnthropicOfficialGuide for building MCP (Model Context Protocol) servers that connect LLMs to external APIs, using Python FastMCP or the Node/TypeScript MCP SDK.
- PDFAnthropicOfficialAnthropic's PDF skill covering text and table extraction, merging, splitting, rotation, watermarks, form filling, encryption and OCR for scanned PDFs.
- PPTXAnthropicOfficialAnthropic's PowerPoint skill for creating, parsing and editing .pptx and .potx decks, including templates, layouts and speaker notes.
- Skill CreatorAnthropicOfficialMeta-skill for creating and improving skills, running evals, benchmarking skill performance and tuning the description for more accurate triggering.
- Web Artifacts BuilderAnthropicOfficialTools for building multi-component claude.ai HTML artifacts with React, Tailwind CSS and shadcn/ui when state management or routing is needed.
- Webapp TestingAnthropicOfficialPlaywright-based toolkit for testing local web apps: verify frontend behavior, debug UI issues, capture browser screenshots and read browser logs.
- XLSXAnthropicOfficialAnthropic's spreadsheet skill for reading, editing and creating .xlsx, .xlsm, .csv and .tsv files, with formulas, formatting, charts and data cleanup.
- Superpowersobra (Jesse Vincent, Prime Radiant)CollectionSoftware development methodology built on composable skills: the agent clarifies the spec, writes a plan, then executes with TDD and subagent-driven development.
- Scientific Agent SkillsK-DenseCollectionScience-focused skill library with 177 skills and 100+ scientific databases for biology, chemistry, medicine and drug discovery; formerly Claude Scientific Skills.
- vercel-labs/agent-skillsVercelCollectionVercel's skill collection with React and Next.js performance rules, web design guideline reviews and Vercel project cost and performance audits.
- Hugging Face SkillsHugging FaceCollectionHugging Face skills for AI/ML tasks such as dataset creation, model training and evaluation, with the hf-cli skill covering core Hub operations.
- Trail of Bits SkillsTrail of BitsCollectionTrail of Bits plugin marketplace of skills for security research, vulnerability detection and audit workflows; Codex can load it through Claude marketplace compatibility.
- Gemini API skillsGoogle (google-gemini GitHub org)CollectionSkills from the google-gemini org that help agents write current Gemini API code, covering the Interactions API, Live API streaming and Gemini Omni video.
- AccessibilityMicrosoftOfficialPrimary accessibility skill for VS Code. REQUIRED for new feature and contribution work, and also applies to updates of existing UI. Covers accessibility help dialogs, accessible views, verbosity settings, signals, ARIA announcements, keyboard navigation, and ARIA labels/roles.
- Agent CustomizationMicrosoftOfficial**WORKFLOW SKILL** — Create, update, review, fix, or debug VS Code agent customization files (.instructions.md, .prompt.md, .agent.md, SKILL.md, copilot-instructions.md, AGENTS.md). USE FOR: saving coding preferences; troubleshooting why instructions/skills/agents are ignored or not invoked; configuring applyTo patterns; defining tool restrictions; creating custom agent modes or specialized…
- Agent Host E2e TestsMicrosoftOfficialUse when writing, recording, updating, validating, or troubleshooting Agent Host end-to-end and real-provider integration tests under src/vs/platform/agentHost/test/node/e2e and providerIntegration. Covers adding a cross-provider test, re-recording fixtures after an SDK bump, required cross-platform Azure validation, gating non-deterministic or platform-specific tests, and diagnosing replay…
- Agent Sessions LayoutMicrosoftOfficialAgents workbench layout — covers the fixed layout structure, grid configuration, part visibility, editor modal, titlebar, sidebar footer, and implementation requirements. Use when implementing features or fixing issues in the Agents workbench layout.
- Author ContributionsMicrosoftOfficialIdentify all files a specific author contributed to on a branch vs its upstream, tracing code through renames. Use when asked who edited what, what code an author contributed, or to audit authorship before a merge. This skill should be run as a subagent — it performs many git operations and returns a concise table.
- Azure PipelinesMicrosoftOfficialUse when validating Azure DevOps pipeline changes for the VS Code build. Covers queueing builds, checking build status, viewing logs, and iterating on pipeline YAML changes without waiting for full CI runs.