Anthropic

santa-method is a multi-agent verification workflow for outputs that need to be right before they ship. It uses independent review to catch blind spots in content, code-adjacent deliverables, compliance-sensitive copy, and workflow automation tasks. Install the santa-method skill when you need a repeatable generate, verify, converge loop.

lead-intelligence is an AI lead intelligence workflow for Lead Research, scoring prospects, finding warm paths, and drafting outreach. Use the lead-intelligence skill to build a ranked lead list, assess fit, and turn research into email, LinkedIn, or X outreach with less guesswork.

gan-style-harness is a Generator-Evaluator skill for Agent Orchestration that helps build complete apps with stricter critique, better iteration, and fewer weak spots. Use it when you need the gan-style-harness skill for frontend-heavy, full-stack, or production-minded work where review quality matters more than speed.

claude-api helps with Anthropic Claude API patterns for Python and TypeScript, including install, messages, streaming, tool use, vision, batches, prompt caching, model selection, and Claude Agent SDK workflows.

autonomous-agent-harness turns Claude Code into a persistent, self-directing agent system with memory, scheduled runs, task dispatch, and computer use. It fits agent orchestration, recurring checks, and long-lived workflows when you need more than a one-time prompt.

writing-skills is a Skill Authoring guide for creating, editing, and validating agent skills with a test-driven workflow. Learn the key files, prerequisites, and practical steps for pressure scenarios, baseline tests, and concise SKILL.md iteration.

skill-creator is a Skill Authoring meta-skill for drafting new skills, revising existing SKILL.md files, running evals, comparing variants, and improving trigger descriptions with repository scripts and review tools.

theme-factory is a curated theming skill for slides, docs, reports, and landing pages. Review the showcase, choose from 10 preset themes, then apply consistent colors and font pairings to your artifact.

canvas-design helps create original static visual work through a two-step flow: write a design philosophy in Markdown, then render it as a .png or .pdf. Best for posters, cover art, concept visuals, and UI-adjacent campaign graphics with minimal text.

webapp-testing is a skill for testing local web apps with Python Playwright. It helps agents start servers with scripts/with_server.py, inspect rendered UI, discover selectors, capture screenshots and console logs, and validate frontend behavior with a reconnaissance-first workflow.

Use the pptx skill to read, create, edit, split, merge, and inspect PowerPoint .pptx files. It guides you through text extraction with markitdown, thumbnail review, unpack/edit/clean/pack workflows, and PptxGenJS for new deck creation.

mcp-builder is a practical guide for planning, building, and evaluating MCP servers for external APIs and services. It helps developers choose tool scope, naming, transport, Python or Node implementation patterns, and evaluation workflows so agents can use the server reliably.

The internal-comms skill helps write internal company communications like 3P updates, newsletters, FAQs, status reports, and leadership updates using example-driven formats from the Anthropic skills repository.

doc-coauthoring is a structured workflow for drafting docs with AI through context gathering, iterative outlining, section-by-section writing, and reader testing for review-ready specs, RFCs, and proposals.

claude-api is a practical skill for installing and using the Claude API and Anthropic SDKs. It helps developers choose the right SDK or raw HTTP path, detect language-specific docs, and implement streaming, tool use, files, batches, and error handling with less guesswork.

brand-guidelines gives agents Anthropic brand colors and typography for restyling docs, slides, HTML, and other text-led artifacts. Use it to apply consistent on-brand formatting, font hierarchy, and palette choices after content is drafted.

algorithmic-art helps create original generative art in p5.js with a two-step workflow: write an algorithmic philosophy, then build runnable .html and .js outputs with seeded randomness, parameter controls, and an interactive viewer.

cso is a Chief Security Officer–style security audit skill for agents. It helps review codebases and workflows for secrets exposure, dependency and supply-chain risk, CI/CD security, and LLM/AI security using OWASP Top 10 and STRIDE. Use cso for structured Security Audit reviews with confidence gates, active verification, and trend tracking.

xlsx is a Claude spreadsheet skill for creating, editing, analyzing, formatting, and recalculating .xlsx, .xlsm, .csv, and .tsv files. It emphasizes zero formula errors, preserving existing workbook templates, financial-model formatting conventions, and LibreOffice-based recalculation with recalc.py.

pptx skill for creating, editing, inspecting, and repairing PowerPoint .pptx decks. Includes workflows for text extraction, slide inventories, replacements, rearranging slides, HTML-to-PowerPoint generation, speaker notes, comments, layouts, and Office Open XML checks.

pdf skill for PDF Processing workflows: extract text and metadata, split or merge files, render pages, create PDFs, and fill forms using SKILL.md, forms.md, reference.md, and helper scripts.

anthropic-administrator-automation helps Claude run Anthropic Admin workflows through Composio's Rube MCP. Use it to discover live tool schemas with RUBE_SEARCH_TOOLS, verify the anthropic_administrator connection, execute schema-based admin actions, and review results safely.

brand-guidelines helps apply Anthropic-style colors, typography, and visual hierarchy to slides, documents, reports, and other artifacts. Use this brand-guidelines skill for consistent styling guidance, with no scripts or assets included.

embedding-strategies helps you choose and optimize embedding models for semantic search and RAG workflows, with practical guidance on chunking, model tradeoffs, multilingual content, and retrieval evaluation.