awesome-claude-skills
```markdown
What this skill does
```markdown --- name: awesome-claude-skills description: Curated collection of Claude Skills for Claude.ai, Claude Code, and Claude API — plus Composio integration for connecting Claude to 500+ apps triggers: - add a claude skill to my project - connect claude to external apps - install a claude skill - create a CLAUDE.md skill - use composio with claude - set up claude code plugin - automate workflows with claude skills - find skills for claude code --- # Awesome Claude Skills > Skill by [ara.so](https://ara.so) — Daily 2026 Skills collection. A curated collection of Claude Skills that extend Claude's capabilities across Claude.ai, Claude Code, and the Claude API. Skills teach Claude repeatable, standardized workflows — from document processing and code tools to connecting Claude to 500+ external apps via Composio. --- ## What Are Claude Skills? Claude Skills are markdown files (typically `SKILL.md` or placed in `.claude/skills/`) that give Claude specialized knowledge and workflows. They are installed into Claude Code as plugins or referenced via `CLAUDE.md`. Skills enable Claude to: - Follow consistent, repeatable workflows - Integrate with external services (GitHub, Slack, Gmail, Notion, etc.) - Apply domain-specific expertise (security, architecture, testing) - Automate multi-step tasks autonomously --- ## Installation ### Install a Skill into Claude Code ```bash # From a local directory claude --plugin-dir ./my-skill-plugin # Install Composio connect-apps plugin (most popular) git clone https://github.com/ComposioHQ/awesome-claude-skills.git cd awesome-claude-skills claude --plugin-dir ./connect-apps-plugin ``` ### Add a Skill to Your Project Skills referenced in `CLAUDE.md` are automatically picked up by Claude Code: ```bash # Create a skills directory in your project mkdir -p .claude/skills # Copy or write a skill file cp path/to/SKILL.md .claude/skills/my-skill.md ``` Reference it in your `CLAUDE.md`: ```markdown ## Skills @.claude/skills/my-skill.md ``` --- ## Connecting Claude to 500+ Apps (Composio) The `connect` skill lets Claude take real actions — send emails, create GitHub issues, post Slack messages, update Notion databases. ### Setup ```bash # 1. Install the plugin claude --plugin-dir ./connect-apps-plugin # 2. Run the setup wizard inside Claude Code /connect-apps:setup # 3. Paste your API key when prompted # Get a free key at: https://platform.composio.dev ``` Set your API key as an environment variable: ```bash export COMPOSIO_API_KEY="your_api_key_here" ``` ### Usage Examples Once connected, ask Claude naturally: ``` Send an email to [email protected] summarizing today's standup notes ``` ``` Create a GitHub issue in my-org/my-repo titled "Fix login bug" with steps to reproduce ``` ``` Post a message to the #deployments Slack channel: "v2.3.1 deployed to production" ``` ``` Add a new page to my Notion database with today's meeting notes ``` ### Python: Using Composio Programmatically ```python import os from composio import ComposioToolSet, App toolset = ComposioToolSet(api_key=os.environ["COMPOSIO_API_KEY"]) # Get tools for specific apps gmail_tools = toolset.get_tools(apps=[App.GMAIL]) github_tools = toolset.get_tools(apps=[App.GITHUB]) slack_tools = toolset.get_tools(apps=[App.SLACK]) # Use with an LLM (e.g., Anthropic) import anthropic client = anthropic.Anthropic() all_tools = toolset.get_tools(apps=[App.GMAIL, App.GITHUB, App.SLACK]) response = client.messages.create( model="claude-opus-4-5", max_tokens=1024, tools=all_tools, messages=[ { "role": "user", "content": "Create a GitHub issue for the bug we discussed and notify the team on Slack" } ] ) # Handle tool calls result = toolset.handle_tool_calls(response) print(result) ``` --- ## Key Skills Reference ### Document Processing | Skill | What it Does | |-------|-------------| | `docx` | Create/edit/analyze Word docs with tracked changes | | `pdf` | Extract text, tables, metadata; merge & annotate PDFs | | `pptx` | Read, generate, and adjust PowerPoint slides | | `xlsx` | Spreadsheet manipulation: formulas, charts, transformations | ```bash # Install official Anthropic document skills git clone https://github.com/anthropics/skills.git ls skills/skills/ # docx, pdf, pptx, xlsx ``` ### Development & Code Tools ```bash # Changelog generator — transforms git commits to user-facing changelogs # Place SKILL.md in .claude/skills/changelog-generator.md # Then ask Claude: "Generate a changelog from the last 10 commits" # MCP Builder — scaffold MCP servers # Ask: "Create an MCP server for the Stripe API" # Webapp Testing with Playwright # Ask: "Test the login flow on localhost:3000 and take screenshots" ``` ### Data & Analysis ```python # postgres skill — safe read-only queries # Configure your connection string: export POSTGRES_CONNECTION_STRING="postgresql://user:pass@localhost:5432/mydb" # Then ask Claude: "Show me the top 10 customers by revenue this month" ``` --- ## Creating Your Own Skill ### Minimal Skill Structure ```markdown --- name: my-skill-name description: One-line description of what this skill does triggers: - phrase users might say to invoke this - another natural trigger phrase - do the thing this skill handles --- # My Skill Name ## Overview What this skill does and when to use it. ## Instructions Step-by-step guidance for Claude to follow. ## Examples Concrete examples of inputs and expected outputs. ``` ### Using the Skill Creator Install the built-in skill creator skill, then ask: ``` Create a skill that [describes your workflow] ``` Claude will scaffold a complete `SKILL.md` with frontmatter, instructions, and examples. ### Skill Creator Python Helper ```python # skill_creator.py — programmatically generate skill stubs import anthropic import yaml def create_skill(name: str, description: str, workflow: str) -> str: client = anthropic.Anthropic() prompt = f"""Create a Claude Skill SKILL.md file for the following: Name: {name} Description: {description} Workflow: {workflow} Include YAML frontmatter with name, description, and 6 triggers. Include sections: Overview, When to Use, Instructions, Examples, Configuration.""" response = client.messages.create( model="claude-opus-4-5", max_tokens=2048, messages=[{"role": "user", "content": prompt}] ) return response.content[0].text skill_content = create_skill( name="api-rate-limit-handler", description="Automatically handles API rate limiting with exponential backoff", workflow="Detect 429 responses, implement backoff, retry requests, log outcomes" ) with open("SKILL.md", "w") as f: f.write(skill_content) ``` --- ## Skill Directory Structure ``` your-project/ ├── CLAUDE.md # References skills with @path syntax ├── .claude/ │ └── skills/ │ ├── testing.md # TDD workflow skill │ ├── git-workflow.md # Git branching/PR skill │ └── api-integration.md # API patterns skill └── connect-apps-plugin/ # Composio plugin directory ├── plugin.json └── commands/ └── setup.js ``` ### CLAUDE.md Integration Pattern ```markdown # Project: My Application ## Active Skills @.claude/skills/testing.md @.claude/skills/git-workflow.md ## Project Context This is a Python FastAPI application with PostgreSQL. ``` --- ## Popular Community Skills ```bash # iOS Simulator testing git clone https://github.com/conorluddy/ios-simulator-skill # D3.js data visualizations git clone https://github.com/chrisvoncsefalvay/claude-d3js-skill # Playwright browser automation git clone https://github.com/lackeyjb/playwright-skill # AWS CDK best practices git clone https://github.com/zxkane/aws-skills # EPUB generation from markdown git clone https://github.com/smerchek/claude-epub-skill # Install any skill by adding SKILL.md to .claude/skills/ c
Related in Writing & Docs
jax-development
IncludedUse this skill when the user is writing, debugging, profiling, refactoring, reviewing, benchmarking, parallelising, exporting, or explaining JAX code, or when they mention JAX, jax.numpy, jit, grad, value_and_grad, vmap, scan, lax, random keys, pytrees, jax.Array, sharding, Mesh, PartitionSpec, NamedSharding, pmap, shard_map, Pallas, XLA, StableHLO, checkify, profiler, or the JAX repo. It helps turn NumPy or PyTorch-style code into pure functional JAX, fix tracer/control-flow/shape/PRNG bugs, remove recompiles and host-device syncs, choose transforms and sharding strategies, inspect jaxpr/lowering/IR, and benchmark compiled code correctly.
nature-article-writer
IncludedDrafts, rewrites, diagnostically critiques, and style-calibrates primary research manuscripts for Nature and Nature Portfolio journals. Use when the user wants a Nature-style title, summary paragraph or abstract, introduction, results, discussion, methods, figure legends, presubmission enquiry, cover letter, reviewer response, or when a scientific draft sounds generic, jargon-heavy, structurally weak, or AI-ish and needs precise, broad-reader-friendly prose without inventing data, analyses, or references. Best for primary research articles and letters rather than reviews or press releases unless explicitly adapting one.
deckrd
IncludedDocument-driven framework that derives requirements, specifications, implementation plans, and executable tasks from goals through structured AI dialogue. Use when user says "write requirements", "create spec", "plan implementation", "derive tasks", "structure this feature", "break down into tasks", or "document this module". Also use for reverse engineering existing code into docs (/deckrd rev). Do NOT use for direct code writing — use /deckrd-coder after tasks are generated. Do NOT use when the user only wants to run or fix existing code without planning.
clinical-decision-support
IncludedGenerate professional clinical decision support (CDS) documents for pharmaceutical and clinical research settings, including patient cohort analyses (biomarker-stratified with outcomes) and treatment recommendation reports (evidence-based guidelines with decision algorithms). Supports GRADE evidence grading, statistical analysis (hazard ratios, survival curves, waterfall plots), biomarker integration, and regulatory compliance. Outputs publication-ready LaTeX/PDF format optimized for drug development, clinical research, and evidence synthesis.
handling-sf-data
IncludedSalesforce data operations with 130-point scoring. Use this skill to create, update, delete, bulk import/export, generate test data, and clean up org records using sf CLI and anonymous Apex. TRIGGER when: user creates test data, performs bulk import/export, uses sf data CLI commands, needs data factory patterns for Apex tests, or needs to seed/clean records in a Salesforce org. DO NOT TRIGGER when: SOQL query writing only (use querying-soql), Apex test execution (use running-apex-tests), or metadata deployment (use deploying-metadata).
accelint-ac-to-playwright
IncludedConvert and validate acceptance criteria for Playwright test automation. Use when user asks to (1) review/evaluate/check if AC are ready for automation, (2) assess if AC can be converted as-is, (3) validate AC quality for Playwright, (4) turn AC into tests, (5) generate tests from acceptance criteria, (6) convert .md bullets or .feature Gherkin files to Playwright specs, (7) create test automation from requirements. Handles both bullet-style markdown and Gherkin syntax with JSON test plan generation and validation.