Discover skills
Discover and install skills to enhance your AI agent's capabilities.
| Name | Contains | Score |
|---|---|---|
Create or edit PowerPoint presentations. Dual-mode skill: (1) Editing mode preserves existing templates via Open XML unpack/edit/repack when an existing .pptx is provided. (2) Generation mode creates new Metis-branded decks from a design system with 36 composable components and 5 layout grids. Includes brand extraction for client decks and visual QA via PowerPoint COM. Triggers on deck, slides, presentation, PPT, or any .pptx request. Contains: metis-pptx Create or edit PowerPoint presentations. When an existing .pptx file is provided or referenced (by attachment, file path, or description), use the template-preserving editing workflow. When no existing file is involved and a new Metis-branded deck is needed, use the generation workflow. Also trigger on "slides," "deck," "presentation," "PPT," or any .pptx request. | Skills | 67 Impact — Average score across 0 eval scenarios Securityby  Advisory Suggest reviewing before use Reviewed: Version: 4.3.1 |
Eval-driven process for improving best-practice skills — analyse eval results, research what agents get wrong, rewrite for maximum uplift, and measure improvement with scenarios. Contains: best-practice-skill-improver Eval-driven process for improving tessl skills that teach best practices. Use when asked to improve, optimize, or iterate on a tessl tile or skill, or when creating a new best-practice skill from scratch. Covers analysing eval results, identifying high-uplift practices, rewriting skills, updating verifiers, and measuring improvement with scenarios. | Skills | 67 Impact — Average score across 0 eval scenarios Securityby Advisory Suggest reviewing before use Reviewed: Version: 0.2.1 |
v0.1.0 Slack workspace access. Surfaces new messages, active threads, and channel activity. Can also send messages and replies. Contains: slack Access your Slack workspace. Run the check-in workflow to surface new messages, active threads, and channel activity for the daily note. Can also send messages and replies. | Skills | 67 Impact — Average score across 0 eval scenarios Securityby Advisory Suggest reviewing before use Reviewed: Version: 0.1.0 |
Apply this skill when building, reviewing, or refactoring any UI in a React + TypeScript + Tailwind + shadcn/ui application. Triggers on requests like "add a form", "build a modal", "create a dropdown", "make this accessible", "add a table", "build a navigation", or any time you are creating interactive components. Use proactively — every component must be accessible by default. EU accessibility law (EAA) mandates compliance since June 2025. Contains: accessibility Apply this skill when building, reviewing, or refactoring any UI in a React + TypeScript + Tailwind + shadcn/ui application. Triggers on requests like "add a form", "build a modal", "create a dropdown", "make this accessible", "add a table", "build a navigation", or any time you are creating interactive components. Use proactively — every component must be accessible by default. EU accessibility law (EAA) mandates compliance since June 2025. | Skills | 67 Impact — Average score across 0 eval scenarios Securityby Passed No known issues Reviewed: Version: 0.1.0 |
notion trpc-group/trpc-agent-go Notion API for creating and managing pages, databases, and blocks. | Skills | 67 1.57x Agent success vs baseline Impact 99% 1.57xAverage score across 3 eval scenarios Securityby Advisory Suggest reviewing before use Reviewed: Version: 0.0.1 |
pytdc K-Dense-AI/claude-scientific-skills Therapeutics Data Commons. AI-ready drug discovery datasets (ADME, toxicity, DTI), benchmarks, scaffold splits, molecular oracles, for therapeutic ML and pharmacological prediction. | Skills | 67 1.16x Agent success vs baseline Impact 91% 1.16xAverage score across 3 eval scenarios Securityby Advisory Suggest reviewing before use Reviewed: Version: 0.0.1 |
csharp-nunit github/awesome-copilot Get best practices for NUnit unit testing, including data-driven tests | Skills | 67 1.31x Agent success vs baseline Impact 84% 1.31xAverage score across 6 eval scenarios Securityby Passed No known issues Reviewed: Version: 0.0.2 |
csharp-nunit github/awesome-copilot Get best practices for NUnit unit testing, including data-driven tests | Skills | 67 1.31x Agent success vs baseline Impact 84% 1.31xAverage score across 6 eval scenarios Securityby Passed No known issues Reviewed: Version: 0.0.2 |
notion deepgram/dglabs-deepclaw Notion API for creating and managing pages, databases, and blocks. | Skills | 67 1.57x Agent success vs baseline Impact 99% 1.57xAverage score across 3 eval scenarios Securityby Advisory Suggest reviewing before use Reviewed: Version: 0.0.1 |
notion qsimeon/openclaw-engaging Notion API for creating and managing pages, databases, and blocks. | Skills | 67 1.57x Agent success vs baseline Impact 99% 1.57xAverage score across 3 eval scenarios Securityby Advisory Suggest reviewing before use Reviewed: Version: 0.0.1 |
notion attilaczudor/Test Notion API for creating and managing pages, databases, and blocks. | Skills | 67 1.57x Agent success vs baseline Impact 99% 1.57xAverage score across 3 eval scenarios Securityby Advisory Suggest reviewing before use Reviewed: Version: 0.0.1 |
notion Hung-Reo/hungreo-openclaw Notion API for creating and managing pages, databases, and blocks. | Skills | 67 1.57x Agent success vs baseline Impact 99% 1.57xAverage score across 3 eval scenarios Securityby Advisory Suggest reviewing before use Reviewed: Version: 0.0.1 |
gcp-examples-expert jeremylongshore/claude-code-plugins-plus-skills Generate production-ready Google Cloud code examples from official repositories including ADK samples, Genkit templates, Vertex AI notebooks, and Gemini patterns. Use when asked to "show ADK example" or "provide GCP starter kit". Trigger with relevant phrases based on skill purpose. | Skills | 67 1.67x Agent success vs baseline Impact 87% 1.67xAverage score across 3 eval scenarios Securityby Passed No known issues Reviewed: Version: 0.0.2 |
context-compression muratcankoylan/Agent-Skills-for-Context-Engineering This skill should be used when long-running agent sessions need context compression, structured summarization, compaction, token-per-task optimization, or durable handoff summaries that preserve decisions, files, risks, and next actions. | Skills | 67 1.30x Agent success vs baseline Impact 95% 1.30xAverage score across 3 eval scenarios Securityby Passed No known issues Reviewed: Version: 0.0.1 |
altoviz-automation ComposioHQ/awesome-claude-skills Automate Altoviz tasks via Rube MCP (Composio). Always search tools first for current schemas. | Skills | 67 5.80x Agent success vs baseline Impact 87% 5.80xAverage score across 3 eval scenarios Securityby Advisory Suggest reviewing before use Reviewed: Version: 0.0.1 |
embeddings ruvnet/claude-flow Vector embeddings with HNSW indexing, sql.js persistence, and hyperbolic support. 75x faster with agentic-flow integration. Use when: semantic search, pattern matching, similarity queries, knowledge retrieval. Skip when: exact text matching, simple lookups, no semantic understanding needed. | Skills | 66 1.60x Agent success vs baseline Impact 74% 1.60xAverage score across 3 eval scenarios Securityby Passed No known issues Reviewed: Version: 0.0.1 |
embeddings ruvnet/ruflo Vector embeddings with HNSW indexing, sql.js persistence, and hyperbolic support. 75x faster with agentic-flow integration. Use when: semantic search, pattern matching, similarity queries, knowledge retrieval. Skip when: exact text matching, simple lookups, no semantic understanding needed. | Skills | 66 1.60x Agent success vs baseline Impact 74% 1.60xAverage score across 3 eval scenarios Securityby Passed No known issues Reviewed: Version: 0.0.1 |
expo-deployment expo/skills Deploying Expo apps to iOS App Store, Android Play Store, web hosting, and API routes | Skills | 66 1.50x Agent success vs baseline Impact 90% 1.50xAverage score across 3 eval scenarios Securityby Passed No known issues Reviewed: Version: 0.0.1 |
unit-testing bkircher/skills Use when writing or updating unit tests (in any language). | Skills | 66 1.12x Agent success vs baseline Impact 98% 1.12xAverage score across 3 eval scenarios Securityby Passed No known issues Reviewed: Version: 0.0.1 |
cloudflare-mcp-server secondsky/claude-skills Build MCP (Model Context Protocol) servers on Cloudflare Workers with tools, resources, and prompts. | Skills | 66 1.64x Agent success vs baseline Impact 94% 1.64xAverage score across 3 eval scenarios Securityby Advisory Suggest reviewing before use Reviewed: Version: 0.0.1 |
Can't find what you're looking for? Evaluate a missing skill.