Agent skills · AI, RAG & memory

50 listings on this page, in order of arrival. Each one has its own page with README, repository facts and source links.

1. speech ★ 30,576
   "Use when the user asks for text-to-speech narration or voiceover, accessibility reads, audio prompts, or batch speech generation. OpenAI re
2. transcribe ★ 30,576
   "Transcribe audio files to text with optional diarization and known-speaker hints. Use when a user asks to transcribe speech from audio/vide
3. mac-storage-cleaner ★ 30,576
   Safely reclaim disk space on a Mac — the trustworthy, transparent, reversible alternative to CleanMyMac and similar tools. Use whenever the
4. notebooklm ★ 30,576
   Use this skill to query your Google NotebookLM notebooks directly from Claude Code for source-grounded, citation-backed answers from Gemini.
5. nowait ★ 30,576
   Implements the NOWAIT technique for efficient reasoning in R1-style LLMs. Use when optimizing inference of reasoning models (QwQ, DeepSeek-R
6. skill-developer ★ 30,576
   Create and manage Claude Code skills following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understan
7. biomni ★ 30,576
   Autonomous biomedical AI agent framework for executing complex research tasks across genomics, drug discovery, molecular biology, and clinic
8. esm ★ 30,576
   Comprehensive toolkit for protein language models including ESM3 (generative multimodal protein design across sequence, structure, and funct
9. pufferlib ★ 30,576
   This skill should be used when working with reinforcement learning tasks including high-performance RL training, custom environment developm
10. torchdrug ★ 30,576
    "Graph-based drug discovery toolkit. Molecular property prediction (ADMET), protein modeling, knowledge graph reasoning, molecular generatio
11. sora ★ 30,576
    "Use when the user asks to generate, remix, poll, list, download, or delete Sora videos via OpenAI\u2019s video API using the bundled CLI (`
12. blockrun ★ 30,576
    Use when user needs capabilities Claude lacks (image generation, real-time X/Twitter data) or explicitly requests external models ("blockrun
13. rote ★ 30,576
    "Compile a proven agent skill (a SKILL.md plus references) into a deterministic pipeline that runs without an LLM in the loop, then serve it
14. azure-ai ★ 1,453
    Use for Azure AI: Search, Speech, OpenAI, Document Intelligence. Helps with search, vector/hybrid search, speech-to-text, text-to-speech, tr
15. ai-image-generation ★ 16
    Generate AI images with GPT-Image-2, FLUX, Gemini, Grok, Seedream, Reve and 50+ models via inference.sh CLI. Models: GPT-Image-2, FLUX Dev L
16. nano-banana-2 ★ 43
    Generate images with Google Nano Banana 2 (Gemini-family flash-tier text-to-image) on RunComfy — bundled with the model's documented prompti
17. image-edit ★ 43
    Edit images on RunComfy — this skill is a smart router that matches the user's intent to the right edit model in the RunComfy catalog. Picks
18. gpt-image-edit ★ 43
    Edit images with OpenAI GPT Image 2 (the `/edit` endpoint of ChatGPT Images 2.0) on RunComfy — bundled with the model's documented prompting
19. codex-pet ★ 43
    Codex Pet generator on RunComfy. Build a Codex-compatible Codex Pet spritesheet.webp + pet.json from a single reference image, drop it into
20. ai-image-generation ★ 43
    Generate and edit images on RunComfy via the `runcomfy` CLI — a smart router across the full image-model catalog: FLUX 2 (Klein 9B/4B, Pro,
21. controlnet-pose ★ 43
    Pose-conditioned generation on RunComfy via the `runcomfy` CLI. Routes across Kling 2-6 Motion Control Pro / Standard (transfer the motion /
22. ui-ux-pro-max ★ 125,080
    UI/UX design intelligence for web, mobile, and desktop. This skill should be used when designing, building, reviewing, or fixing interfaces,
23. media-use ★ 48,395
    Agent Media OS, the single skill for every media need in a HyperFrames project. Resolve BGM, SFX, image, icon, brand logo, voice, color grad
24. caveman-compress ★ 104,558
    Compress a memory file such as CLAUDE.md or a todo list into caveman format to save input tokens, keeping a readable backup. Trigger: /cavem
25. full-output-enforcement ★ 84,422
    Overrides default LLM truncation behavior. Enforces complete code generation, bans placeholder patterns, and handles token-limit splits clea
26. ai-image-generation ★ 4
    Generate and edit images on RunComfy via the `runcomfy` CLI — a smart router across the full image-model catalog: FLUX 2 (Klein 9B/4B, Pro,
27. hyperframes-media ★ 48,395
    Audio and media assets for HyperFrames compositions, produced by one shared audio engine (`scripts/audio.mjs`) — multi-provider TTS (HeyGen
28. higgsfield-marketplace-cards ★ 915
    Generate marketplace product image cards through Higgsfield: compliant main image, secondary product images, and A+ style content modules. U
29. google-agents-cli-publish ★ 5,883
    This skill should be used when the user wants to "publish an agent", "publish my ADK agent", "register an agent with Gemini Enterprise", "pu
30. firebase-ai-logic-basics ★ 438
    Official skill for integrating Firebase AI Logic (Gemini API) into web applications. Covers setup, multimodal inference, structured output,
31. lottie ★ 48,395
    Lottie and dotLottie adapter patterns for HyperFrames. Use when embedding lottie-web JSON animations, .lottie files, @lottiefiles/dotlottie-
32. audit-website ★ 87
    Audit a website with the squirrelscan CLI and fix the findings in code. Runs SEO, performance, security, technical, content, accessibility,
33. gpt-image-2 ★ 43
    Generate and edit images with OpenAI GPT Image 2 (ChatGPT Images 2.0) on RunComfy. Documents GPT Image 2's strengths (embedded text, logos,
34. ai-sdk
    Answer questions about the AI SDK and help build AI-powered features. Use when developers: (1) Ask about AI SDK functions like generateText,
35. seam-craft ★ 48,395
    Render-correctness doctrine for scene-to-scene seams in HyperFrames launch videos — the prerequisites that make transitions composite correc
36. compress ★ 104,558
    Compress natural language memory files (CLAUDE.md, todos, preferences) into caveman format to save input tokens. Preserves all technical sub
37. mastra ★ 76
    Comprehensive Mastra framework guide for building agents, workflows, tools, memory, workspaces, and storage with current APIs. Use for docum
38. golang-structs-interfaces ★ 3,173
    Golang struct and interface design patterns — composition, embedding, type assertions, type switches, interface segregation, dependency inje
39. firebase-ai-logic ★ 438
    Official skill for integrating Firebase AI Logic (Gemini API) into web applications. Covers setup, multimodal inference, structured output,
40. karpathy-guidelines ★ 210,213
    Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make
41. python-performance-optimization ★ 39,427
    Profile and optimize Python code using cProfile, memory profilers, and performance best practices. Use when debugging slow Python code, opti
42. baoyu-image-gen ★ 25,780
    AI image generation with OpenAI GPT Image 2, Azure OpenAI, Google, OpenRouter, DashScope, Z.AI GLM-Image, MiniMax, Jimeng, Seedream, Replica
43. firecrawl-knowledge-base ★ 157
    Build a knowledge base from web content with Firecrawl. Use for local reference docs, RAG-ready chunks, fine-tuning datasets, documentation
44. baoyu-comic ★ 25,780
    Knowledge comic creator supporting multiple art styles and tones. Creates original educational comics with detailed panel layouts and batch-
45. baoyu-danger-gemini-web ★ 25,780
    Generates images and text via reverse-engineered Gemini Web API. Supports text generation, image generation from prompts, reference images f
46. react-native-best-practices ★ 1,639
    Provides React Native performance optimization guidelines for FPS, TTI, bundle size, memory leaks, re-renders, and animations. Applies to ta
47. caveman-discover ★ 104,558
    Find and label every LLM workflow in the repository so Caveman Cloud groups spend by workflow instead of one bucket. Use for "discover workf
48. caveman-evidence-review ★ 104,558
    Read-only review of Caveman Cloud evidence: cost, Cave Score, workflows, traces, latency, errors, routing, savings. Use when asked what Cave
49. caveman-setup ★ 104,558
    Wire a repository through the Caveman Cloud gateway so every LLM request is measured, with no behavior change. Use for "set up caveman" or a
50. prompt-engineering-patterns ★ 39,427
    This skill should be used when the user asks to "optimize a prompt", "improve prompt performance", "design a prompt template", "write better