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. hf-mem ★ 11,032
   Hugging Face CLI to estimate the required memory to load Safetensors or GGUF model weights for inference from the Hugging Face Hub
2. huggingface-best ★ 11,032
   Use when the user asks about finding the best, top, or recommended model for a task, wants to know what AI model to use, or wants to compare
3. huggingface-community-evals ★ 11,032
   Run evaluations for Hugging Face Hub models using inspect-ai and lighteval on local hardware. Use for backend selection, local GPU evals, an
4. huggingface-gradio ★ 11,032
   Build Gradio web UIs and demos in Python. Use when creating or editing Gradio apps, components, event listeners, layouts, or chatbots.
5. huggingface-llm-trainer ★ 11,032
   Train or fine-tune language and vision models using TRL (Transformer Reinforcement Learning) or Unsloth with Hugging Face Jobs infrastructur
6. huggingface-local-models ★ 11,032
   Use to select models to run locally with llama.cpp and GGUF on CPU, Mac Metal, CUDA, or ROCm. Covers finding GGUFs, quant selection, running
7. huggingface-lora-space-builder ★ 11,032
   Build and publish a Gradio demo on Hugging Face Spaces for a user-provided LoRA. Use when someone asks to create, generate, ship, or publish
8. huggingface-paper-publisher ★ 11,032
   Publish and manage research papers on Hugging Face Hub. Supports creating paper pages, linking papers to models/datasets, claiming authorshi
9. huggingface-spaces ★ 11,032
   Build, deploy, and maintain applications on Hugging Face Spaces — Gradio / Docker / Static SDKs, ZeroGPU and dedicated hardware, model loadi
10. huggingface-tool-builder ★ 11,032
    Use this skill when the user wants to build tool/scripts or achieve a task where using data from the Hugging Face API would help. This is es
11. huggingface-trackio ★ 11,032
    Track and visualize ML training experiments with Trackio. Use when logging metrics during training (Python API), firing alerts for training
12. huggingface-vision-trainer ★ 11,032
    Trains and fine-tunes vision models for object detection (D-FINE, RT-DETR v2, DETR, YOLOS), image classification (timm models — MobileNetV3,
13. huggingface-zerogpu ★ 11,032
    AI demos and GPU compute with Gradio Spaces and Hugging Face Spaces ZeroGPU. Use when writing or reviewing code that uses `@spaces.GPU`, con
14. train-sentence-transformers ★ 11,032
    Train or fine-tune sentence-transformers models across `SentenceTransformer` (bi-encoder, dense or static embedding model for retrieval, sim
15. transformers-js ★ 11,032
    Use Transformers.js to run state-of-the-art machine learning models directly in JavaScript/TypeScript. Supports NLP (text classification, tr
16. trl-training ★ 11,032
    Train and fine-tune transformer language models using TRL (Transformers Reinforcement Learning). Supports SFT, DPO, GRPO, KTO, RLOO and Rewa
17. aeo ★ 25,768
    Answer Engine Optimization (AEO) skill — optimize content to be cited by AI language models (ChatGPT, Perplexity, Claude, Gemini, Mistral) a
18. agent-designer ★ 25,892
    Use when the user asks to design a multi-agent system, pick an orchestration pattern (supervisor/swarm/pipeline), generate tool schemas for
19. agent-launcher-orchestrator ★ 25,892
    Use when a user wants to build, launch, grade, or schedule a Claude Managed Agent (CMA) in their own Anthropic account — "build me an agent"
20. agent-memory ★ 25,892
    Use when a project's CLAUDE.md has grown past what anyone reads and you want the agent to learn durable facts from its own sessions instead
21. agent-workflow-designer ★ 25,892
    Design production-grade multi-agent workflows with clear pattern choice (sequential, parallel, hierarchical), handoff contracts, failure han
22. agenthub ★ 25,892
    Multi-agent collaboration plugin that spawns N parallel subagents competing on the same task via git worktree isolation. Agents work indepen
23. brand-guidelines ★ 25,768
    When the user wants to apply, document, or enforce brand guidelines for any product or company. Also use when the user mentions 'brand guide
24. caio-review ★ 25,892
    /cs:caio-review <plan> — Eval-demanding Chief AI Officer interrogation of any plan that involves AI: model selection, risk classification, c
25. cross-eval ★ 25,892
    /cs:cross-eval <memo> — Multi-model consensus on a board memo or strategy brief. Claude + Codex + Gemini cross-review with graceful degradat
26. decide ★ 25,892
    /cs:decide <memo> — Log a decision to two-layer memory via decision-logger. Approved memo becomes durable; raw transcripts kept for referenc
27. decision-logger ★ 25,892
    Two-layer memory architecture for board meeting decisions. Manages raw transcripts (Layer 1) and approved decisions (Layer 2). Use when logg
28. deep-learning-book ★ 25,892
    Study companion and working knowledge base for the Deep Learning textbook by Goodfellow, Bengio & Courville (MIT Press, 2016), read free at
29. engineering-advanced-skills ★ 25,892
    Index of 37 advanced engineering agent skills for Claude Code, Codex, Gemini CLI, Cursor, OpenClaw. Use when browsing or choosing among the
30. eval ★ 25,892
    Evaluate and rank agent results by metric or LLM judge for an AgentHub session. Use when the user runs /hub:eval or asks to score, compare,
31. extract ★ 25,892
    Turn a proven pattern or debugging solution into a standalone reusable skill with SKILL.md, reference docs, and examples. Use when the user
32. hub-init ★ 25,892
    Create a new AgentHub collaboration session with task, agent count, and evaluation criteria. Use when the user runs /hub:hub-init or asks to
33. karpathy-coder ★ 25,892
    Use when writing, reviewing, or committing code to enforce Karpathy's 4 coding principles — surface assumptions before coding, keep it simpl
34. llm-cost-optimizer ★ 25,892
    Use proactively whenever LLM API costs come up -- or should. Triggers include: 'my AI costs are too high', 'optimize token usage', 'which mo
35. llm-wiki ★ 25,892
    Use when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources,
36. memory-engineering ★ 25,892
    Use when designing, reviewing, or paying for an agent memory system — adding memory to an agent, choosing between long-context / RAG / graph
37. memory-review ★ 25,892
    Analyze auto-memory for promotion candidates, stale entries, consolidation opportunities, and health metrics. Use when the user runs /si:mem
38. memory-status ★ 25,892
    Memory health dashboard showing line counts, topic files, capacity, stale entries, and recommendations. Use when the user runs /si:memory-st
39. performance-profiler ★ 25,892
    Systematic performance profiling for Node.js, Python, and Go applications. Identifies CPU, memory, and I/O bottlenecks, generates flamegraph
40. promote ★ 25,892
    Graduate a proven pattern from auto-memory (MEMORY.md) to CLAUDE.md or .claude/rules/ for permanent enforcement. Use when the user runs /si:
41. prompt-governance ★ 25,892
    Use when managing prompts in production at scale: versioning prompts, running A/B tests on prompts, building prompt registries, preventing p
42. rag-architect ★ 25,892
    Use when the user asks to design a RAG pipeline, choose a chunking strategy or embedding model, pick a vector database, or evaluate retrieva
43. remember ★ 25,892
    Explicitly save important knowledge to auto-memory with timestamp and context. Use when a discovery is too important to rely on auto-capture
44. self-eval ★ 25,892
    Honestly evaluate AI work quality using a two-axis scoring system. Use after completing a task, code review, or work session to get an unbia
45. senior-prompt-engineer ★ 25,892
    Use when the user asks to optimize prompts, design prompt templates, evaluate LLM outputs with an eval set, measure RAG retrieval quality, v
46. skillopt-sleep ★ 25,892
    Use when the user wants their Claude agent to self-improve from past usage, asks about a nightly/offline 'sleep' or 'dream' cycle, memory/sk
47. spinning-up-deep-rl ★ 25,892
    Knowledge base from "Spinning Up in Deep RL" by Joshua Achiam (OpenAI, MIT-licensed). Use when applying Achiam's frameworks for RL fundament
48. stage-launch ★ 25,892
    Phase 2 of building a Claude Managed Agent — turn a validated build sheet into exact API payloads and a resumable BYOK curl launch script, t
49. workflow-builder ★ 25,892
    Design and write deterministic multi-agent workflow scripts (.js files in .claude/workflows/) for Claude Code's Workflow tool. Use when a us
50. wrap-up ★ 25,892
    Close out a launched Claude Managed Agent — recap every primitive the founder now owns, regenerate the single-file overview page, and sugges