1,847 free skills
AI & ML skills
Skills for AI/ML work — LLM prompt engineering, RAG pipelines, vector databases, fine-tuning, and agent orchestration.
Sourced from real, public repositories — synced daily, never invented.
1,847 free skills
Skills for AI/ML work — LLM prompt engineering, RAG pipelines, vector databases, fine-tuning, and agent orchestration.
Sourced from real, public repositories — synced daily, never invented.
15 tools across six categories
13 of them never send your data anywhere
Free · No signup · No trial clock
SEE THE DIRECTORY
karpathy-kb
pedronauck/skills
Creates and maintains Karpathy-style knowledge bases — Obsidian markdown vaults where an LLM compiles raw sources into cross-linked wiki articles, files Q&A answers back into the corpus, appends a chronological log.md, and lints for gaps. Use when scaffolding a new topic folder, scraping sources into raw/, writing or updating wiki/concepts/ articles, maintaining Dashboard/Concept Index/Source Index/log.md files, running the ingest-compile-query-lint cycle, or adding frontmatter to notes. Do not use for general markdown editing, non-knowledge-base Obsidian notes, code documentation, or personal daily notes.
eval-designer
nickcrew/claude-cortex
Use this skill when building evaluation frameworks to measure LLM quality, safety, accuracy, or alignment including test suites, human eval rubrics, automated evals, and metrics design. Not for training or fine-tuning models. Not for dataset curation or benchmark comparison across publicly available models.
nanograph-ops
nanograph/nanograph-skills
Operational guide for managing nanograph embedded graph databases. Use this skill whenever the user works with nanograph files (.pg schemas, .gq queries, nanograph.toml, *.nano/ databases), asks about graph data operations, mutations, schema changes, data loading, CDC, embeddings, media, or any nanograph CLI command. Also trigger when you see nanograph-related files in the project or the user mentions graph databases or Lance-backed local graph storage in the context of this codebase.
subagent-orchestrator
yuniorglez/gemini-elite-core
Senior Multi-Agent Systems (MAS) Architect for 2026. Specialized in Model Context Protocol (MCP) orchestration, Agent-to-Agent (A2A) communication, and recursive delegation frameworks. Expert in managing complex task handoffs, shared memory state, and parallel subagent execution for high-autonomy engineering missions.
vercel-ai-sdk
vercel-labs/py-ai
Vercel AI SDK (Python) - patterns for building LLM-powered apps with streaming, tools, hooks, and structured output
databricks-model-serving
databricks-solutions/ai-dev-kit
Deploy and query Databricks Model Serving endpoints. Use when (1) deploying MLflow models or AI agents to endpoints, (2) creating ChatAgent/ResponsesAgent agents, (3) integrating UC Functions or Vector Search tools, (4) querying deployed endpoints, (5) checking endpoint status. Covers classical ML models, custom pyfunc, and GenAI agents.
LangChain RAG Pipeline
langchain-ai/langchain-skills
INVOKE THIS SKILL when building ANY retrieval-augmented generation (RAG) system. Covers document loaders, RecursiveCharacterTextSplitter, embeddings (OpenAI), and vector stores (Chroma, FAISS, Pinecone).
lora
itsmostafa/llm-engineering-skills
Parameter-efficient fine-tuning with Low-Rank Adaptation (LoRA). Use when fine-tuning large language models with limited GPU memory, creating task-specific adapters, or when you need to train multiple specialized models from a single base.
diff-profile-archives
kernel/skills
Compare two Kernel profile snapshots to investigate behavioral differences. Use when an issue (e.g. login failure, captcha, broken automation, vendor mismatch) reproduces on one profile but not another, or when a "good" vs "bad" profile needs to be diffed. Takes two profile IDs/names plus an issue description, downloads and extracts both profiles via the Kernel CLI, and surfaces differences in cookies, storage, preferences, extensions, and login state that could explain the issue.
resilience-patterns
yonatangross/orchestkit
Production-grade fault tolerance for distributed systems. Use when implementing circuit breakers, retry with exponential backoff, bulkhead isolation patterns, or building resilience into LLM API integrations.
coding-discipline
jr2804/prompts
Language-agnostic behavioral guidelines to reduce common LLM coding mistakes. Use for ANY coding task (all languages) to avoid overcomplication, make surgical changes, surface assumptions before coding, and define verifiable success criteria. Applies behavioral rigor—separate from language-specific technical standards.
gtm-data-architecture
swan-gtm/gtm-skills
GTM data architecture for revenue operators who are not data engineers; warehouse-native and zero-copy patterns that have won in the market. Use when designing GTM data stacks, planning data transformation layers, evaluating CDP vendors, building identity resolution and unified customer intelligence, implementing reverse ETL (Hightouch or Census), or assessing data readiness for AI agents. Also trigger on \"data architecture\", \"ELT vs ETL\", \"warehouse-native CDP\", \"composable CDP\", \"reverse ETL implementation\", \"dbt for RevOps\", \"unified health scores\", \"customer data platform strategy\", or \"data mesh for GTM\". BOUNDARY: Covers architecture and transformation layers only. Handoff to revops-data-governance for CRM data quality and governance; to revops-tech-stack for vendor selection frameworks; to gtm-planning for strategy implications. This skill addresses the data layer for a RevOps team scaling AI adoption.
mcp-builder
autumnsgrove/claudeskills
Comprehensive guide for building Model Context Protocol (MCP) servers with support for tools, resources, prompts, and authentication. Use when: (1) Creating custom MCP servers, (2) Integrating external APIs with Claude, (3) Building tool servers for specialized domains, (4) Creating resource providers for documentation, (5) Implementing authentication and security
mcp-server-building
yonatangross/orchestkit
Building MCP (Model Context Protocol) servers for Claude extensibility. Use when creating MCP servers, building custom Claude tools, extending Claude with external integrations, or developing tool packages for Claude Desktop.
writing-fragments
jorgealves/matt_pocock_skills
Writing, explore — mine raw fragments, no structure yet.
writing-shape
jorgealves/matt_pocock_skills
Writing, exploit — shape raw material into an article, paragraph by paragraph.
mcp-builder
dedalus-erp-pas/hexagone-foundation-skills
Guide pour la création de serveurs MCP (Model Context Protocol) de qualité permettant aux LLM d'interagir avec des services externes via des outils bien conçus. À utiliser pour construire des serveurs MCP intégrant des API ou services externes, en Python (FastMCP) ou Node/TypeScript (MCP SDK).
firecrawl
acedergren/agentic-tools
Use when scraping web pages, extracting content from JS-rendered sites or SPAs, running search-plus-scrape workflows, or mapping entire site URL trees. Produces clean LLM-friendly Markdown. Prefer over WebFetch when JavaScript execution is required. Keywords: web scraping, fetch URL, scrape website, search web, extract content, SPA, JS-rendered, site map, crawl, Firecrawl.
matlab-estimate-sar
matlab/matlab-agentic-toolkit
Estimate Specific Absorption Rate (SAR) of electromagnetic fields inside dielectric tissue phantoms using MATLAB Antenna Toolbox. Supports three approaches -- birdcage coil with volumetric Phantom (full tissue properties), conformalArray with shape.Custom3D (antenna outside tissue), and direct EHfields for implantable antennas (antenna inside tissue). Computes internal E-fields, calculates point and mass-averaged SAR, and validates via power balance. Use when the user wants to compute SAR, tissue absorption, or RF exposure from antennas near or inside biological tissue.
ai-fine-tuning
lebsral/dspy-programming-not-prompting-lms-skills
Fine-tune models on your data to maximize quality and cut costs. Use when prompt optimization hit a ceiling, you need domain specialization, you want cheaper models to match expensive ones, you heard fine-tuning will make us AI-native, you have 500+ training examples, or you need to train on proprietary data. Also use when you have spent weeks of manual iteration with no systematic improvement path, or manual prompt tuning got you to a working system but quality plateaued. Covers DSPy BootstrapFinetune, BetterTogether, model distillation, and when to fine-tune vs optimize prompts, LoRA vs full fine-tune, when to fine-tune vs few-shot, distill GPT-4 into a smaller model, teacher-student model training, custom model training with DSPy, model distillation, make a cheap model as good as GPT-4.
encore-bucket
encoredev/skills
Store unstructured files in Encore.ts using `Bucket` from `encore.dev/storage/objects` — uploads, images, documents, blobs.
wpds
firecrawl/agent-skills
Use when building UIs leveraging the WordPress Design System (WPDS) and its components, tokens, patterns, etc.
wp-plugin-development
firecrawl/agent-skills
Use when developing WordPress plugins: architecture and hooks, activation/deactivation/uninstall, admin UI and Settings API, data storage, cron/tasks, security (nonces/capabilities/sanitization/escaping), and release packaging.
dspy
nousresearch/hermes-agent
DSPy: declarative LM programs, auto-optimize prompts, RAG.
databricks-vector-search
databricks-solutions/ai-dev-kit
Patterns for Databricks Vector Search: create endpoints and indexes, query with filters, manage embeddings. Use when building RAG applications, semantic search, or similarity matching. Covers both storage-optimized and standard endpoints.
embedding-strategies
rmyndharis/antigravity-skills
Select and optimize embedding models for semantic search and RAG applications. Use when choosing embedding models, implementing chunking strategies, or optimizing embedding quality for specific domains.
ai-coding-agent-setup
markpitt/claude-skills
Configures AI agents (GitHub Copilot, Claude Code, Cursor, Codex) to understand a codebase and self-improve as the project evolves. Use when setting up a new project for AI-assisted development, onboarding AI agents to an existing repo, creating AGENTS.md, configuring MCP servers for code navigation, packaging project workflows as agent skills, or establishing self-improvement feedback loops. Covers AGENTS.md authoring, skill packaging, MCP configuration, context management, and living-documentation strategies.
encore-go-bucket
encoredev/skills
Store unstructured files in Encore Go using `objects.NewBucket` from `encore.dev/storage/objects` — uploads, images, documents, blobs.
contextual-retrieval
yonatangross/orchestkit
Anthropic's Contextual Retrieval technique for improved RAG. Use when chunks lose context during retrieval, implementing hybrid BM25+vector search, or reducing retrieval failures.
rag-architect
alexander-danilenko/cortex-ai-skills
Use when building RAG systems, vector databases, or knowledge-grounded AI applications requiring semantic search, document retrieval, or context augmentation.
llms-txt
enderpuentes/ai-agent-skills
Create llms.txt per llmstxt.org for AI assistants and AEO/GEO. Use when adding llms.txt, llms-full.txt, AI-readable site maps, agent context, or when the user mentions llms.txt, llmstxt, answer engine optimization, GEO, or B2A content.
zephyr-storage
ksachdeva/zephyr-rtos-ai
Direct key-value storage using NVS (Non-Volatile Storage) and ZMS (Zephyr Memory Storage) subsystems in Zephyr OS. Use when storing data directly to flash with numeric IDs (not string keys), choosing between NVS and ZMS, configuring flash partitions for storage, calculating flash wear and device lifetime, or working with storage APIs (mount, read, write, delete). For high-level string-key persistence, use zephyr-settings skill instead.
docyrus-agent-design
docyrus/agent-skills
Design, build, validate, and test a custom Docyrus AI agent end-to-end using the `docyrus agent` CLI commands and its sub-resources. Use when the user wants to create or configure a custom AI agent (assistant/skill/workflow agent) in a dev app — set its instructions, pick its models, toggle capabilities (tools, data sources, files, knowledge base, web search), attach data sources, attach tools, add knowledge docs, wire MCP servers, connect agents (forward/subagent), add dynamic contexts, build workflow steps, or create deployments. Covers choosing the agent shape, the required vs optional config, the sub-resource attach order, and proving the agent is well-formed. Triggers on "create an AI agent", "build an assistant", "configure an agent", "give the agent a data source / tool / knowledge", "agent workflow steps", "agent deployment", "connect agents", `docyrus agent create`, `docyrus agent tools`, `docyrus agent data-sources`, `docyrus agent workflow-steps`, or any custom-agent design + validation task. For authoring the tools an agent calls, use docyrus-app-ai-tools (define with `apps ai-tools`, then attach here with `agent tools`).
update-llms-text
flutter/website
Update and maintain the llms.txt file. Use when the user wants to add sections, add links, correct information, or review the llms.txt file.
vector
simota/agent-skills
Automating browsers via Playwright and Chrome DevTools for data collection, form interaction, screenshot capture, and network monitoring. Task completion focus (vs Voyager for E2E testing).
agentic-rag-patterns
yonatangross/orchestkit
Advanced RAG with Self-RAG, Corrective-RAG, and knowledge graphs. Use when building agentic RAG pipelines, adaptive retrieval, or query rewriting.
prompt-engineer
alexander-danilenko/cortex-ai-skills
Use when designing prompts for LLMs, optimizing model performance, building evaluation frameworks, or implementing advanced prompting techniques like chain-of-thought, few-shot learning, or structured outputs.
scaffold-rules
plaited/development-skills
Scaffold development rules for AI coding agents. Auto-invoked when user asks about setting up rules, coding conventions, or configuring their AI agent environment.
gemini-embeddings
akrindev/google-studio-skills
Generate text embeddings using Gemini Embedding API via scripts/. Use for creating vector representations of text, semantic search, similarity matching, clustering, and RAG applications. Triggers on "embeddings", "semantic search", "vector search", "text similarity", "RAG", "retrieval".
structured-logging
sjungling/sjungling-claude-plugins
This skill should be used when the user asks to "analyze data with SQLite", "query logs", "find patterns in test results", or "correlate errors across files". Automatically activates when parsing large output (>100 lines), correlating data from multiple sources, tracking state across operations, aggregating results (counts, averages, grouping), or querying the same dataset multiple times. Not for tiny datasets (<50 records) with a single simple query.
pseo-llm-visibility
lisbeth718/pseo-skills
Optimize programmatic SEO pages for visibility and citation in AI-generated answers from ChatGPT, Perplexity, Google AI Overviews, and other LLM-powered search. Use when optimizing for LLM citation, implementing llms.txt, configuring AI crawler access, structuring content for AI extraction, or when the user asks about generative engine optimization (GEO), AI search visibility, or getting cited by AI.
agent-dx
justinramos101/agent-skill-kit
Use for AGENT DX — the surface an AI agent consumes as a developer. DO — keep SDK/tool/structured-output/error/telemetry changes agent-consumable. REVIEW — audit agent-facing surfaces for stable contracts, recovery, trust-boundary safety. DESIGN — shape new agent-facing surfaces. Triggers: 'design our Agent SDK', 'are our tool schemas agent-safe', 'review MCP surface', 'is telemetry leaking PII'. Do NOT use for human developer surfaces (use dx-audit / dx-design), agent-readable docs (use agent-docs), or repo agent-hardening (use harden-repo-for-coding-agents).
yolo-training
ultralytics/skills
>
langchain-architecture
rmyndharis/antigravity-skills
Design LLM applications using the LangChain framework with agents, memory, and tool integration patterns. Use when building LangChain applications, implementing AI agents, or creating complex LLM workflows.
guidance
nousresearch/hermes-agent
Constrain LLM output with grammars; guarantee valid JSON.
LangSmith Evaluators
langchain-ai/langchain-skills
INVOKE THIS SKILL when building evaluation pipelines for LangSmith. Covers three core components: (1) Creating Evaluators - LLM-as-Judge, custom code; (2) Defining Run Functions - how to capture outputs and trajectories from your agent; (3) Running Evaluations - locally with evaluate() or auto-run via LangSmith. Contains helper scripts.
mcp-integration
anthropics/claude-plugins-public
This skill should be used when the user asks to "add MCP server", "integrate MCP", "configure MCP in plugin", "use .mcp.json", "set up Model Context Protocol", "connect external service", mentions "${CLAUDE_PLUGIN_ROOT} with MCP", or discusses MCP server types (SSE, stdio, HTTP, WebSocket). Provides comprehensive guidance for integrating Model Context Protocol servers into Claude Code plugins for external tool and service integration.
prompt-engineering-suite
yonatangross/orchestkit
Comprehensive prompt engineering with Chain-of-Thought, few-shot learning, prompt versioning, and optimization. Use when designing prompts, improving accuracy, managing prompt lifecycle.
llm-safety-patterns
yonatangross/orchestkit
Security patterns for LLM integrations including prompt injection defense and hallucination prevention. Use when implementing context separation, validating LLM outputs, or protecting against prompt injection attacks.
outlines
nousresearch/hermes-agent
Outlines: structured JSON/regex/Pydantic LLM generation.
obliteratus
nousresearch/hermes-agent
OBLITERATUS: abliterate LLM refusals (diff-in-means).
dca
alsk1992/cloddsbot
Dollar-cost averaging across all platforms
jinko-context
novainsilico/jinko-skills
>-
chroma
nousresearch/hermes-agent
Embedding database for RAG and semantic search.
axolotl
nousresearch/hermes-agent
Axolotl: YAML LLM fine-tuning (LoRA, DPO, GRPO).
mcpc
apify/mcpc
Use the mcpc CLI to work with MCP (Model Context Protocol) servers from the shell - connect to a server as a persistent session, then list and call tools, read resources, get prompts, and run async tasks. Use --json for scripting and code mode. Reach for this whenever interacting with MCP servers, calling MCP tools, or accessing MCP resources programmatically.
eval-guide
microsoft/eval-guide
Eval enablement accelerator — help customers think through "what does good look like" for their AI agent, then generate a structured eval plan and test cases they can use immediately. No running agent required. Works from a description, an idea, or even a vague goal. Use when anyone mentions agent evaluation, eval planning, "what should we test", "how do we know if the agent is good", test case generation, or interpreting eval results.
inference-sh-cli
nousresearch/hermes-agent
Run 150+ AI apps (image, video, LLM) via inference.sh CLI.
pinecone
nousresearch/hermes-agent
Managed vector DB for production RAG and search.
bmad-checkpoint-preview
bmad-labs/skills
LLM-assisted human-in-the-loop review. Make sense of a change, focus attention where it matters, test. Use when the user says "checkpoint", "human review", or "walk me through this change".