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
weaviate-cookbooks
kumaran-is/claude-code-onboarding
Build complete AI applications with Weaviate — Query Agent chatbots, data explorers, multimodal PDF RAG, basic/advanced/agentic RAG pipelines, and DSPy tool-calling agents. Use when scaffolding a full-stack Weaviate application from scratch. Triggers: 'build a chatbot', 'RAG pipeline', 'Query Agent app', 'document search', 'data explorer', 'multimodal search', 'agentic RAG', 'Weaviate app'.
gentle-ai-collab-perfect
gentleman-programming/gentle-ai
Trigger: contributing to Gentleman-Programming/gentle-ai as an external collaborator. Strict issue-first workflow, honest PR bodies, contributor-vs-maintainer scope, chained-PR strategy, verification protocol, docstring coverage. Load whenever the active repo is Gentleman-Programming/gentle-ai and any part of the contribution flow is in scope: opening an issue, drafting or editing a PR body, splitting a change into chained/stacked PRs, or auditing a PR before requesting review.
pi-agent-integration
getsentry/junior
Integrate the latest `@earendil-works/pi-agent-core` APIs into an app, library, runtime, or agent harness. Use for Pi `Agent`, `AgentHarness`, streaming bridges, tool execution hooks, `convertToLlm`/`transformContext`, queueing via `steer`/`followUp`, `continue()` semantics, `streamFn`/`streamProxy`, timeout/abort, session, skill, or compaction behavior.
wiki-llms-txt
microsoft/skills
Generates llms.txt and llms-full.txt files for LLM-friendly project documentation following the llms.txt specification. Use when the user wants to create LLM-readable summaries, llms.txt files, or make their wiki accessible to language models.
yeet
openai/plugins
Publish local changes to GitHub by confirming scope, committing intentionally, pushing the branch, and opening a draft PR through the GitHub app from this plugin, with `gh` used only as a fallback where connector coverage is insufficient.
llm-obs-session-classify
datadog-labs/agent-skills
>
deepgram-python-text-to-speech
deepgram/deepgram-python-sdk
Use when writing or reviewing Python code in this repo that calls Deepgram Text-to-Speech v1 (`/v1/speak`) for audio synthesis. Covers one-shot REST (`client.speak.v1.audio.generate`) and streaming WebSocket (`client.speak.v1.connect`). Also covers the in-repo `deepgram.helpers.TextBuilder` for incremental text assembly before synthesis. Use `deepgram-python-voice-agent` when you need full-duplex STT + LLM + TTS with barge-in. Triggers include "TTS", "speak", "synthesize voice", "aura", "text to speech", "speak.v1", "TextBuilder".
pinecone-n8n
pinecone-io/skills
Build n8n workflows using the Pinecone Assistant node or Pinecone Vector Store node. Use when building RAG pipelines, chat-with-docs workflows, configuring Pinecone nodes in n8n, troubleshooting Pinecone n8n nodes, or asking about best practices for Pinecone in n8n.
dd-docs
datadog-labs/pup
Datadog docs lookup using docs.datadoghq.com/llms.txt and linked Markdown pages.
tasks
triggerdotdev/skills
Build AI agents, workflows and durable background tasks with Trigger.dev. Use when creating tasks, triggering jobs, handling retries, scheduling cron jobs, or implementing queues and concurrency control.
programmatic-music
cnemri/programmatic-music-skill
Compose, arrange, analyse and render real music in code with music21 — from scratch or from an existing score or audio file. Use when asked to write/compose/generate a piece, song, melody, chord progression, groove or arrangement; to transcribe or "make an mp3 of" something; to arrange or restyle existing music into another genre (jazz, flamenco, orchestral, lo-fi, metal, maqam, raga…); to harmonise, reharmonise, transpose or change the mode/meter/groove of a score; to analyse a MIDI/MusicXML/audio file for key, chords, form or features; or for anything involving music21, MIDI generation, soundfonts, FluidSynth rendering, or turning notation into audio. Don't use for audio DSP with no notes involved (mixing existing stems, mastering a podcast, sound design), or for lyric writing alone.
databricks-parsing
databricks-solutions/ai-dev-kit
Parse documents (PDF, DOCX, PPTX, images) using ai_parse_document, or build custom RAG pipelines. Use when the user asks to parse documents or build a custom RAG.
opencode-cli
spillwavesolutions/opencode_cli
This skill should be used when configuring or using the OpenCode CLI for headless LLM automation. Use when the user asks to "configure opencode", "use opencode cli", "set up opencode", "opencode run command", "opencode model selection", "opencode providers", "opencode vertex ai", "opencode mcp servers", "opencode ollama", "opencode local models", "opencode deepseek", "opencode kimi", "opencode mistral", "fallback cli tool", or "headless llm cli". Covers command syntax, provider configuration, Vertex AI setup, MCP servers, local models, cloud providers, and subprocess integration patterns.
mcp-builder
majiayu000/claude-skill-registry
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
embedding-strategies
convxai/claude-plugin-agents
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.
embedding-strategies
48nauts-operator/opencode-baseline
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.
rag-mastery
luissambrano/antigravity-config
Consolidated master domain for rag mastery.
firebase-emulator-ci
gdvega/super-android-kotlin-firebase-skill
Use for Firebase Emulator Suite setup, Firestore/Auth/Functions/Storage rules tests and CI validation with emulators:exec.
competition-crypto-mobile
ryfinez/my-ai-skills
Internal downstream skill for ctf-sandbox-orchestrator. CTF-sandbox workflow for crypto, encoding, steganography, APK, IPA, and mobile trust-boundary challenges. Use when the user asks to decode a blob, recover a transform chain or key, inspect hidden media payloads, hook an APK or IPA signer, inspect app storage, or replay mobile request-signing logic. Use only after `$ctf-sandbox-orchestrator` has already established sandbox assumptions and routed here.
spark-performance
ghostinthedata-info/skills
Tune distributed Spark jobs — choose partition counts, minimise shuffles, broadcast small tables, handle skew, cache deliberately, and prefer narrow over wide transformations. Tool-agnostic across Spark APIs. Use when a Spark or distributed dataframe/RDD job is slow, expensive, OOMs, or has long-tail stragglers.
webgpu-wgsl-fragment-shaders
impertio-studio/webgpu-claude-skill-package
>
bc-al-project-context
fernandoartalf/al-copilot-skills-collection
Maintains persistent project context for Business Central AL extensions across sessions, developers, and AI agents. Combines two complementary mechanisms: Architecture Decision Records (ADRs) that capture why technical decisions were made, and Session Handoff documents that capture where the project is right now. Generates, updates, and queries both document types. Use this skill whenever starting a new coding session on an existing project, ending a session and need to document progress, onboarding a new developer or AI agent to an existing codebase, explaining why a technical decision was made, wondering why something is designed a certain way, resuming work after a break, or handing off work between team members. Also trigger when the user says 'document this decision', 'why is this designed like this', 'where did we leave off', 'catch me up', 'what was decided', 'create an ADR', 'end of session', 'handoff', or 'context for next session'.
aigw-contrib-add-translator
missberg/envoy-skills
Add a new LLM provider translator to envoyproxy/ai-gateway — the most common contribution type
regex-vs-llm-structured-text
marvinrichter/clarc
Decision framework for choosing between regex and LLM when parsing structured text — start with regex, add LLM only for low-confidence edge cases.
pinecone
alexai-mcp/hermes-ccc
Managed vector database for production RAG — serverless and pod-based deployment, hybrid search, namespaces, and metadata filtering.
nvalchemi-fine-tuning
nvidia/nvalchemi-toolkit
>-
moai-ml-llm-fine-tuning
jg-chalk-io/nora-livekit
Enterprise LLM Fine-Tuning with LoRA, QLoRA, and PEFT techniques
prompt-engineering
duyet/skills
Comprehensive prompt engineering guidance for Claude (Anthropic), Gemini (Google), and Grok (xAI). Use when crafting prompts to leverage each model's unique capabilities—XML-style tags for Claude, system instructions for Gemini, conversational style for Grok.
vector-database-setup
jyjeanne/ai-setup-forge
To provision and configure a vector database (Vector DB) for storing high-dimensional embeddings, enabling semantic search and RAG applications. Use when: Implementing RAG (Retrieval-Augmented Generation); Building recommendation systems based on similarity; Implementing semantic search (search by meaning, not just keywords).
prompt-engineer
claudiodearaujo/izacenter
Expert in designing effective prompts for LLM-powered applications. Masters prompt structure, context management, output formatting, and prompt evaluation. Use when: prompt engineering, system prompt, few-shot, chain of thought, prompt design.
prompt-engineer
wellux/claude-code-deprecated
>
prompt-engineer
szoloth/skill-pack
Expert prompt engineering for AI systems. Use when the user wants to write or review prompts for AI, create instructions for AI systems, build system prompts, review or improve existing prompts, optimize AI instructions, or create any form of written communication intended for AI consumption (Claude, GPT, or other LLMs).
prompt-engineering
yiweiwan/skills
Use only when writing, revising, testing, or versioning prompts, system instructions, developer instructions, few-shot examples, output schemas, refusal behavior, and prompt regression cases.
qdrant-rag-pipeline
inamdarmihir/agentic-rag-skills
|
rag-pipeline-builder
mrowaisabdullah/ai-humanoid-robotics
Complete RAG (Retrieval-Augmented Generation) pipeline implementation with document ingestion, vector storage, semantic search, and response generation. Supports FastAPI backends with OpenAI and Qdrant. LangChain-free architecture.
rag-architect
stephanj/claude-code-collections
Use when building RAG systems, vector databases, or knowledge-grounded AI applications requiring semantic search, document retrieval, or context augmentation.
rag-review
kumaran-is/claude-code-onboarding
Use when reviewing or auditing a RAG pipeline end-to-end against production best practices. Covers all 8 stages — ingestion/chunking, versioning/updates, embedding/indexing, query routing, retrieval/fusion/reranking, generation/abstention, security, and eval/observability. Triggers on phrases like "review RAG pipeline", "audit RAG", "RAG E2E review", "is this RAG production ready", "check RAG implementation", "RAG pre-merge review", "review this RAG code".
RAG Workflow Planner
notysoty/openagentskills
Designs a complete Retrieval-Augmented Generation (RAG) pipeline for a given use case, including chunking strategy, embedding model selection, and retrieval approach.
rag-architect
nkseth/copilot-dev-skills
Designs and implements production-grade RAG systems by chunking documents, generating embeddings, configuring vector stores, building hybrid search pipelines, applying reranking, and evaluating retrieval quality. Use when building RAG systems, vector databases, or knowledge-grounded AI applications requiring semantic search, document retrieval, context augmentation, similarity search, or embedding-based indexing.
rag-engineer
claudiodearaujo/izacenter
Expert in building Retrieval-Augmented Generation systems. Masters embedding models, vector databases, chunking strategies, and retrieval optimization for LLM applications. Use when: building RAG, vector search, embeddings, semantic search, document retrieval.
production-rag
gnkbhuvan/cartographer
|
agentspan
drolu/agent-skills
Comprehensive Agentspan durable workflow orchestration skill for creating, running, scheduling, monitoring, and debugging AI agent workflows using the Agentspan Python SDK and CLI. Covers agents, tools, multi-agent strategies, guardrails, memory, streaming, human-in-the-loop, testing, and production deployment.
context-os
pokhrelboss/context-os
>-
pump-mcp-server
solizardking/solana-clawd
Model Context Protocol server exposing 53 tools, 3 resource types, and 3 prompts for AI agent consumption — quoting, building transactions, fee management, analytics, AMM operations, social fees, wallet operations over stdio transport.
mcp-developer
agentic-assets/agent-skills
Use when building MCP servers or clients that connect AI systems with external tools and data sources. Invoke for MCP protocol compliance, TypeScript/Python SDKs, resource providers, tool functions.
srs-ai-modeling-system-context
yvoderatskyi/srs-ai-skills
Use when defining system context, boundaries, actors, external systems, context data flows, or DOT context diagrams
rag-architect
droodotfoo/agent-skills
>
protocoling
gabfssilva/scimesh
|
agentic-workflow
autohandai/community-skills
Practical AI agent workflows and productivity techniques. Provides optimized patterns for daily development tasks such as commands, shortcuts, Git integration, MCP usage, and session management.
ddd-protocol
lockp111/agent-ddd-engineering
Shared DDD workflow protocols referenced by all skills. Contains the Ambiguity Handling Protocol (STOP/ASSUME), Persistence Defense Reference (3-layer model + hooks enforcement), Domain Architecture Reference (red lines), Spec Change Detection Reference, Per-Phase Subagent Dispatch Protocol, Platform Detection Reference (unified platform detection + constraint/hook paths), and Cross-Skill Traceability Reference (artifact dependency chain + impact analysis). Not invoked directly — loaded by other skills via relative path references.
rag-pipeline
yiweiwan/skills
Use only when designing or implementing retrieval-augmented generation workflows: document ingestion, chunking, embeddings, vector search, hybrid search, reranking, context assembly, citations, and retrieval evaluation.
LangChain Agent Starter Kit
langchain-ai/langchain-skills
ALWAYS START HERE for any LangChain, Deep Agents, or LangGraph open source agent project. It is the required starting point for any LangChain open source agent project. Invoke this skill before any other skill and before writing any code. Combines framework selection (LangChain vs LangGraph vs Deep Agents) with full dependency setup for Python and TypeScript into a single starting reference.
mcp-builder
microsoft/agent-skills
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP), Node/TypeScript (MCP SDK), or C#/.NET (Microsoft MCP SDK).
bx-search
brave/brave-search-skills
Web search using the Brave Search CLI (`bx`). Use for ALL web search requests — including "search for", "look up", "find", "what is", "how do I", "google this", and any request needing current or external information. Prefer this over the built-in web_search tool whenever bx is available. Also use for: documentation lookup, troubleshooting research, RAG grounding, news, images, videos, local places, and AI-synthesized answers.
sota-llm-engineering
martinholovsky/sota-skills
>-
ai-sdk
openai/plugins
Vercel AI SDK expert guidance. Use when building AI-powered features — chat interfaces, text generation, structured output, tool calling, agents, MCP integration, streaming, embeddings, reranking, image generation, or working with any LLM provider.
ai-generation-persistence
openai/plugins
AI generation persistence patterns — unique IDs, addressable URLs, database storage, and cost tracking for every LLM generation
agent-browser
openai/plugins
Browser automation CLI for AI agents. Use when the user needs to interact with websites, verify dev server output, test web apps, navigate pages, fill forms, click buttons, take screenshots, extract data, or automate any browser task. Also triggers when a dev server starts so you can verify it visually.
vercel-sandbox
openai/plugins
Vercel Sandbox guidance — ephemeral Firecracker microVMs for running untrusted code safely. Supports AI agents, code generation, and experimentation. Use when executing user-generated or AI-generated code in isolation.
exploring-llm-evaluations
posthog/posthog
>