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
agentsmd-optimize
majiayu000/spellbook
Audit AND optimize a CLAUDE.md / AGENTS.md instruction file — score it against the five high-leverage patterns, flag anti-patterns, then apply approved fixes in place. Use when the user says 优化 CLAUDE.md / 优化 AGENTS.md / optimize my agent doc / 帮我改 claudemd, or after an audit when they want the fixes applied (not just reported).
firebase-ai-logic
akillness/oh-my-gods
Integrate Firebase AI Logic (Gemini in Firebase) for intelligent app features. Use when adding AI capabilities to Firebase apps, implementing generative AI features, or setting up Firebase AI SDK. Handles Firebase AI SDK setup, prompt engineering, and AI-powered features.
beads-br
boshu2/agentops
Local-first issue tracker (beads_rust) for AI agents — track tasks, manage dependencies, find ready work, sync via git JSONL. Triggers: "beads-br", "beads br", "local-first issue tracker beads rust".
bx-ai-agents
ortus-boxlang/skills
Use this skill when building AI agents with aiAgent(): instructions, custom models, tools, skills (always-on and lazy), MCP servers, memory, fluent configuration, multi-agent hierarchies, streaming, and agent middleware.
Gleam Erlang Interop
thebushidocollective/han
Use when gleam-Erlang interoperability including calling Erlang code from Gleam, using Erlang libraries, external functions, working with Erlang types, NIFs, and leveraging the BEAM ecosystem from Gleam applications.
rag-architect
hainamchung/agent-assistant
Use when building RAG systems, vector databases, or knowledge-grounded AI applications requiring semantic search, document retrieval, or context augmentation.
AgentDB Vector Search
ruvnet/agentic-flow
Implement semantic vector search with AgentDB for intelligent document retrieval, similarity matching, and context-aware querying. Use when building RAG systems, semantic search engines, or intelligent knowledge bases.
project-health
fefogarcia/approved-skills
|
axiom-ios-ai
megastep/codex-skills
Use when implementing ANY Apple Intelligence or on-device AI feature. Covers Foundation Models, @Generable, LanguageModelSession, structured output, Tool protocol, iOS 26 AI integration.
mission
itisbryan/claude-missions
Orchestrate multi-phase development missions. Use when the user asks to 'start a mission', 'run a mission', or uses /mission with a description. Supports standard (6-phase) and minimal (3-phase) workflows with planning, implementation, testing, audit, and verification.
mlx-fine-tuning
89jobrien/steve
Specialized skill for MLX-based LLM fine-tuning on Apple Silicon. This skill should be used when working with LoRA fine-tuning, model conversion from HuggingFace to MLX format, adapter management, hyperparameter tuning, memory optimization, and benchmarking on M1/M2/M3/M4 chips.
openhands
nousresearch/hermes-agent
Delegate coding to OpenHands CLI (model-agnostic, LiteLLM).
llm-obs-eval-bootstrap
datadog-labs/agent-skills
Bootstrap evaluators from production traces — by default propose online LLM-judge evaluators and, after you confirm, create them in Datadog as disabled drafts (never auto-enabled); on request emit Python SDK code or a framework-agnostic JSON spec instead. Use when user says "bootstrap evaluators", "generate evaluators", "create evals from traces", "eval bootstrap", "write evaluators", "build eval suite", "publish evaluators", or wants to generate BaseEvaluator/LLMJudge code or online judge configs from production LLM trace data. Works with ml_app and optional RCA report or failure hypothesis.
llm-obs-experiment-analyzer
datadog-labs/agent-skills
Analyze LLM experiment results. Handles single or comparative experiments, exploratory or Q&A modes. Use when user says "analyze experiment", "compare experiments", "analyze against baseline", or provides one or two experiment IDs for analysis.
nebius-finetune
arindam200/nebius-skills
Fine-tune a model on Nebius Token Factory. Use this skill whenever the user wants to train, fine-tune, or adapt a model on Nebius — including uploading training data, creating a fine-tuning job, monitoring training progress, or downloading model checkpoints. Trigger for phrases like "fine-tune on Nebius", "train a model with my dataset", "start a Nebius fine-tuning job", "LoRA fine-tune", "check my training job status", or any question about supervised fine-tuning workflows on Token Factory.
nebius-deploy-lora
arindam200/nebius-skills
Deploy a fine-tuned LoRA adapter as a serverless endpoint on Nebius Token Factory. Use this skill whenever the user wants to serve a fine-tuned model, deploy a LoRA adapter from a Nebius fine-tuning job or HuggingFace, check deployment status, or delete a deployed custom model. Trigger for phrases like "deploy my fine-tuned model", "serve my LoRA adapter on Nebius", "deploy from fine-tuning checkpoint", "upload LoRA to Nebius", "deploy from HuggingFace", "delete my custom model", or any question about making a trained model available for inference on Token Factory.
ai-shaped-readiness-advisor
buyaka/product-manager-skills
Assess whether your product work is AI-first or AI-shaped. Score 5 competencies and recommend the next capability to build.
AgentDB Vector Search
dnyoussef/ai-chrome-extension
Implement semantic vector search with AgentDB for intelligent document retrieval, similarity matching, and context-aware querying. Use when building RAG systems, semantic search engines, or intelligent knowledge bases.
langsmith-evaluator
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.
npx-skills
dagster-io/erk
This skill should be used when working with the npx skills CLI (skills@1.4.5 by Vercel Labs) for managing agent skills — installing, discovering, updating, and publishing portable AI agent instructions. Use when users mention npx skills commands, skill installation, skills.sh, agentskills.io, skills-lock.json, or the open agent skills ecosystem. Essential for understanding the skills mental model, SKILL.md format, and multi-agent interoperability.
deepgram-js-text-to-speech
deepgram/deepgram-js-sdk
Use when writing or reviewing JavaScript/TypeScript in this repo that calls Deepgram Text-to-Speech v1 (`/v1/speak`) for audio synthesis. Covers one-shot REST via `client.speak.v1.audio.generate` and streaming WebSocket via `client.speak.v1.createConnection()` / `connect()`. Use `deepgram-js-voice-agent` when you need full-duplex STT + LLM + TTS instead of one-way synthesis. Triggers include "TTS", "text to speech", "speak", "aura", "streaming TTS", and "speak.v1".
sqlite-skill
snowbeatrain/skills
用于平台中立的 SQLite 数据层设计与审查，包括 schema、SQL、migration、事务、索引、PRAGMA/WAL/FTS/JSON、同步持久化、备份恢复、limits 和安全。当用户明确提到 SQLite/sqlite，或需要判断本地关系型数据库是否适合 SQLite 时使用；不要用于未指定 SQLite 的 IndexedDB、localStorage、key-value storage 或服务端数据库任务。
masthead-storage-savings-with-tables
masthead-data/for-agents
Optimize BigQuery storage costs by identifying and removing dead-end and unused tables.
crawl4ai-skill
bighardperson/computer-science-skills-collection
Web crawling and scraping tool with LLM-optimized output. 网页爬虫爬取工具 | Web crawler, web scraper, spider. DuckDuckGo search, site crawling, dynamic page scraping. 智能搜索爬取 | Free, no API key required.
bx-ai-rag
ortus-boxlang/skills
Use this skill when building RAG (Retrieval-Augmented Generation) systems with BoxLang AI: aiDocuments() for loading and chunking documents, aiEmbed() for embeddings, vector memory providers, ingesting documents into vector stores, and wiring RAG into agents.
healthcheck
bighardperson/computer-science-skills-collection
Track water and sleep with JSON file storage.
philosophy-of-language
chrislemke/stoffy
Master philosophy of language - meaning, reference, truth, speech acts. Use for: semantics, pragmatics, meaning theory, reference. Triggers: 'meaning', 'reference', 'Frege', 'sense', 'Kripke', 'speech act', 'semantics', 'pragmatics', 'truth conditions', 'propositions', 'names', 'descriptions', 'rigid designator', 'natural kind', 'context', 'indexical'.
rag-pipeline-architect
viliawang-pm/ai-engineering-toolkit
>
vectorize
danielrosehill/claude-image-production-plugin
Use when the user wants to trace a raster image (PNG/JPEG) into an SVG vector — useful for logos, line art, diagrams, and stylized illustrations. Wraps `vtracer` (Rust-backed, via Python wheel in the plugin venv). Companion to `svg-to-raster` (other direction).
agent-workflows
cyrilichti/agent-workflows
>-
build-context-model
alex-on-ai/company-llm-wiki
Build and maintain a Company Context Model - the root-level document that lets any AI assistant (ChatGPT, Claude, n8n agents) produce specific, on-brand, delegation-ready output instead of generic slop. /build writes a usable context-model.md immediately, then enriches it from sources or an interview; unresolved gaps stay visible but never block later skills. /refresh runs the weekly update ritual. Triggers - "build context model", "build my context model", "/build-context-model", "/build", "/refresh", "set up company context", "my AI answers are generic".
catalyst-calendar
anthropics/financial-services-plugins
Build and maintain a calendar of upcoming catalysts across a coverage universe — earnings dates, conferences, product launches, regulatory decisions, and macro events. Helps prioritize attention and position ahead of events. Triggers on "catalyst calendar", "upcoming events", "what's coming up", "earnings calendar", "event calendar", or "catalyst tracker".
ai-readiness
anthropics/financial-services-plugins
Scan the portfolio for the highest-leverage AI opportunities and rank where to deploy operating-partner time. Ingests quarterly updates and financials across multiple portfolio companies, identifies quick wins at each, and stacks them into a single ranked action list. Use during quarterly portfolio reviews, annual planning, or when deciding which companies get AI investment first. Triggers on "AI readiness", "AI opportunity scan", "where should we deploy AI", "AI across the portfolio", "AI quick wins", or "which portcos are ready for AI".
morning-note
anthropics/financial-services-plugins
Draft concise morning meeting notes summarizing overnight developments, trade ideas, and key events for coverage stocks. Designed for the 7am morning meeting format — tight, opinionated, actionable. Triggers on "morning note", "morning meeting", "what happened overnight", "trade idea", "morning call prep", or "daily note".
LangChain Middleware & HITL
langchain-ai/langchain-skills
INVOKE THIS SKILL when you need human-in-the-loop approval, custom middleware, or structured output. Covers HumanInTheLoopMiddleware for human approval of dangerous tool calls, creating custom middleware with hooks, Command resume patterns, and structured output with Pydantic/Zod.
ai-readiness
anthropics/financial-services
Scan the portfolio for the highest-leverage AI opportunities and rank where to deploy operating-partner time. Ingests quarterly updates and financials across multiple portfolio companies, identifies quick wins at each, and stacks them into a single ranked action list. Use during quarterly portfolio reviews, annual planning, or when deciding which companies get AI investment first. Triggers on "AI readiness", "AI opportunity scan", "where should we deploy AI", "AI across the portfolio", "AI quick wins", or "which portcos are ready for AI".
catalyst-calendar
anthropics/financial-services
Build and maintain a calendar of upcoming catalysts across a coverage universe — earnings dates, conferences, product launches, regulatory decisions, and macro events. Helps prioritize attention and position ahead of events. Triggers on "catalyst calendar", "upcoming events", "what's coming up", "earnings calendar", "event calendar", or "catalyst tracker".
morning-note
anthropics/financial-services
Draft concise morning meeting notes summarizing overnight developments, trade ideas, and key events for coverage stocks. Designed for the 7am morning meeting format — tight, opinionated, actionable. Triggers on "morning note", "morning meeting", "what happened overnight", "trade idea", "morning call prep", or "daily note".
image-gen
spillwavesolutions/image_gen
Generate compelling cover images and in-article illustrations for technical articles using the imagen CLI tool. Use when asked to "generate images", "create cover image", "make article illustrations", "create visual assets", or "add images to article". Handles both high-impact conceptual cover images and technical diagrams/illustrations for specific concepts. Includes prompt engineering best practices and SEO-friendly image integration.
scaffold-rules
plaited/agent-eval-harness
Scaffold development rules for AI coding agents. Auto-invoked when user asks about setting up rules, coding conventions, or configuring their AI agent environment.
multi-model-orchestrator
majiayu000/spellbook
Use when coordinating complex tasks across multiple AI agents with a centralized handoff document for planning, execution tracking, and feedback fusion.
tax-efficient-investing
gajetoso/financeskills
When the user wants to invest in a tax-efficient way, maximise contributions to tax-advantaged accounts, understand the tax drag on investment returns, compare traditional vs. Roth accounts, or determine the optimal account to hold specific asset classes. Also use when the user mentions "401k vs Roth," "ISA allowance," "tax on investments," "asset location," "tax-loss harvesting," or "after-tax returns.
masthead-storage-savings-with-datasets
masthead-data/for-agents
Optimize BigQuery storage costs at the dataset level by switching storage billing models and setting expiration policies.
prompt-engineer
nicolasestrem/antigravity-gemini-skills
a senior prompt engineer with expertise in crafting and optimizing prompts for maximum effectiveness
pgvector
terminalskills/skills
>-
dataverse-mcp
korchard333/claude-power-platform-community
Dataverse MCP (Model Context Protocol) Integration. Use when: querying Dataverse data conversationally, Copilot Studio tool integration, schema discovery in constrained environments, live data validation during development.
simulink-interactions
simulink/skills
Resolve references to the currently open or selected Simulink context ("this model", "this subsystem", "this block", "selected blocks") and find blocks in an open model. Use whenever the user refers to "this model", "this block", "this subsystem", "selected blocks", or asks to find specific blocks in an already-open model. After resolving context, hand off to the appropriate Simulink skill for edits, simulation, or testing.
bridge-commons
mikeng-io/agent-skills
Shared contract for all bridge adapters — pre-flight SOP, standardized input/output schemas, artifact format, and status semantics. Read by any bridge or orchestrating skill. Not invocable standalone.
xcodebuildmcp-rendering-streaming-review
getsentry/xcodebuildmcp
Use when reviewing XcodeBuildMCP rendering, streaming fragment, next-step, and CLI output mode changes for boundary violations.
web-search
halt-catch-fire/superpowers
Web search and content extraction with Tavily and Exa via inference.sh CLI. Apps: Tavily Search, Tavily Extract, Exa Search, Exa Answer, Exa Extract. Capabilities: AI-powered search, content extraction, direct answers, research. Use for: research, RAG pipelines, fact-checking, content aggregation, agents. Triggers: web search, tavily, exa, search api, content extraction, research, internet search, ai search, search assistant, web scraping, rag, perplexity alternative
langsmith-dataset
langchain-ai/langchain-skills
INVOKE THIS SKILL when creating evaluation datasets from trace OR uploading datasets to LangSmith OR querying datasets. Covers dataset types (final_response, single_step, trajectory, RAG) and LangSmith upload. Contains helper scripts to use or refer to.
LangSmith Datasets
langchain-ai/langchain-skills
INVOKE THIS SKILL when creating evaluation datasets from trace OR uploading datasets to LangSmith OR querying datasets. Covers dataset types (final_response, single_step, trajectory, RAG) and LangSmith upload. Contains helper scripts to use or refer to.
llm-obs-experiment-py-bootstrap
datadog-labs/agent-skills
Generates a self-contained Python experiment client that uses the ddtrace.llmobs SDK. Emits either a runnable .py script or a Jupyter .ipynb notebook matching the canonical DataDog reference notebook style. Use when the user says "generate Python experiment", "write an SDK experiment", "create a ddtrace experiment", "Python notebook experiment", "use the LLM Obs SDK", or has `ddtrace` installed and wants idiomatic SDK code.
chroma
firecrawl/ai-research-skills
Open-source embedding database for AI applications. Store embeddings and metadata, perform vector and full-text search, filter by metadata. Simple 4-function API. Scales from notebooks to production clusters. Use for semantic search, RAG applications, or document retrieval. Best for local development and open-source projects.
prompt-guard
firecrawl/ai-research-skills
Meta's 86M prompt injection and jailbreak detector. Filters malicious prompts and third-party data for LLM apps. 99%+ TPR, <1% FPR. Fast (<2ms GPU). Multilingual (8 languages). Deploy with HuggingFace or batch processing for RAG security.
project-kickoff
jezweb/claude-skills
Bootstrap new projects with curated settings.local.json permissions, CLAUDE.md, and .gitignore. Detects project type (cloudflare-worker, vercel-app, node-generic, python, ops-admin) and generates grouped, commented permission presets. Also tidies existing messy settings files (removes leaked secrets, shell fragments, deprecated MCP refs, duplicate entries). Trigger with 'kickoff', 'new project', 'bootstrap', 'setup claude', 'tidy permissions', 'clean settings', or 'init project'.
elegant-code
athola/claude-night-market
Guide minimal code via a decision ladder with full safety, edge, and negative-case coverage. Use when adding code, choosing a dependency, or auditing a diff.
perf-comparison
clickhouse/clickhouse
Evaluate ClickHouse performance test results from existing CI/dashboard data or local perf.py runs. Use to check PR performance changes, run local performance tests, compare with history, assess flakiness, inspect coverage/PR relevance, and summarize whether a result is actionable.
omniroute-embeddings
diegosouzapw/omniroute
Embeddings via OmniRoute using OpenAI /v1/embeddings format with auto-fallback across text-embedding-3-large, Voyage, Cohere, Gemini embeddings, Jina. Use when the user needs vector embeddings for RAG, similarity search, or clustering.
docs-sync
redis/node-redis
Analyze master branch implementation and configuration to find missing, incorrect, or outdated documentation in docs/, README.md, and per-package READMEs. Use when asked to audit doc coverage, sync docs with code, or propose doc updates/structure changes. Provide a report and ask for approval before editing docs.