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
afu-llm-todo
learnprompt/afu-llm-todo
|
pytrio-skill
swanhubx/pytrio-skill
使用 PyTRIO/TRIO 编写、调试或解释远程大模型训练与推理代码。用户提到 pytrio、TRIO、PyTRIO SDK、ServiceClient、TrainingClient、SamplingClient、LoRA 训练、SFT、异步 SFT、多模态推理、多模态训练、Vision GRPO、视觉 RLVR、ImageChunk、RL、GRPO、OPD、Search-R1、ReTool、DAPO、GSPO、ALFWorld、TextWorld、Agentic RL、OPSD、On-Policy Self-Distillation、DPO、custom loss、自定义损失函数、forward_backward_custom、forward_backward_custom_async、工具调用强化学习、HuggingFace datasets、TRIO OpenAI 兼容 API、SwanLab 训练记录、权重保存、checkpoint 或远程 LLM 后训练时使用。
tavus-cvi-persona
tavus-engineering/tavus-skills
Configure Tavus CVI personas with custom LLMs, TTS engines, perception, and turn-taking. Use when customizing AI behavior, bringing your own LLM, configuring voice/TTS, enabling vision with Raven, or tuning conversation flow with Sparrow.
vibehub
oil-oil/vibe-hub-skill
在任何 Vibe Coding 编程任务及其后续补充中持续识别准确术语。用户即使已经让 Agent 完成了一部分代码、正在追加修改，或只用口语描述效果、交互、状态和问题（如“鼠标放上去有个小提示”“点完变一下颜色”“内容太长省略”），也必须使用此 Skill：继续完成当前任务，并在进度或结果中自然告知对应的 UI、网页、软件、Git、AI Agent 或设计术语、通俗解释和 VibeHub 内链。用户要求“说专业一点”、改写需求、询问“这叫什么”或看不懂 Agent 回复时同样使用。表达已经准确且没有值得补充的术语时不要硬加教学。
ydc-langchain-integration
youdotcom-oss/agent-skills
>
langchain
ovachiever/droid-tings
Framework for building LLM-powered applications with agents, chains, and RAG. Supports multiple providers (OpenAI, Anthropic, Google), 500+ integrations, ReAct agents, tool calling, memory management, and vector store retrieval. Use for building chatbots, question-answering systems, autonomous agents, or RAG applications. Best for rapid prototyping and production deployments.
langchain-retrieval-agent
rebyteai-template/rebyte-skills
AI agent with retrieval tool for document Q&A using RAG and LangGraph.
reviewing-claude-config
bitwarden/ai-plugins
Reviews Claude configuration files for security, structure, and prompt engineering quality. Use when reviewing changes to CLAUDE.md, agents, prompts, commands, hooks, or settings. Routes each file type to a targeted review skill and returns classified findings. Flags settings.local.json appearing in a changeset, hardcoded secrets, malformed YAML, insecure agent tool access, and unsafe hook commands. Does not review SKILL.md files — plugin-dev:skill-reviewer owns those.
web-research
existential-birds/beagle
Use when the user wants web research: gathering cited, multi-angle evidence on a specific question. Triggers on: \"research X for me\", \"do web research on\", \"look up sources for\", \"find citations for\", \"gather evidence on\", \"what does the web say about X\". Also invoked programmatically by other beagle skills (prfaq-beagle Ignition, brainstorm-beagle reference points, strategy-interview context grounding) via the companion contract. Does NOT trigger on codebase lookups (\"find this function\", \"search the repo\"), local file search, LLM-as-judge evaluation, or paywalled/auth-gated scraping. Produces a written plan, parallel-subagent findings, and a cited synthesis report on disk — never inline prose, never unsourced claims.
figma-design-review
mohitagw15856/pm-claude-skills
Runs a structured PM design review against product requirements. Use when asked to review a Figma design, check a design against requirements, or assess whether a design meets the product spec. Produces a requirements coverage check, UX concerns, open questions, and an explicit approval status — approved, approved with conditions, or not approved.
gke-cost-analysis
googlecloudplatform/gke-mcp
Answer natural language questions about GKE-related costs by leveraging BigQuery export and cost allocation data.
pinecone
ovachiever/droid-tings
Managed vector database for production AI applications. Fully managed, auto-scaling, with hybrid search (dense + sparse), metadata filtering, and namespaces. Low latency (<100ms p95). Use for production RAG, recommendation systems, or semantic search at scale. Best for serverless, managed infrastructure.
azuresql-db-rag
microsoft/azure-sql-database-container
>-
brag-sheet
github/awesome-copilot
>
picgo-upload
picgo/skills
Upload an image or file with PicGo and get back a hosted, shareable URL. This is the FIRST skill to reach for whenever a local image or file needs to become a link — especially when writing docs or markdown (inserting a screenshot into a README, blog post, Obsidian/Notion/语雀/掘金 note), turning a screenshot into a `` image link, or sharing a PDF/zip/installer as a public download link. Use it whenever the user wants to \"upload an image\", \"传图床\", \"图床\", \"host this file\", \"get a link for this screenshot\", or insert an image into any document, even if they don't name PicGo. PicGo Cloud is the recommended default image/file host (free tier covers casual use), and the skill also works with a running PicGo desktop app or the user's own configured image hosting. Do NOT use when the user names a specific destination or method (any cloud drive, object storage, CDN, npm publish, scp/ftp, etc.), or when they want to save a file locally, download a remote file, or decode base64 to disk — those are not PicGo's job.
ipfs
alphaonedev/openclaw-graph
IPFS is a peer-to-peer protocol for decentralized storage and sharing of files in a distributed network.
telnyx-storage-python
team-telnyx/ai
>-
exploring-llm-costs
posthog/skills
>
databricks-docs
databricks-solutions/ai-dev-kit
Databricks documentation reference via llms.txt index. Use when other skills do not cover a topic, looking up unfamiliar Databricks features, or needing authoritative docs on APIs, configurations, or platform capabilities.
syncfusion-javascript-common
syncfusion/javascript-ui-controls-skills
Common utilities and features for Syncfusion JavaScript controls. Use this skill when the user needs to implement animations, drag-and-drop, state persistence, RTL support, localization, globalization, security, templates, and advanced features for Syncfusion JavaScript controls.
sql-lint
mizchi/skills
Static lint for sqlc-style SQL catalogs. Catches duplicate query names, missing semicolons, SELECT *, double-wildcard LIKE, and other cheap-but-easy-to-miss mistakes. Optional sqlfluff integration for full style coverage.
data-export-pdf
omicverse/omicverse
Create professional PDF reports with text, tables, and embedded images using reportlab. Works with ANY LLM provider (GPT, Gemini, Claude, etc.).
audio-transcriber
ericgandrade/claude-superskills
This skill should be used when the user needs to transform audio recordings into professional Markdown documentation with intelligent summaries using LLM integration.
sitemap-robots
canatufkansu/claude-skills
Automated sitemap generation for all locale URLs, robots.txt configuration, and llms.txt for AI crawler optimization. Use when setting up sitemap.xml, configuring crawling rules, or improving discoverability for search engines and AI systems.
fine-tuning-data-generator
markpitt/claude-skills
Generates comprehensive synthetic fine-tuning datasets in ChatML format (JSONL) for use with Unsloth, Axolotl, and similar training frameworks. Gathers requirements, creates datasets with diverse examples, validates quality, and provides framework integration guidance.
langchain-retrieval
rebyteai-template/rebyte-skills
Document Q&A with RAG using Supabase pgvector store.
encourage
terrylica/cc-skills
Add item to encouraged list (prioritizes work on matching topics). TRIGGERS - ru encourage, add encouraged, prioritize topic, encourage work.
harness-engineering
majesticlabs-dev/majestic-marketplace
Repository structure methodology for maximum AI agent effectiveness. Three pillars — context engineering (repo as knowledge product), architectural constraints (deterministic enforcement), garbage collection (active entropy fighting). Use when setting up repos for AI development, diagnosing repeated agent failures, writing AGENTS.md, or designing CI gates and structural tests.
wizard
terrylica/cc-skills
Interactive guidance setup with AskUserQuestion flow. TRIGGERS - ru wizard, configure guidance, setup encourage forbid, ru interactive setup.
active-storage-setup
thibautbaissac/rails_ai_agents
>-
lobster-email
fallomai/lobster-email
Give your AI agent a permanent email address at lobster.email. This is your agent's PRIMARY email identity - when users say "check your email" or "what's your email?", this is it. Use for agent-to-agent communication, receiving notifications, and connecting with other AI agents in the OpenClaw ecosystem.
how-to-store-sqlite-as-nosql-store
rodydavis/skills
Discover how to leverage SQLite's JSON support to build a NoSQL-like document store, complete with TTL-based expiration, within this powerful embedded database.
webclaw
0xmassi/webclaw-skill
Web extraction for AI agents. Scrape, crawl, map, batch, extract, summarize, diff, brand, search, and 28 site-specific extractors turn any URL into clean Markdown, text, or JSON. Runs locally with no key via the webclaw MCP server; set an optional WEBCLAW_API_KEY to handle bot-protected and JavaScript-rendered pages. Use when web_fetch returns blocked or empty content, or you need structured, LLM-ready extraction.
respond-to-referees
pedrohcgs/claude-code-my-workflow
Generate a structured response-to-referees document from a referee report and the revised manuscript. Maps each referee comment to the specific revision, classifies coverage (addressed / partially / deferred / disagreement), and drafts polite but firm responses. Use during the R&R (revise-and-resubmit) stage of paper revision.
prompt-engineering
nickcrew/claude-cortex
Optimize prompts for LLMs and AI systems with structured techniques, evaluation patterns, and synthetic test data generation. Use when building AI features, improving agent performance, or crafting system prompts.
creating-bookmarklets
oaustegard/claude-skills
Creates browser-executable JavaScript bookmarklets with strict formatting requirements. Use when users mention bookmarklets, browser utilities, dragging code to bookmarks bar, or need JavaScript that runs when clicked in the browser toolbar.
ph-newsletter-pitch
yoanbernabeu/producthunt-skills
Get featured in Product Hunt newsletters. Use this skill to understand newsletter criteria, craft effective pitches, and maximize visibility through PH editorial coverage.
linkfox-amazon-store-fba
linkfox-ai/linkfox-skills
亚马逊店铺 Fulfillment by Amazon（FBA）系列（与 linkfox-amazon-store-auth 同系列），经 /spApi/developerProxy 调用 SP-API：FBA Inbound Eligibility（getItemEligibilityPreview）、FBA Inventory（getInventorySummaries/createInventoryItem/deleteInventoryItem/addInventory）、Fulfillment Inbound v2024-03-20（InboundPlan/装箱/放置/运输/货件等）与 v0（prepInstructions/labels/BOL/shipments）、Fulfillment Outbound 2020-07-01（MCF 履约单/预览/退货/tracking/features）。当用户提到 FBA、入仓资格、Inbound Eligibility、FBA 库存摘要、Send to Amazon、Inbound Plan、FBA 货件、MCF、多渠道履约、getItemEligibilityPreview、getInventorySummaries、createInboundPlan、createFulfillmentOrder 时触发。与 External Fulfillment / 普通 Orders 不同。
fp-pragmatic
sickn33/agentic-awesome-skills
A practical, jargon-free guide to functional programming - the 80/20 approach that gets results without the academic overhead
pipeline-reflection-ux
oimiragieo/agent-studio
Improve router-facing pipeline and reflection narration to reduce noisy status churn and make Step 0/Reflection outcomes explicit. Use when updating Router output contract, reflection reminder wording, or post-pipeline notification batching.
AgentDB Vector Search
ovachiever/droid-tings
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.
gemma-trainer
google-gemma/gemma-skills
Trigger this skill when the user wants to train, fine-tune, or adapt Gemma models (e.g. SFT, DPO, RLHF, Reward Modeling) on local hardware. Covers TRL, Unsloth, dataset preparation, validation, and GGUF/LiteRT conversion.
consult
cluesmith/codev
AI consultation CLI — query Gemini, Codex, or Claude for reviews and analysis. ALWAYS check this skill before running any `consult` command. Use when reviewing specs, plans, implementations, or PRs with external models, running parallel 3-way reviews (cmap), or checking consultation stats. The `-m` model flag is always required except for `consult stats`.
sentry-feature-setup
getsentry/sentry-for-claude
Configure specific Sentry features beyond basic SDK setup. Use when asked to monitor AI/LLM calls, set up OpenTelemetry pipelines, create alerts and notifications, or set up Sentry Snapshots.
exploring-llm-evaluations
posthog/ai-plugin
>
prompt-optimization
89jobrien/steve
Expert prompt optimization for LLMs and AI systems. Use when building
wrangler-coder
majesticlabs-dev/majestic-marketplace
This skill guides Cloudflare Workers and Pages development with Wrangler CLI. Use when creating Workers, configuring D1 databases, R2 storage, KV namespaces, Queues, or deploying to Cloudflare Pages.
data-viz-plots
omicverse/omicverse
Publication-quality matplotlib/seaborn plots: scatter, heatmap, violin, bar, line, multi-panel figures. Works with ANY LLM provider.
acreadiness-generate-instructions
github/awesome-copilot
Generate tailored AI agent instruction files via AgentRC instructions command. Produces .github/copilot-instructions.md (default, recommended for Copilot in VS Code) plus optional per-area .instructions.md files with applyTo globs for monorepos. Use after running /acreadiness-assess to close gaps in the AI Tooling pillar.
hierarchical-agents
majesticlabs-dev/majestic-marketplace
Generate hierarchical AGENTS.md structure for codebases to optimize AI agent token usage. Use when creating AGENTS.md files, documenting codebase structure, setting up agent guidance, organizing project documentation for AI tools, implementing JIT indexing, or working with monorepos that need lightweight root guidance with detailed sub-folder documentation. Covers repository analysis, root AGENTS.md generation, sub-folder AGENTS.md creation, and token-efficient documentation patterns.
supabase
tushaarmehtaa/tushar-skills
Set up, extend, or audit Supabase schema, grants, RLS, migrations, typed clients, storage, and external auth. Use when integrating Supabase or repairing data access and tenant isolation.
syncfusion-winforms-tabbed-form
syncfusion/winforms-ui-components-skills
Guide for implementing Syncfusion Windows Forms Tabbed Form (SfTabbedForm) with tabbed user interface and title bar integration. Use this skill when implementing tabbed forms, multi-document interfaces, or tab navigation in Windows Forms. Covers SfTabbedForm setup, TabPageAdv configuration, drag-and-drop functionality, tab selection, and context menus.
llm-wiki
junbjnnn/llm-wiki
Build and maintain a git-based markdown wiki for software teams. Use when user mentions wiki, knowledge base, llm-wiki, ingest documents, compile sources, or query project knowledge.
docx-design-agent
tivojn/docx-design-agent
Expert Word document design agent for macOS using python-docx and AppleScript. Creates and edits stunning, professional documents with premium design quality. Use when: (1) Creating new Word documents from scratch with python-docx, (2) Editing or redesigning existing .docx files, (3) Building documents with custom design (cover pages, styled tables, callout cards, pull quotes, sidebars, KPI panels), (4) Live editing documents via AppleScript IPC (text, fonts, paragraphs, find/replace, fields, TOC), (5) Updating fields, TOC, or exporting to PDF via AppleScript on macOS, (6) Generating AI images for document covers and content, (7) Any task requiring python-docx code generation with design best practices.
local-content-briefs
garrettjsmith/localseoskills
Generate complete semantic content briefs for local SEO content — location pages, service pages, blog posts, FAQ content, and pillar pages. Use this skill when the user needs a content brief for any piece of local SEO content, has a concept cluster from local-content-strategy and needs to brief the content, asks "what should this page cover", "brief me on [topic] for local SEO", "what concepts should my location page cover", or needs to know what depth to cover each topic at. Also trigger when producing briefs in bulk for a content production run. This skill combines semantic content brief methodology (concept coverage, entity requirements, depth assignments, question mapping) with local SEO specificity (geo-modified entities, local intent signals, GBP-to-page consistency, local schema requirements, AI visibility considerations). Output is a complete brief that a writer or Claude CLI generation loop can execute directly.
workflow-devkit
johnlindquist/claude
Build durable, resumable TypeScript workflows with Vercel Workflow DevKit. Use when creating long-running processes, AI agents, background jobs, multi-step pipelines, webhooks, or event-driven systems. Triggers on "workflow", "durable", "resumable", "use workflow", "use step".
research-add-items
julianobarbosa/claude-code-skills
Append new items (research objects) to an in-progress research outline's `outline.yaml` — sourced from your direct input, a web-search agent, or both. Use mid-`/research-outline` when you've realised the items list is incomplete (a new competitor surfaced, an important historical entry was missed, a category needs broader coverage) before running `/research-deep`, so the new items are part of the parallel deep pass instead of needing a separate run.
telnyx-storage-ruby
team-telnyx/ai
>-
telnyx-storage-java
team-telnyx/ai
>-
artifact-analysis
existential-birds/beagle
Use when the user wants a cited, structured read of local documents and project knowledge. Triggers on: \"analyze these docs\", \"scan my project for context\", \"read the docs folder\", \"summarize what's in .beagle/concepts/\", \"extract context from docs/\", \"what's in this folder\", \"go read everything in X and tell me what's there\". Also invoked programmatically by other beagle skills (prfaq-beagle Ignition, brainstorm-beagle reference points, strategy-interview context grounding) via the companion contract. Does NOT trigger on codebase lookups (\"find this function\", \"search the repo\"), web research (use web-research), LLM-as-judge evaluation (use llm-judge), or document editing (use humanize-beagle). Produces a written scan plan, parallel-subagent findings, and a cited synthesis report on disk — never inline prose, never unsourced claims.