Agent Skills
Instruction packs that give your AI agent know-how. Three different kinds — pick the right one below.
✦ Standalone skills2,933
Self-contained. Install one into any project and it works on its own — no other software needed.
🧰 Tool add-ons725
Come bundled with a specific tool and only work together with it — they teach your agent how to operate that tool.
sponsor-finder
✓★ 36,200by github
Identify sponsorable open source maintainers across your project's entire dependency tree. Resolves full dependency trees (direct and transitive) across npm, PyPI, Cargo, Go, RubyGems, Maven, and NuGet using the deps.dev API Discovers funding links from npm metadata, FUNDING.yml files (repo and org-level), and web search; verifies every URL before reporting Groups dependencies by maintainer and funding destination, showing health indicators (Maintained/Partially maintained/Unmaintained) and...
datapack-builder
✓★ 33,000by anthropic
Build professional financial services data packs from various sources including CIMs, offering memorandums, SEC filings, web search, or MCP servers. Extract,…
datapack-builder
✓★ 33,000by anthropic
Build professional financial services data packs from various sources including CIMs, offering memorandums, SEC filings, web search, or MCP servers. Extract,…
web-research
★ 25,700by langchain-ai
Orchestrates multi-source web research by delegating to subagents, synthesizing findings, and producing cited reports. Breaks research questions into 2–5 distinct subtopics, creates a research plan file, and spawns up to 3 subagents in parallel for efficient investigation Each subagent performs 3–5 web searches per subtopic and writes findings to local files with key facts, quotes, and source URLs Synthesizes results by reading local findings files, integrating insights across subtopics, and...
openai-docs
✓★ 23,200by openai
Access current OpenAI developer documentation with MCP tools and model-selection guidance. Prioritizes the OpenAI Developer Docs MCP server for all queries; falls back to web search only on official OpenAI domains if MCP returns no results Includes reference files for model selection, GPT-5.4 upgrade planning, and prompting guidance; always verifies recommendations against live docs before answering Covers seven core OpenAI products: Apps SDK, Responses API, Chat Completions, Codex, gpt-oss,...
tavily-dynamic-search
★ 399by tavily-ai
Search the web, filter results, and extract content so that raw search data never enters your context window . Only your curated print() output comes back.
local-descriptions
✓★ 158by brave
USE FOR getting AI-generated POI text descriptions. Requires POI IDs obtained from web-search (with result_filter=locations). Returns markdown descriptions…
spellcheck
✓★ 158by brave
USE FOR spell correction. Returns corrected query if misspelled. Most search endpoints have spellcheck built-in; use this only for pre-search query cleanup or…
news-search
✓★ 158by brave
USE FOR news search. Returns news articles with title, URL, description, age, thumbnail. Supports freshness and date range filtering, SafeSearch filter and…
deep-research
★ 157by samber
Deep research skill — broad parallel web searches, multi-source validation, confidence tracking, cited Markdown report. Supports 11 research types: market (TAM/SAM, segments, pricing, trends), domain (industry structure, ecosystem, regulatory landscape), technical (architecture, tools, benchmarks), competitive (competitor teardown, positioning, win/loss), product (feature analysis, reviews, roadmap signals), academic (literature survey, citation networks, key authors), person/org (due...