Agent Skills

PDF

✓★ 158,000

by Anthropic

Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. When Claude needs to fill in a PDF form or programmatically process, generate, or analyze PDF documents at scale. license: Proprietary. LICENSE.txt has complete terms

pdftk-server

✓★ 36,200

by github

Command-line PDF manipulation covering merging, splitting, encryption, form filling, watermarking, and metadata extraction. Supports 12+ operations including merge, split, rotate, encrypt/decrypt, burst, stamp, watermark, and repair Fill PDF forms from FDF/XFDF data with optional flattening to lock filled fields Extract and manipulate metadata, bookmarks, and embedded files; collate separately scanned pages Cross-platform installation via package managers (Windows, macOS, Linux) with...

sponsor-finder

✓★ 36,200

by 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...

earnings-analysis

✓★ 33,000

by anthropic

Create professional equity research earnings update reports (8-12 pages, 3,000-5,000 words) analyzing quarterly results for companies already under coverage.…

earnings-analysis

✓★ 33,000

by anthropic

Create professional equity research earnings update reports (8-12 pages, 3,000-5,000 words) analyzing quarterly results for companies already under coverage.…

datapack-builder

✓★ 33,000

by anthropic

Build professional financial services data packs from various sources including CIMs, offering memorandums, SEC filings, web search, or MCP servers. Extract,…

datapack-builder

✓★ 33,000

by anthropic

Build professional financial services data packs from various sources including CIMs, offering memorandums, SEC filings, web search, or MCP servers. Extract,…

hook-development

✓★ 31,500

by anthropic

Event-driven automation for Claude Code plugins using prompt-based and command hooks. Supports 9 hook events (PreToolUse, PostToolUse, Stop, SubagentStop, UserPromptSubmit, SessionStart, SessionEnd, PreCompact, Notification) for validation, policy enforcement, and workflow automation Prompt-based hooks use LLM reasoning for context-aware decisions; command hooks execute bash scripts for deterministic checks Includes matchers for filtering by tool name (exact, regex, wildcard) and parallel...

web-research

★ 25,700

by 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

✓★ 23,200

by 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

★ 399

by 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

✓★ 158

by brave

USE FOR getting AI-generated POI text descriptions. Requires POI IDs obtained from web-search (with result_filter=locations). Returns markdown descriptions…

llm-context

✓★ 158

by brave

USE FOR RAG/LLM grounding. Returns pre-extracted web content (text, tables, code) optimized for LLMs. GET + POST. Adjust max_tokens/count based on complexity.…

spellcheck

✓★ 158

by 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

✓★ 158

by 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

★ 157

by 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...

apollo-client

★ 90

by apollographql

Comprehensive guide for building React applications with Apollo Client 4.x, covering queries, mutations, caching, and state management. Supports multiple React frameworks and setups: client-side apps (Vite, CRA), Next.js App Router with React Server Components, React Router 7 with streaming SSR, and TanStack Start Includes hooks for queries ( useQuery , useLazyQuery ), mutations ( useMutation ), and Suspense-based patterns ( useSuspenseQuery , useBackgroundQuery ) for modern React 18+ and 19...