compare
01Skill Claude CodeCodex
Structured comparison of 2+ alternatives with consistent criteria and decision matrix.
17 2d ago A 15 tokens
original Apache-2.0
Skill Claude CodeCodex
Multi-step research orchestration. Use when user asks "research X", "summarize current state of Y", "what's the latest on Z", or compares approaches. Calls extract(action="agent") which searches the web, extracts top results, then synthesises a citation-preserving Markdown answer with one configured LLM.
17 2d ago A 68 tokens
original Apache-2.0
scrape-batch
03Skill Claude CodeCodex
Extract many known URLs in one polite, rate-limited pass. Use when the user hands over a list of links, a set of search hits to read in full, or asks to "scrape these pages" / "pull the content from all of them". Drives extract(action="batch"), which fans out with per-domain rate limiting and returns partial results…
17 2d ago A 84 tokens
original Apache-2.0
Skill Claude CodeCodex
Remove project-local Crawl4AI cache and robots data without deleting outputs or installed runtimes.
12 21d ago A 24 tokens
original MIT
Skill Claude CodeCodex
Install or update Crawl4AI, Trafilatura, and browser dependencies in isolated Python virtual environments.
12 21d ago A 25 tokens
original MIT
crawl4ai
06Skill Claude CodeCodex
Crawl, scrape, question, or extract structured data from live websites with Crawl4AI and optional Trafilatura. Use for fresh web content, multi-page crawls, compact page reading, and JSON extraction.
12 21d ago A 47 tokens
original MIT
research
07Skill Claude CodeCodex
Browse the live web like a person and build a faithful evidence locker — a folder of clean markdown, one file per source page with metadata, saved under ./research/. YOU (Claude) drive the browsing — running searches, reading the result links, picking which to visit, and inspecting each page's content before saving…
3 1mo ago A 138 tokens
original MIT
Skill Claude CodeCodex
Use this whenever the user wants to publish, release, ship, cut a version, push a package, publish a container, publish to PyPI, publish to GHCR, publish to Docker Hub, publish to the MCP Registry, prepare release notes, bump the SourceWeave version, or verify that SourceWeave is release-ready. Use it even if the user…
2 4mo ago A 119 tokens
original MIT
Skill Claude CodeCodex
Use this whenever the user wants to validate SourceWeave Web Search locally before deployment or after runtime changes, especially when they mention smoke-testing searchweb and readpages, checking whether src/sourceweavewebsearch/tool.py and artifacts/sourceweavewebsearch.py are still aligned, confirming host-side…
2 4mo ago A 109 tokens
original MIT
e2e-runner
10Kacper0199/Opencode-Ultrathinker
Skill Claude CodeCodex
End-to-end testing specialist using Playwright. Use PROACTIVELY for generating, maintaining, and running E2E tests. Manages test journeys, quarantines flaky tests, uploads artifacts (screenshots, videos, traces), and ensures critical user flows work.
2 3mo ago A 59 tokens
Kacper0199/Opencode-Ultrathinker
Skill Claude CodeCodex
Security vulnerability detection and remediation specialist. Use PROACTIVELY after writing code that handles user input, authentication, API endpoints, or sensitive data. Flags secrets, SSRF, injection, unsafe crypto, and OWASP Top 10 vulnerabilities.
2 3mo ago A 52 tokens
Kacper0199/Opencode-Ultrathinker
Skill Claude CodeCodex
Backend architecture patterns, API design, database optimization, and server-side best practices for Node.js, Express, and Next.js API routes.
2 3mo ago A 31 tokens