An operating spec that forces Claude to build, retrieve, and correct evidence-grounded local person profiles using only Distilly's exact five MCP tools.
A four-mode code quality skill covering technical-debt cleanup, Ruff/Biome linting, a Python quality gate, and a multi-language universal gate.
Creates properly linked Epic → Feature → Story → Subtask hierarchies in Jira Cloud using SAFe conventions and REST API v3.
A skill for querying and analyzing DepMap CRISPR gene dependency and drug sensitivity data to validate cancer-specific targets.
Verify UI, console, network, performance and accessibility in a real browser through the Chrome DevTools MCP server.
Trains Claude to ship features as thin, working vertical slices — implement, test, verify, commit — instead of dumping an entire feature at once.
A playbook for running parallel code reviews across quality dimensions, then deduplicating findings, calibrating severity and producing one consolidated report.
Debug multi-cause bugs by splitting them into competing hypotheses, investigating them in parallel, and arbitrating the true root cause from evidence.
Runs the SEOmator CLI to audit any site against 373 rules across 20 categories and diff two audits to see what a deploy changed.
Auto-detects your knowledge source type — docs site, GitHub repo, PDF, video — and turns it into an AI-ready skill.
A skill that drives the Actionbook CLI to operate any website — snapshot for element refs, then click, fill, scrape, across many tabs in parallel.
A maintenance skill that scans project-local Claude Code permissions, promotes the good ones to global config, and cleans up redundant or risky entries.
A skill that fetches live Vercel AI SDK docs and AI Gateway model data so Claude codes against the current API instead of stale memory.
Lets Claude Code generate and edit images through OpenAI's GPT Image API with a bundled Python script.
Paste a Bilibili video link or BV ID to fetch comments, run four-axis sentiment analysis, and generate an interactive HTML report.
Search the latest Bilibili videos by keyword with sort/date filters and get a clean Markdown table of views, likes and comments.
Give it a platform and an account ID/URL, and it pulls the channel's recent posts from Douyin, Kuaishou, Bilibili or YouTube, resolves direct download links, and can batch-download them.
Reviews GitHub pull requests with six parallel specialist subagents, adversarial verification, and confidence/severity gates so only high-signal findings get posted.
Splits a research goal into parallel sub-goals, runs each in a headless `claude -p` subprocess, and aggregates everything into a polished standalone report file.
Delegates coding, code review, and plan review to the OpenAI Codex CLI with strict sandbox and review-safety rules.