Measure any OpenAI- or Anthropic-compatible LLM endpoint across six dimensions: availability, request fidelity, speed, concurrency, protocol compliance, and quality regression.
A rigorous maintainer-grade workflow that re-reviews GitHub pull requests against the current base branch, binding every verdict to exact Git OIDs.
A field-tested guide for building iOS/macOS apps with XcodeGen, SwiftUI and SPM, plus Apple code signing, notarization and CI/CD fixes.
A thin, battle-tested layer over the minimax-docx OpenXML engine that produces contract-grade Word files and enforces a PDF→PNG visual verification chain.
A rigorous visual QA protocol that audits already-rendered web, deck, dashboard, and Electron UIs with real-browser evidence and produces an evidence-backed defect report.
Exports the complete transcript of any claude.ai chat or share link — tool calls, attachments and all — into local Markdown with a lossless-render guarantee.
A battle-tested guide to writing, testing, registering, and debugging Claude Code PreToolUse / PostToolUse / SessionStart / Stop hooks.
A macOS network-debugging skill that isolates and fixes Tailscale conflicts with Shadowrocket/Clash/Surge/OrbStack — route hijacks, proxy env vars, SSH double tunnels, Docker proxy propagation and stalled DNS.
Writes house-quality UI component specs — anatomy, variants, the 8 states, token mapping, and gated accessibility checks.
A rigorous playbook for designing and shipping Expo/React Native screens that feel truly native, verified by simulator screen recordings.
A Bugcrowd-specific reporting overlay: VRT selection, manual severity-override requests, and ready-made out-of-scope rebuttals.
Turns approved business evidence into a reviewable Google Ads asset manifest — sitelinks, callouts, snippets, image assets and PMax briefs — and publishes only after explicit approval.
A read-only Google Ads audit skill that reduces account health to three pulse metrics — waste, demand captured, CPA — each tied to a named contributor and a concrete fix.
An expert skill for DORA (Regulation (EU) 2022/2554): article-level gap analysis, ICT incident classification and reporting, third-party risk, and TLPT scoping.
Generates WeChat Official Account cover images and in-article illustrations by matching the article's title and content to reusable style presets.
Orchestrates five sub-agents to turn your idea and experiment logs into a submission-ready LaTeX manuscript and compiled PDF.
Runs PaperOrchestra's four LLM-as-judge autoraters — Citation F1, 6-axis literature-review quality, and two side-by-side comparisons — on your paper drafts.
Audits a paid ad account against a typed 20-item ROAS profile using your own exported data and returns a SHIP/FIX/BLOCK/UNDECIDED verdict.
Guides Claude in writing PinMe Worker (Cloudflare Worker TypeScript) payment code that calls UniwebPay directly via @uniwebpay/sdk.