All skills

Scans a codebase for hardcoded credentials and blocks repomix packaging until it's clean.

Pulls market data, historical financials and WACC inputs for US-listed tickers from yfinance and emits a validated, standardized JSON for downstream financial analysis skills.

Sets up internationalization in React/Next.js/Vue codebases, replaces hard-coded strings with keys, and validates locale parity, plurals, and formatting.

Measure any OpenAI- or Anthropic-compatible LLM endpoint across six dimensions: availability, request fidelity, speed, concurrency, protocol compliance, and quality regression.

Safely analyzes macOS disk usage and produces a cleanup report that explains the real cost of deleting each item.

A phase-based playbook for shipping pull requests that maintainers of third-party repos actually merge.

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.

Rebuilds only the actionable context from local `.claude` session files so you can resume interrupted work without `claude --resume`.

Converts markdown to print- or mobile-ready PDFs with CJK-safe fonts, a theme system, and mandatory page-by-page visual verification.

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.

Extracts every Mermaid diagram from a markdown file and renders them as high-resolution PNG images.

Reviews Claude Code skills against official best practices, with modes for self-review, external repo evaluation, and automated improvement PRs.

Turns vague requests into precise, testable prompt specifications using EARS syntax and domain theory grounding.

Fetches tweets and long-form X Articles with all images and engagement metadata into clean Markdown files.

Compares two videos and generates an interactive, self-contained HTML report with PSNR/SSIM metrics and frame-by-frame visuals.

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.

Git forensics skill that recovers lost commits, branches and stashes, proves merges by content, and retires leftovers only after verified backups.

Turns local ccusage data into a clear, evidence-based explanation of your Claude Code token spend, cost, and quota burn.