Explorar skills

VOVO 全格式数据分析专家 - 远端超级代码解释器与数据洞察引擎。 支持上传任意格式（Excel/CSV/PDF/脏数据等）进行硬核清洗、多维分析、图表生成与商业总结。 打破传统格式限制，全程自动化执行代码沙盒并返回直观产物。

Generate an intelligent context handoff document for the next agent. Triggers on: handoff, hand off, pass to next agent, context handoff, next agent, session done, stage done, wrap up for next agent, /handoff

Create a single weekly narrative anchor that ties one proof asset to a 7-day content loop, so a brand can publish with coherence instead of posting random fragments.

Mint and trade ClawPhunks NFTs. The first collection designed for AI agents.

Turn Gmail into structured dashboards — extract and track subscriptions, packages, invoices, job applications, and more.

AI chief designer that critiques every visual decision through the Quartr standard via Claude Code

Claude Code skill: record Playwright browser automation as MP4 — auto ffmpeg detection, smart naming, clickable output link

Use when test files are accumulating across projects, test suites are growing unwieldy, flaky tests appear, test execution is slow, user asks about test cleanup or archival strategy, or when organizing tests after skill-generated workflows like bkit or superpowers TDD cycles

Run a comprehensive repo-wide documentation truth audit. Cross-references CLAUDE.md, all Markdown docs, structured config files, and the codebase. Surfaces drift, contradictions, orphans, and bloat. Resolves them interactively. Trims CLAUDE.md as a final phase. Long-running, comprehensive, designed for occasional invocation. Use when the user asks for a documentation audit, doc alignment check, CL

Analyze, plan, review, and optimize any codebase across 4 modes: Discovery (understand architecture and risks), Review (validate changes and detect breaking changes), Optimization (find bottlenecks and vulnerabilities), Implementation Planning (generate step-by-step guidance). Works with React, Django, Rails, Go, Rust, and 30+ frameworks. Use when analyzing codebase structure, assessing feature sa

Diagnose SKU-level forecast accuracy for supply chain teams. Computes WMAPE, FVA, ABC segmentation, ADI/CV² demand patterns, and denominator coverage. Exports an Excel report with charts and a prioritized actions worklist.

Use when the user provides a public video URL (YouTube, Bilibili, or any yt-dlp-supported platform) and wants to turn it into a polished Markdown article. In Claude Code the skill runs offline - local faster-whisper for transcription, Claude Code itself writes the article (no external LLM API). Fetch + transcribe are local commands; generation is done by you (the assistant) reading the transcript