Explore skills

Verify a `review-ready` work item (or an entire batch) meets every acceptance criterion and every Quality Bar gate. Reject by default — each check requires cited evidence. Must run in a session distinct from the `/implement` session that produced the item.

Run an audit scanner against ODD repositories. Reads scanner definition, picks unscanned items from coverage manifest, writes findings, updates navigation.

Show current progress of the audit and implementation system — scanner completion, backlog counts, blockers.

根据用户描述创建任务条目，自动判断归属（已有项目、新建项目、跨项目复制），插入到合适位置。当用户说"添加任务""新建任务""加一个任务""创建任务""我要学""我要做"时触发。

第四步：生成书级写作约束 BOOK-STYLE.md。调用方式：/config-book <book-id>

Actively exercise the headsup hook stack end-to-end. Flashes the three tab colors (idle → processing → waiting) on the current tab and verifies each round-trips through the daemon. Use when the user asks "is the headsup thing actually working", "test the headsup hooks", "/headsup-diagnose", or wants confirmation after a change. Different from /headsup-status (passive snapshot) — this skill perform

Deep-dive research and analysis of external reference materials (YouTube videos, articles, GitHub repos, documentation, code sources) against the current project. Reads pulse-config.yaml for config. Reports save to {research_dir}/deep-dives/. ONLY trigger when the user explicitly asks to research, analyze, or compare a resource against their project — not just because they share a link. Trigger: "

Audit existing screenshot captures for quality issues. Checks every PNG file in a directory for wrong-company content, blank sections, cookie banners, error pages, and other problems. Reports what needs recapturing. Use when screenshots look wrong or after a batch capture to verify quality. Invoke with /site-capture:audit.

Capture full-page screenshots of one or more websites. Handles scroll-triggered animations, lazy-loaded content, cookie banners, and bot-protected sites. Uses a tiered approach: Microlink API first, Chrome browser fallback for protected sites. Use when you need design references, competitive analysis screenshots, or visual audits. Invoke with /site-capture:capture.

Fetch a spoken-word transcript from a video URL. Supports YouTube, YouTube Shorts, Instagram posts/Reels, TikTok, and Threads. Use whenever you need the words said in a video — for research, summarization, or analysis. Invoke with /transcribe:transcribe <url> or from Bash as `transcribe <url>`.

Classify a proposed code change as Leaf Node or Core Code to decide how much AI usage and review rigor is appropriate. Use this skill whenever the user asks "is this leaf or core", "what kind of change is this", "should I vibe code this", "can AI write this", "how rigorous should the review be", or before starting any non-trivial change. Also useful as a sub-step inside other workflows (planning,

Review a Pull Request or code change with rigor calibrated to whether it's leaf-node or core code. Use this skill whenever the user asks to review, audit, or evaluate code — phrases like "review this PR", "audit this code", "is this PR ready", "look at this branch", "review my changes", "what do you think of this", "code review please". Also trigger when reviewing AI-authored code specifically. Th