Explore skills

Run the graph-retriever subagent — intelligent, iterative retrieval over the derived graph query layer. The maintainer asks a free-form information-need question ("where is X", "what depends on Y", "which findings concern Z"); the agent constructs a strong query, runs a bounded retrieve→read→judge→refine loop (≤10 iterations) with adaptive traversal, and returns a cited answer set. Emits substrate

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.

Run the test-coverage-mapper reducer subagent over the per-node enrichment sidecars + actual test files in the target repo. Verifies sidecar-claimed test files exist; surfaces uncovered behaviours as TEST-GAP-NNN candidates ranked by node criticality (anchored on concepts.yaml's security/performance aggregates); cross-references with `doc-gaps.md` for double-jeopardy findings (undocumented AND unt

Convert raw scanner findings into atomic work items in the backlog. Assigns priority, category, effort, and identifies file conflicts.

Force-resync the iTerm2 tab color for a Claude Code session whose hook chain has fallen out of sync. Use when a tab's color is visibly stuck on a stale state (e.g., still orange after the user replied, still white after Claude started processing) — that means Claude Code's automatic PreToolUse/PostToolUse/UserPromptSubmit/etc. events aren't reaching the hook. This skill bypasses the automatic path

Print a health snapshot for the headsup hook stack — daemon PID + heartbeat status, launchd watchdog state, active sessions and their current colors, count of stray PostToolUse events suppressed today, and token usage for the current Claude Code session ($PWD). Use when the user asks "is this still working", "how's the headsup tab thing", "show me the headsup hook status", or invokes /headsup-stat

Pull the latest headsup release from GitHub and apply it in-place. Use when the user types /headsup-update, asks to "update headsup", or wants to pull the newest version of the tab-color/status hooks.

実装されたコードを仕様整合・設計適合・可読性の観点でレビューする。PR / 変更差分のレビュー、コミット前のセルフレビューに使う。対象が PR なら確認ゲート経由で PR にレビューを投稿する。重要変更は Codex クロスチェックを推奨する。

Weekly strategic intelligence. Dispatches 5 analyst agents (Market Scout, Competitor Tracker, Audience Analyst, Growth Analyst, Product Scout), reads the last 7 daily reports, and produces a strategy brief + recommendations for PM ingestion. Reads pulse-config.yaml from the nearest research directory. Run Monday mornings or whenever you need strategic direction. Trigger: "run weekly strategy", "we

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.