Explore skills

Process status/needs-triage items through the full pipeline: sort (reject/dedup), spec (brainstorming + writing-plans for M/L/XL items), score against the agent-ready checklist, and promote to status/ready (with owner/ai or owner/human) or reject to out-of-scope. Interactive — you confirm every decision. Trigger: "triage", "process backlog", "review incoming items", "spec items", or /pm:triage.

Find where a feature, component, or concept lives in the ODD codebase. Uses the navigation index for O(1) lookups.

Run the feature-reflector subagent (Layer 4b — top-down product-owner reflection) over one composed feature flow. Produces `lineage/{repo}/feature-reflections/detail/{F-NNN}.yaml` with a stepped-back product-owner narrative + 5-15 falsifiable user-facing hypotheses + per-hypothesis verdicts (confirmed / contradicted / partial / probe-needed) traced through the implementation chain. Contradictions

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

检测 Claude Code 技能目录的变更，自动更新 README 并推送到 GitHub。仅通过 /push-skills 主动调用。

Customize the three global tab colors for Claude Code's iTerm2 status hook — idle (fresh session), processing (Claude working), and waiting (Claude needs you). Invoke when the user wants to change any of those three colors ("change waiting color to orange", "idle should be gray", "swap blue for purple while processing"). Edits ~/.claude/hooks/headsup-status.conf, applies the matching color to the

Set or change the per-iTerm2-session label — both the window/tab title AND the badge (watermark) for THIS iTerm2 pane only. Use when the user wants a custom name for this specific tab ("call this tab 'deploy debugging'", "label this session 'prod work'", "set the badge to 'frontend'"). Title and badge always share the same string in this skill (the banner and watermark always match). Edits ~/.clau

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.

Daily research automation. Scans configured domains for actionable intelligence, filters through the weekly strategy brief for relevance, and produces a dated research report with action items for PM ingestion. Opens an auto-mergeable PR. Reads pulse-config.yaml from the nearest research directory. Trigger: "run daily research", "research scan", "what's new", "check for updates", or /product-pulse

Autonomous batch driver for the rev-2 agentic-ontology sprint. Picks the next pending theme from state/sprint-themes.yaml, spawns 5 file-analyser subagents in parallel, then 5 reducers in parallel, merges deltas, refreshes coverage, appends the investigator-log entry, commits, pushes to remote, marks the theme done. Designed to be fired by `/loop` overnight without maintainer input.

Quick orientation for a new session — shows system overview, current state, and available actions.

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