Refresh fact-based sections of crates/AGENTS.md (STRUCTURE, WHERE TO LOOK, COMPLEXITY HOTSPOTS, KNOWN BROKEN) from current codebase state. Use after refactoring, renaming files, adding crates, or when the agent notices AGENTS.md info is stale.

Agent Loop that runs local pre-flight CI checks, auto-fixes issues, creates/pushes the PR, monitors CI, and loops until all checks pass. Replaces the manual chain of preflight → create-pr → babysit-pr.

Run an independent adversarial review loop for a Markdown implementation plan. Use when the user asks to review, validate, stress-test, or challenge a plan before implementation, including requests for a second opinion or a plan review loop.

Record a lesson learned into crates/AGENTS.md (CONVENTIONS or ANTI-PATTERNS section). Use after discovering a project-specific gotcha, resolving a tricky bug, or when the user says 'remember this' about a coding pattern. Append one concise rule that will prevent the same mistake in future sessions.

Drive the UniClipboard iOS app in a simulator and read its OSLog yourself to diagnose a mobile-sync bug, instead of asking the user to paste logs. Use when debugging why the iOS sync engine or M5 reducer did something, reproducing an iOS sync / clipboard bug on the simulator, or whenever you'd otherwise ask the user "what do the logs say". All output is Swift OSLog under subsystem `app.uniclipboard` — the Rust core (uc-mobile) emits no logs of its own; the Swift shell logs the reducer's decisions.

Generate bilingual, user-facing release changelogs from Git history. Use when the user asks to generate a changelog, prepare release notes, or update `docs/changelog` for a release and provides a base tag or commit.

Agent Loop for build/compilation errors: run the build yourself, collect ALL errors at once, find root causes via dependency analysis, fix in order, revert failed hypotheses, loop until green. Eliminates the user-paste-error → agent-guess → still-broken ping-pong.

Analyze the current branch's diff against main and determine which changes are testable via CLI-based end-to-end tests. Outputs a concrete test plan with runnable test case sketches using the uc-e2e-tests harness. Use when the user wants to think about, plan, or evaluate e2e test coverage for their current work.

Push the macOS working-tree changes to the Windows peer's repo via rsync over SSH. Use when the user wants to "sync to win", "push my changes to windows", "mirror the working tree", or otherwise propagate uncommitted edits from this Mac to the paired Windows machine for cross-platform testing of uniclipboard. Replaces the older SMB-mount strategy.

Inspect uniclipboard logs from BOTH the macOS host and the mounted Windows peer when debugging cross-platform sync, pairing, transfer, or daemon issues. Use whenever the user asks to "check logs", "see what's happening on both sides", or describes a symptom that involves the Windows peer (e.g. "Windows didn't receive...", "Mac sent but...", pairing/transfer/sync failures during dual-side dev).

Agent Loop for cross-device sync/transfer issues: collect environment fingerprints from BOTH machines first, check memory for known patterns, manage hypotheses with forced falsification, and persist evidence via $wrap. Orchestrates dual-side-debug + local-log-debug + systematic-debugging into a structured loop.

Interactive meeting preparation — builds a relationship brief and talking points before a call. Use when the user says "prep me for my call with", "I'm meeting with X", "prepare me for", "what should I bring up with", "meeting prep", "get ready for my call", or wants to review history with someone before a meeting.

Add a note to the current recording or annotate a past meeting. Use whenever the user says "note that", "remember this", "mark this as important", "add a note about", "annotate the meeting", or wants to capture a thought during or after a recording. Plain text input — no markdown needed.

Self-coaching analysis of your own behavior across meetings — talk-time ratio, filler words, hedging language, monologue length, energy patterns, and (when meetings are tagged via /minutes-tag) what your behavior in winning meetings looks like vs losing ones. Use this whenever the user says "how did I do", "review my last meeting", "mirror", "self-review", "show my patterns", "coach me", "where am I weak", "talk time", "am I improving", "what do I do in meetings I win", "feedback on me", or asks for any kind of personal feedback on their own meeting behavior. This is the rare skill that gives the user a mirror to their own habits — surface it whenever they show curiosity about their own performance, even if they don't use the word "mirror".

Act as the user's live meeting sidekick inside the current terminal agent session. Use when the user explicitly asks you, the terminal agent, to watch a meeting, follow the live transcript, answer during the call, offer strategist thoughts, silently watch for risks, or track decisions. Do not use this skill to start or control the separate Minutes Coach HUD; explicit Coach or HUD lifecycle requests belong to minutes-copilot, and an ambiguous request such as "coach me live" requires one short surface clarification.

List recent meetings and voice memos. Use when the user asks "what meetings did I have", "show my recent recordings", "any meetings today", "list my voice memos", or wants an overview of their meeting history. Also use when they need to find a specific meeting by browsing rather than searching.

Health-check your meeting knowledge for contradictions, stale commitments, and decision conflicts. Use when the user asks "any conflicts in my meetings", "check for stale action items", "lint my meetings", "consistency check", "are there contradictions", or wants to audit their decision history.

Extract facts from meetings and update your knowledge base — person profiles, chronological log, and index. Use when the user asks "ingest my meetings", "update my knowledge base", "extract facts from meetings", "sync meetings to wiki", "backfill knowledge", or wants their PARA/Obsidian/wiki profiles updated from conversation data.

Policy-safe relationship rankings, commitments, aliases, person profiles, and topic research. Always use Minutes' bounded native CLI surfaces; never build or read a durable graph cache.

Start and control Minutes Coach, the separate real-time copilot HUD, with an explicit meeting goal. Use only for explicit Coach or HUD lifecycle requests such as "start Minutes Coach", "open the Coach HUD", "pause Minutes Coach", "resume Minutes Coach", "Minutes Coach status", or "stop Minutes Coach". Do not use for requests that explicitly ask the current terminal agent to watch or strategize; those belong to minutes-live-sidekick. An ambiguous request such as "coach me live" requires one short surface clarification and must not automatically start Coach.