Consult Gemini as an independent expert with deep web research. Sends a question or task to Gemini CLI and returns a research-backed response.

Session wrap-up: commit pending changes, push, write structured state for the next session to resume from. Eliminates 'glue sessions' that exist only to commit/push, and preserves debug context across sessions.

Agent Loop for pixel-perfect UI adjustments: extract a structured spec from the user's intent, apply changes one property at a time, self-verify via screenshot, and converge instead of ping-ponging. Designed for high-fidelity UI cloning and spacing/style iteration.

TRIGGER when writing, modifying, or reviewing any Rust code that involves tracing, logging, spans, events,

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes

Perform a strict, evidence-based review of the current branch or working-tree changes without modifying files. Use when the user asks for a strict review, deep review, senior review, merge assessment, or explicitly invokes `$review-strict`.

Agent Loop for tasks that need research before implementation: check existing research first, run structured investigation (bb-browser/context7/code study), produce a Brief, then implement against the Brief. Prevents repeated research on already-studied topics and research-to-implementation drift.

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.

Push the current branch and open a GitHub pull request against `main`. Use when the user says "create PR", "open PR", "make a PR", "提 PR", "开 PR", "打 PR", or otherwise asks to publish their committed work for review. Before pushing it gates the diff on four things — branch name accuracy, stale `docs-site/` docs, missing PostHog telemetry, and tracing-spec conformance — and surfaces each as a candidate list for the user to approve.

Resume work from a $wrap state file. Reads the structured active-task.json, presents a context summary, restores branch state, and lets you pick up exactly where the last session left off — no manual context rebuild.