compound-engineering-plugin

Run browser tests for pages affected by the current branch or PR.

Babysits or watches an open GitHub PR until merge-ready, continuously reacting to new review comments and CI failures throughout the PR's life. Use when asked to 'babysit the PR', 'watch the PR', monitor, or keep an eye on a PR over time — not a one-shot request to resolve review comments or debug one CI failure (those are separate skills). GitHub only, including GitHub Enterprise.

Commit, push, and open a PR. Use when asked to ship/open a PR, or for PR-description-only flows like writing, rewriting, or describing a PR body.

Diagnosis loop for bugs and failing behavior. Use for errors, stack traces, regressions, failed tests, issue-tracker bugs, stuck investigations after failed fixes, or asks to debug/fix a bug.

Resolve PR review feedback. Use when addressing review comments, resolving review threads, or fixing code-review feedback.

Check Compound Engineering health and repo-local config.

Run the full hands-off engineering pipeline from planning through a green PR.

Explore vague or ambitious ideas into a right-sized requirements-only unified plan. Use when the user wants to brainstorm, think through scope, decide what to build, or needs collaborative product framing before planning. Also use when the user must scope work in territory they say they do not know ("I know nothing about X but need to...") or asks for a blindspot pass — mapping the decision surface before questions begin. Not for executing already-specified work — direct implementation, debugging, or code review where no product scope is left to decide. Not for a decisive verdict on whether to adopt or switch to a specific external technology, library, or platform — brainstorming scopes what to build, not whether to commit to an outside option.

Structured code review for bugs, regressions, tests, and standards. Use before PRs or when asked for review; interactive mode can fix locally, while mode:agent reports only for pipeline callers.

Refresh docs/solutions learnings against the current codebase. Use when auditing stale, overlapping, superseded, or drifted learnings; avoid general refactor, debugging, or code review unless docs/solutions is explicit.

Document a recently solved problem or durable project vocabulary in docs/solutions/ or CONCEPTS.md. Use when capturing a learning after work.

Create structured plans for multi-step work, including software and non-software tasks. Use when asked to plan, break down implementation, plan from requirements, or deepen an existing plan; prefer ce-brainstorm for exploratory framing.

Turn a concept, a diff, an idea, or a window of your own recent work into a dense, visual explainer written for you personally — with an optional check-in (predict-then-reveal for diffs, corrected exercises) that makes the material stick. For learning, not repo docs or verdicts.

Generate and evaluate grounded ideas. Use when the user asks for ideas, improvements, surprising options, or AI-generated directions before choosing one to develop; use ce-brainstorm to refine the user's own idea.

Run metric-driven optimization loops. Use when improving measurable outcomes such as search relevance, clustering quality, build performance, prompt quality, or scored behavior through experiments.

Start the dev server, inspect the feature in browser, and iterate on polish.

Give a decisive, project-grounded verdict on an external input — judged against the current project, not in the abstract. Use to decide whether to adopt, switch to, or revisit a technology, library, pattern, platform, or architecture; to compare a candidate against what the project already uses; to judge whether an external change (a CVE, a deprecation, an ecosystem shift) actually affects this project; or for a mid-session second opinion. Always returns a project-specific verdict, so it is not for neutral explainers or generating options.

Analyze Riffrec feedback captures from bundles or standalone recordings. Always load for `riffrec-*.zip`, `session.json` + `events.json` + `recording.webm` + `voice.webm` bundles, `.mp4`/`.mov`/`.webm` videos, `.m4a`/`.mp3`/`.wav` audio, or capture/share requests.

Sweep configured feedback sources (Slack, GitHub Issues; email experimental) for new items: acknowledge at source, analyze recordings, verify fixes merged to main, and emit an /lfg-ready plan. First run sets up sources; supports mode:headless for scheduled runs.

Create a git commit with a clear, value-communication message. Use when the user asks to commit/save staged or unstaged changes with a repo-appropriate, value-communicating message.

Generate time-windowed product pulse reports from configured signals.

Review requirements, plans, or specs with role-specific lenses. Use when the user wants to improve an existing planning document.

Simplify recently changed code for clarity, reuse, quality, and efficiency while preserving behavior. Use for tidy/refactor passes; use ce-debug for bugs.

Execute a plan or concrete work prompt end-to-end. Use when implementing from docs/plans, a spec path, or a clear build request; use ce-debug for open-ended bugs.

Hands-off, diff-scoped browser QA of the active branch: maps user flows, drives a real browser, autonomously fixes small breakages with regression tests and commits, judges experience against product personas, and writes a durable dogfood report. Manual invocation only.

Set up isolated git worktrees — create a new branch for fresh work, or attach a worktree to an existing branch/PR/commit to work on it in isolation. Use when starting isolated work or isolating an existing ref; detects existing isolation first.

Publish, read, comment on, or edit markdown in Proof. Use for Proof links, sharing specs/plans/drafts, or publish handoffs from planning workflows; avoid proofread, math, evidence, or proof-of-concept meanings.

Draft launch or promotion copy for a shipped feature.

Create or update STRATEGY.md. Use when starting a product, changing direction or roadmap, or when ce-ideate, ce-brainstorm, or ce-plan need upstream product grounding.

Build and test iOS apps on simulator with XcodeBuildMCP.

An agent-only skill not intended for direct user invocation

A skill restricted to Claude Code only