compound-engineering

Plugin compound-engineering from marketplace compound-engineering-plugin in ucirello/compound-engineering-plugin. Commands read from the repo's manifest — today.

Skills (39)

• ce-skill-work

  Applies this repository's skill-authoring standard as a procedure. Use for any change to, or judgment about, a file under skills/** — a SKILL.md, a reference, a persona prompt, a bundled script's instructions: creating a skill, editing one, reviewing a skill change, or acting on review feedback (hum

• ce-babysit-pr

  Babysits an open GitHub PR until merge-ready, first judging whether an old PR still belongs. Use when asked to watch a PR over time or update an old one — not for one-shot comment resolution or one CI failure. GitHub (incl. Enterprise) only.

• ce-bakeoff

  Develop independent competing solutions to a defined brief, compare them, and synthesize a winning approach. Use when choosing well requires developing alternatives beyond their current form. Use ce-pov to judge developed material and ce-ideate to discover opportunities.

• ce-brainstorm

  Explore vague or ambitious ideas into a right-sized requirements-only unified plan. Use when the user wants to brainstorm or scope what to build. Not for executing already-specified work. Use ce-pov for a verdict on adopting a named external technology.

• ce-code-review

  Review a named diff or PR for bugs, regressions, tests, and standards. Use when asked to review code or when a shipping skill needs a review receipt. Use when asked to apply this review's findings locally. Use ce-resolve-pr-feedback for feedback already left on a PR.

• ce-commit-push-pr

  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.

• ce-commit

  Create local commits with JJ and clear, repository-appropriate messages. Use when the user asks to commit/save changes.

• ce-compound-refresh

  Old name for refreshing learnings, which now lives in `ce-compound`. Use only when a prompt or standing instruction names `ce-compound-refresh`; use `ce-compound` for every other learnings audit.

• ce-compound

  Capture a solved problem's lesson in its cheapest durable form, a test or lint rule, a coding standard, or a repo learning, or refresh existing learnings against the codebase. Use when verified work corrected a wrong belief about how something behaves, such as a failed approach, a real defect a revi

• ce-debug

  Diagnosis loop for bugs and failing behavior. Use when asked to debug or fix failing or slow behavior.

• ce-doc-review

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

• ce-dogfood

  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.

• ce-explain

  Explain how and why something has its current shape, or what happened over a window of work, grounded in evidence. Use when the user asks for an explanation. Use ce-pov for a judgment or recommendation.

• ce-handoff

  Create a session handoff for another agent, or resume, find, and read any user-selected continuity source. Use when work or conversation must continue without access to the current session history.

• ce-help

  Help and orientation for RocketClaw: place the user's work on the compounding loop and recommend the next command, without running it. Use when the user invokes ce-help to ask which skill fits, what comes next, how setup, configuration, cost, or upgrades work, or why a skill misbehaved.

• ce-ideate

  Generate and evaluate grounded ideas. Use when the user wants ideas, improvements, or surprising directions before choosing one to develop. Not for refining an idea they already have (ce-brainstorm) or judging one already on the table (ce-pov).

• ce-noslop

  Rewrite, check, or draft prose so it carries no AI writing tells, reads plainly on the first read, and keeps every source fact. Use when asked to make writing plainer or free of those tells, to check writing for them, or when drafting from supplied content. Use ce-promote for channel-specific market

• ce-optimize

  Optimize a named target with a measured loop: attribute a workload's cost, or score variants and keep winners. Use when a working system's metric should move and the winning change is not already known. Use ce-debug when the job is diagnosis; use ce-work when the change is already known.

• ce-plan

  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.

• ce-polish

  Polish a working feature through user-directed live browser feedback. Use when a functional feature needs focused UX refinement before shipping.

• ce-pov

  Judge a supplied subject against the project's evidence and constraints. Use when assessing an external-adoption question, a holistic take on a document, or a supplied approach set. Use for an oracle panel to consult other models and reconcile their opinions. Use ce-explain for understanding and ce-

• ce-product-pulse

  Generate time-windowed product pulse reports from configured signals.

• ce-promote

  Draft launch or promotion copy for a shipped feature.

• ce-proof

  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.

• ce-prototype

  Build a throwaway prototype to answer how something should work, feel, or read. Use when committing the wrong answer would be expensive to unravel and a cheap sketch cannot settle it. Not a rough visual probe during brainstorming, not for deciding what to build, not polishing a feature that already

• ce-resolve-pr-feedback

  Judge PR feedback centrally, apply valid fixes, and complete review conversations with publication verified. Use when addressing feedback already left on a PR, preparing local fixes for a caller to publish, or completing a saved feedback batch. Use ce-code-review for reviewing code before feedback e

• ce-retro

  Look back over an agent session in this repo, the current one by default or any scope the user names across harnesses, and find what in the repo's environment keeps costing agents effort or leading them into mistakes, keeping only fixes the evidence shows are worth it. Lands the approved environment

• ce-retune

  Retune a skill corpus for a new model, measurement-first: mine the run archive for a baseline, establish a noise floor, audit the corpus adversarially, then cut in measured passes until a pre-registered bar clears. Requires a benchmark harness that can A/B two builds of the corpus; refuses without o

• ce-riffrec-feedback-analysis

  Analyze recorded product feedback into evidence for bugs and requirements. Use when a Riffrec capture or other screen, voice, or notes artifact needs interpretation. Use for Riffrec setup, capture, or sharing help when no recording exists yet.

• ce-setup

  Check RocketClaw's tools and repo config and fix what it finds, scaffold a RocketClaw Pack with `pack:<id>`, or draft and refresh coding standards and review docs from pull request history. Use when setting up or diagnosing RocketClaw, or when creating or updating CODING_STANDARDS.md or REVIEW.md, i

• ce-simplify-code

  Simplify code for clarity, reuse, quality, and efficiency while preserving behavior, and prune tests and comments that carry no value. Use after implementation and before review, or to audit tests or comments in any part of a repo; use ce-debug for bugs.

• ce-strategy

  Create or update STRATEGY.md. Use when starting a product, adding a strategy doc, or changing direction or roadmap.

• ce-sweep

  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:non-interactive for scheduled runs.

• ce-test-browser

  Run browser tests for pages affected by the current branch or PR. Use when asked to run or check browser tests for the current change.

• ce-test-xcode

  Test iOS apps in a simulator with XcodeBuildMCP. Use when iOS changes need simulator evidence before handoff.

• ce-work

  Execute a plan or concrete work prompt end-to-end. Use when implementing from a plan document, a spec path, or a clear build request; use ce-debug for open-ended bugs. Use when an outer orchestrator needs implementation and local verification only, without the shipping tail.

• ce-worktree

  Set up isolated, colocated JJ workspaces for fresh work or an existing bookmark, PR, or revision, preserving harness ownership and session lifecycle.

• lfg

  Take a request all the way to done, hands-off, through the right RocketClaw skills. A code change ends as an open pull request, pushed without stopping. Use only when the user explicitly asks for autonomous end-to-end work or invokes lfg directly. Use ce-plan, ce-work, ce-debug, or ce-commit-push-pr

• wtf

  Explain the last message, or a supplied file, link, or passage, in plain language a person follows on the first read. Use when the user invokes wtf because they did not follow something. Use ce-explain to investigate how or why code works, and ce-noslop to rewrite prose.

Similar plugins