Official Compound Engineering plugin for Claude Code, Codex, Cursor, and more
EveryInc/compound-engineering-plugin
Skill Claude CodeCodex
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 (human or bot) about one.…
EveryInc/compound-engineering-plugin
Skill Claude CodeCodex
Babysits an open GitHub PR until merge-ready. Use when asked to watch a PR over time — not for one-shot comment resolution or one CI failure. GitHub (incl. Enterprise) only.
EveryInc/compound-engineering-plugin
Skill Claude CodeCodex
Explore vague or ambitious ideas into a right-sized requirements-only unified plan. Use when the user wants to brainstorm, scope what to build, or needs collaborative product framing before planning. Also use when they must scope work in territory they do not know, or ask for a blindspot pass. Not for executing…
EveryInc/compound-engineering-plugin
Skill Claude CodeCodex
Structured code review for bugs, regressions, tests, and standards. Use before PRs or when asked to review code. Use when the user asks to apply this review's findings locally. Not for resolving feedback already left on a PR; that is ce-resolve-pr-feedback.
EveryInc/compound-engineering-plugin
Skill Claude CodeCodex
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.
EveryInc/compound-engineering-plugin
Skill Claude CodeCodex
Create a git commit with a clear, value-communicating message. Use when the user asks to commit/save staged or unstaged changes with a repo-appropriate message.
EveryInc/compound-engineering-plugin
Skill Claude CodeCodex
Refresh the repo's captured learnings against the current codebase. Use when auditing stale, overlapping, superseded, or drifted learnings; avoid general refactor, debugging, or code review unless the learnings store is explicit.
EveryInc/compound-engineering-plugin
Skill Claude CodeCodex
Document a recently solved problem as a durable repo learning. Use when capturing a learning after work.
EveryInc/compound-engineering-plugin
Skill Claude CodeCodex
Diagnosis loop for bugs and failing behavior. Use when asked to debug or fix failing behavior.
EveryInc/compound-engineering-plugin
Skill Claude CodeCodex
Review requirements, plans, or specs with role-specific lenses. Use when the user wants to improve an existing planning document.
EveryInc/compound-engineering-plugin
Skill Claude CodeCodex
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.
EveryInc/compound-engineering-plugin
Skill Claude CodeCodex
Create a durable visual teaching artifact for something worth learning. Use when the user wants to be taught, wants a deep explainer, wants to understand a substantial change, or wants a work recap built for retention. Not for ordinary Q&A, operational diagnosis, or a concise trade-off that belongs in chat. For…
EveryInc/compound-engineering-plugin
Skill Claude CodeCodex
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.
EveryInc/compound-engineering-plugin
Skill Claude CodeCodex
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).
EveryInc/compound-engineering-plugin
Skill Claude CodeCodex
Run metric-driven optimization loops. Use when improving a measurable outcome through experiments.
EveryInc/compound-engineering-plugin
Skill Claude CodeCodex
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.
EveryInc/compound-engineering-plugin
Skill Claude CodeCodex
Polish a working feature through user-directed live browser feedback. Use when a functional feature needs focused UX refinement before shipping.
EveryInc/compound-engineering-plugin
Skill Claude CodeCodex
Give a decisive, project-grounded point of view: a graded verdict on an external-adoption question, a holistic take on a document, or a position on a supplied approach set. Use for a solo POV. Use when asked to consult other models, reconcile their opinions, or oracle. Not for findings review (use ce-doc-review)…
EveryInc/compound-engineering-plugin
Skill Claude CodeCodex
Generate time-windowed product pulse reports from configured signals.
EveryInc/compound-engineering-plugin
Skill Claude CodeCodex
Draft launch or promotion copy for a shipped feature.
EveryInc/compound-engineering-plugin
Skill Claude CodeCodex
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.
EveryInc/compound-engineering-plugin
Skill Claude CodeCodex
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 works, not…
EveryInc/compound-engineering-plugin
Skill Claude CodeCodex
Resolve PR review feedback. Use when addressing feedback already left on a PR. Not for reviewing the code before feedback exists; that is ce-code-review.
EveryInc/compound-engineering-plugin
Skill Claude CodeCodex
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 one.