mirror of
https://github.com/EveryInc/compound-engineering-plugin.git
synced 2026-09-19 01:09:55 +08:00
Trevin Chow
483bca0f87
All four are "which number wins when two rules apply": A raw total below the frame floor was unsatisfiable. "3 ideas about auth" divided three ideas across six required frames, so the run had to either overshoot the ask or leave frames unrun. Any total at or below roughly one per frame now reads the way `top 3` does -- generate normally, cut to that many survivors -- on both paths. An explicit survivor count lost to the depth default. The universal convergence target was unconditional, so `top 3 names for a coffee shop` could return five at Standard depth even though line 81 makes `top 3` the survivor limit. An explicit count now wins outright, with the depth-keyed target as the fallback. The issue-tracker fallback said "the default fleet" -- the ordinary five -- directly above a sentence forbidding that figure. It now falls back to the six-frame default at this run's own count, which is 6 under go deep or surprise-me. The docs page claimed all software/product tactical runs keep five agents, but an issue-tracker run with usable themes dispatches four. Exception added. Claude-Session: https://claude.ai/code/session_01LFdS46yevebfqNrcrJMiVq
Skill Documentation
End-user-facing documentation for compound-engineering plugin skills. Each page covers the skill's high-level purpose, novel mechanics, use cases, and chain position relative to other skills.
For runtime behavior and contributor reference, the SKILL.md in each skill's source folder under skills/ is authoritative.
Checkout-local defaults shared across skills are documented in Compound Engineering configuration.
Artifact paths shown throughout these pages (docs/plans/, docs/solutions/, docs/ideation/, and the rest) are the defaults. A project can relocate every CE artifact folder under one repo-relative root with docs_root; when it is set, read the shown paths as <your-docs_root>/plans/, <your-docs_root>/solutions/, and so on. See Artifact root.
The compound-engineering core loop
[/ce-ideate] (optional) "What's worth exploring?"
│
▼
┌─→ /ce-brainstorm "What does this need to be?"
│ │
│ ▼
│ /ce-plan "What's needed to accomplish this?"
│ │
│ ▼
│ /ce-work "Build it."
│ │
│ ▼
└── /ce-compound "Capture what we learned."
/ce-compound is the closer that makes the loop compound: it writes learnings into docs/solutions/, which the next iteration's /ce-brainstorm and /ce-plan read as grounding — that return arrow is the whole point. /ce-ideate is an optional prelude for when you don't yet know what to work on. Everything else in this catalog is either an anchor around the loop or an on-demand tool used when a specific need arises — not a step you walk through every time.
The Core Loop
The steps of every engineering iteration. /ce-ideate runs only when you need to find a direction first; the other four run in order per piece of work.
| Skill | Description |
|---|---|
/ce-ideate |
Optional first step — discover strong, qualified directions worth exploring with six conceptual frames, warrant requirement, adversarial filtering |
/ce-brainstorm |
Define what something should become — collaborative dialogue, named gap lenses, requirements-only unified plan |
/ce-plan |
Bound execution with guardrails — enrich unified plans with U-IDs, test scenarios, automatic confidence check; WHAT decisions, not HOW code |
/ce-work |
Execute against implementation-ready plan guardrails — figure out the HOW with code in front of you, ship through quality gates |
/ce-compound |
Close the loop by capturing what you learned into docs/solutions/ so the next iteration starts smarter — bug track + knowledge track |
Around the Loop
Skills that anchor, feed, or maintain the loop without being steps inside it.
| Skill | Description |
|---|---|
/ce-strategy |
Create or maintain STRATEGY.md — the upstream anchor read by ce-ideate, ce-brainstorm, and ce-plan as grounding |
/ce-product-pulse |
Outer feedback loop — single-page time-windowed report on usage, performance, errors, followups; saved to docs/pulse-reports/ as a timeline |
/ce-sweep |
Recurring feedback sweep — ingest Slack/GitHub items (email experimental) since per-source cursors, acknowledge at source, analyze recordings, verify fixes merged, and reconcile an /lfg-ready rolling plan |
/ce-compound-refresh |
Maintain docs/solutions/ over time — five outcomes (Keep / Update / Consolidate / Replace / Delete), Interactive + Autofix modes |
On-Demand
Invoked when a specific need arises — not part of any chain.
| Skill | Description |
|---|---|
/ce-pov |
Form a decisive, project-grounded POV as an adoption verdict, holistic document take, or position on supplied approaches — optional named/oracle panel with a blind initial round, bounded evidence-based reconciliation, and a user-extensible checkpoint |
/ce-explain |
Turn a concept, a diff, an idea, or a window of your own recent work into a dense, self-contained visual document built to keep — evidence-grounded recaps, capability-detected destination ask, optional opt-in check-in (predict-then-reveal for diffs, corrected exercises) |
/ce-debug |
Find root causes systematically — causal chain gate, predictions, post-fix polish/review, PR handoff |
/ce-code-review |
Structured code review with skill-local reviewer personas, confidence-gated findings, four modes |
/ce-doc-review |
Review requirements or plan documents using skill-local reviewer personas — coherence, feasibility, product-lens, design-lens, security-lens, scope-guardian, adversarial |
/ce-simplify-code |
Refine recently changed code — reuse, quality, and efficiency review; behavior preservation verified |
/ce-optimize |
Metric-driven iterative optimization loops — three-tier evaluation, parallel experiments, persistence discipline |
/ce-retune |
Retune a skill corpus for a new model, measurement-first — archive baseline, noise floor, adversarial audit, measured cut passes |
Research & Context
| Skill | Description |
|---|---|
/ce-riffrec-feedback-analysis |
Turn raw Riffrec recordings into structured feedback — quick bug or extensive analysis with ce-brainstorm handoff |
Git Workflow
| Skill | Description |
|---|---|
/ce-commit |
Create a single, well-crafted git commit — convention-aware, sensitive-file-safe, file-level logical splitting |
/ce-commit-push-pr |
Go from working changes to an open PR with adaptive descriptions, related-reference handling, three modes (full workflow / description update / description-only generation), opt-in retrospective PR-stack construction/submit, and a concept-teaching section for anything the change newly introduces |
/ce-babysit-pr |
Watch an open PR and keep it moving toward merge — react to incoming review comments (via /ce-resolve-pr-feedback) and CI failures (via /ce-debug) as each arrives, comments-first, with postures for confirmed managed stacks (target / stack-ready / stack-land), a crash-safe resumable tick, continuous or checkpoint mode per harness, and a settle window that avoids premature "ready to merge" |
/ce-worktree |
Ensure work happens in an isolated git worktree — detect existing isolation, prefer the harness's native worktree tool, fall back to plain git |
Autonomous Pipeline
| Skill | Description |
|---|---|
/lfg |
Run the full hands-off engineering pipeline through a green PR, then conditionally recommend an opt-in fresh-session handoff for the next separately planned area |
Frontend Design
| Skill | Description |
|---|---|
/ce-polish |
Conversational UX polish — start dev server, open browser, iterate together; auto-detects 8 frameworks (manual invocation only) |
Collaboration
| Skill | Description |
|---|---|
/ce-proof |
Publish, view, comment on, and edit markdown via Proof, Every's collaborative editor — hosted v3 web API with owner credential lifecycle |
Workflow Utilities
| Skill | Description |
|---|---|
/ce-promote |
Draft user-facing announcement copy for a shipped feature (X, changelog, LinkedIn, email) — voice-matched via the optional Spiral CLI, a lite layer of editorial & social expertise without it, drafts only |
/ce-resolve-pr-feedback |
Evaluate, fix, and reply to PR review feedback in parallel — including nitpicks |
/ce-dogfood |
Hands-off diff-scoped browser QA of the active branch — maps flows, autonomously fixes small breakages with regression tests and commits, writes a durable report (manual invocation only) |
/ce-test-browser |
End-to-end browser tests using a host-native browser with agent-browser fallback |
/ce-test-xcode |
Build and test iOS apps on simulator using XcodeBuildMCP — screenshots, logs, human verification |
/ce-setup |
Diagnose optional tool capabilities and bootstrap safe project-local config |
/ce-handoff |
Create a session handoff at the default temp store or a requested destination, then discover or orient from a selected source — no automatic continuation |
See also
For the top-level install and usage guide, see README.md. Each skill's authoritative runtime spec is in skills/<skill>/SKILL.md.