ce-doc-review
Skill26k starsChanged 3 months agoMITView on GitHub
Review requirements, plans, or specs with role-specific lenses. Use when the user wants to improve an existing planning document.
We split this skill into the rules it gives an agent
2 rules. 1 is common, 1 is distinctive, and 0 are very specific to this project.
1
Common
Most of the 3 edited versions we read keep these.
1
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Common: line 39
Verify before any dispatch: Every resolved path must be readable on disk.
- Distinctive: line 71
Read or pass only the persona prompts the current review selected, each to its own reviewer.
“Common” is measured: kept by at least 6 in 10 of the 3 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Document Review
Help the author finish a sound document they can use to carry out the agreed work. Find problems that would change that work's outcome or materially hinder execution, and resolve them within the authority already given. Judge the document by whether it guides correct work, not by how much detail it contains. Serious consequences warrant attention even when the defect is small. An adequate document needs no changes.
Reviewer personas supply evidence; the judgment is yours. Check their claims against the whole document, project facts, and settled decisions. Correct proven errors that prevent an existing decision from being carried out, within the edit authority and reviewer requirements the synthesis reference states. Return only worthwhile improvements still needing permission, consequential choices or essential information only the user can supply, and useful observations.
Done when: every selected reviewer has returned or is named as failed in Coverage, retained findings have a verified consequence for the agreed work, and every authorized correction assigned to Apply has been made and checked. Report that final state through the interactive approval or decision process, or return it as structured text in non-interactive mode.
Interactive mode rules
Read references/modes.md before anything else. It defines how the mode is detected, the non-interactive argument contract, and the question-tool rules: match the host's blocking question tool already in the current tool list (never call a user-facing question tool to discover it), pre-load it at the top of the interactive flow if it is listed but unloaded, and fall back to a numbered list only when the harness genuinely lacks one.
Either way, a question that calls for a user decision calls the tool or falls back loudly. Narrating it as plain text is a bug.
Artifact Root
Resolve <root> only in the no-path interactive branch, which discovers the most recent plan under <root>/plans/. Every other run reads the document at the path it was handed. So an absolute-path or non-interactive review — /tmp/plan.md, possibly outside any repo — never depends on a repo root or a CE config it does not need.
<!-- ce-docs-root:start -->Resolve the CE artifact root <root> before composing any artifact path.
- Read
docs_rootfrom<repo-root>/.compound-engineering/config.yamlonly (<repo-root>=git rev-parse --show-toplevel). Do not read it fromconfig.local.yaml. Unset -><root>isdocs, exactly as before. - Validate a set value: a repo-relative directory whose real, symlink-resolved path stays inside the repo and is neither the repo root nor under
.git/. Otherwise stop with an error namingdocs_rootand the value -- never fall back todocs. - Use
<root>as the sole artifact location: create it if absent, compose each path as<root>/<subdir>with this skill's own subdirectory, and never also readdocs.
<!-- ce-docs-root:end -->Phase 1: Get and Analyze Document
Read references/document-intake.md now. It covers how the document is obtained in each mode, what to do and say when no document is found, and the classification signals.
Two of its rules apply to every later step.
Verify before any dispatch. Every resolved path must be readable on disk. If one is not, dispatch no personas: reviewers read from the filesystem, so they cannot reach a path that exists only on an unchecked-out branch (issue #925).
Classify by content, not readiness labels or file path. A unified artifact with only a Product Contract is unified-requirements; missing implementation sections are expected. Any implementation planning makes it unified-plan, including incomplete or blocked planning that needs review. Other artifacts use the legacy requirements / plan split.
HTML unified artifacts take the same routes. Every fix lands in the document's native format; never insert markdown into HTML. That reference covers ID-bearing items. Pass the classification to each persona in the {document_type} slot.
Phase 2: Announce and Dispatch Personas
Skip dispatch only when the completed-review reuse condition in references/document-intake.md passes; continue with that evidence at Phase 3.
Read references/persona-selection.md for each conditional persona's activation signals and the announcement format. Two of those signals over-activate on plausible evidence: the sensitive-data bound on security-lens-reviewer, and the challenge-surface bar on adversarial-document-reviewer. Then read references/dispatch.md for payload variables, slicing, model tiering, and reviewer-failure handling.
The team is coherence-reviewer and feasibility-reviewer always, plus each activated conditional persona. Announce the team briefly before any dispatch, and stay quiet while reviewers run.
Dispatch generic subagents with bounded parallelism through the platform's subagent primitive. Give each one its references/personas/<reviewer-name>.md as references/dispatch.md describes. Never dispatch a standalone agent by type or name.
A capacity rejection is backpressure, not reviewer failure: wait and retry. If capacity cannot recover and selected reviewers remain undispatched, collect and clean up any started cross-model jobs as references/cross-model-review.md describes, then stop as incomplete without synthesis, fixes, or a success handoff. Preserve collected outcomes and report which reviewers completed, failed, or could not run, and why.
Cross-Model Judgment Pass
Run this pass if any of the conditional judgment trio was activated: adversarial-document-reviewer, product-lens-reviewer, security-lens-reviewer. Follow references/cross-model-review.md, which defines the whole pass: confirming the host, the one target and route used for the whole document, the disclosure before anything leaves the machine, and how peers are launched, collected, and folded in.
The pass is additive and non-blocking: a failure or timeout stops nothing and is named in Coverage. The checkout's cross_model_review_mode setting is checked first and can skip the pass with a named reason. Filter recipients only when CROSS_MODEL_PEERS is set — unset means unfiltered, not unsanctioned. Never silently change an explicit model or recipient.
Phases 3-5: Synthesis, Presentation, and Next Action
Wait until every dispatched agent has returned, including any cross-model <reviewer-name>-<provider>.json returns. Then read references/synthesis-and-presentation.md. It defines synthesis, how each finding is routed by confidence and fix class, fix application, the non-interactive result format, and the handoff to the routing question. When promoting agreement, only an artifact with independence_verified: true counts as an independent reviewer.
Interactive mode only. Read references/walkthrough.md for the routing question, the per-finding walk-through, and the completion report. Read references/bulk-preview.md for the preview behind the walk-through's auto-resolve. Load neither before review evidence is complete, whether newly collected or validly reused, and a non-interactive run never loads them at all — it stops at the structured review result.
Read or pass only the persona prompts the current review selected, each to its own reviewer. The template and schema the dispatch payload fills:
@./references/subagent-template.md
@./references/findings-schema.json
Trending
Quiet since July.thin dataabout the whole repository
Who's talking about EveryInc/every-marketplace
- AI LABS“How to 10X Your Claude Code Workflow”YouTube · Oct 12, 2025 · 28k views
- A Hacker News story“Compounding Engineering for Claude Code”Hacker News · Oct 11, 2025 · 2 points
- EveryInc/compound-engineering-plugin“Request to merge PR #11 - Comprehensive standardization”GitHub · Nov 11, 2025 · 1 reactions
- aj-ebels/rapid-scribe“Add Every compound-engineering plugin marketplace to project settings”GitHub · Jul 7, 2026
- EveryInc/compound-engineering-plugin“Installing via README vs guide”GitHub · Feb 25, 2026
The biggest 5 of 12 mentions linking to the repository that our crawl found. Each line is their own headline.
See all 12
Talked about on GitHub, YouTube and Hacker News (12 times).
On GitHub · 10
- Nov 11, 2025Request to merge PR #11 - Comprehensive standardization — EveryInc/compound-engineering-plugin1 reaction · 1 comment
- Jul 7, 2026Add Every compound-engineering plugin marketplace to project settings — aj-ebels/rapid-scribe0 reactions
- Feb 25, 2026Installing via README vs guide — EveryInc/compound-engineering-plugin0 reactions · 3 comments
- Nov 30, 2025Compound engineering Command not installed with Droid — EveryInc/compound-engineering-plugin0 reactions · 8 comments
- Nov 25, 2025feat: Add plan mode support to /issue, /architect, and /product-manager commands — psd401/psd-claude-plugins0 reactions · 1 comment
5 more on GitHub
- Nov 18, 2025Install compounding-engineering plugin from Every marketplace — ThePharmer/stepmania0 reactions
- Nov 13, 2025Enhance issue with planner — minyk/lazy-bird0 reactions
- Nov 6, 2025feat: install Compounding Engineering plugin from Every marketplace — nerdymil30/gmail_classifier_speckit0 reactions
- Oct 15, 2025Add one-command installation option via Claude Plugins CLI — EveryInc/compound-engineering-plugin0 reactions · 1 comment
- Oct 10, 2025Claude v 2.013 - Failed to closne repository.. — EveryInc/compound-engineering-plugin0 reactions · 1 comment
On YouTube · 1
- Oct 12, 2025How to 10X Your Claude Code Workflow — AI LABS28k views · 197 comments
On Hacker News · 1
- Oct 11, 2025Compounding Engineering for Claude Code2 points
Other versions5 projects use a version of this.
Word for word · 2
- EveryInc/compounding-engineering-plugin★ 26k100% same
- EveryInc/compound-engineering-plugin★ 26k100% same
Edited · 2
- kieranklaassen/compound-engineering-plugin★ 26k94% same
- MortuisVMain/ai-agent-superpowers★ 067% same
Wrote their own version · 1
- Pdbjork/hermosskills-site★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository37 other files it gives its agents.
- AGENTS.mdAGENTS.md
- ce-skill-workSkill
- ce-babysit-prSkill
- ce-bakeoffSkill
- ce-brainstormSkill
- ce-code-reviewSkill
- ce-commit-push-prSkill
- ce-commitSkill
- ce-compound-refreshSkill
- ce-compoundSkill
- ce-debugSkill
- ce-dogfoodSkill
- ce-explainSkill
- ce-handoffSkill
- ce-ideateSkill
- ce-noslopSkill
- ce-optimizeSkill
- ce-planSkill
- ce-polishSkill
- ce-povSkill
- ce-product-pulseSkill
- ce-promoteSkill
- ce-proofSkill
- ce-prototypeSkill
- ce-resolve-pr-feedbackSkill
- ce-retuneSkill
- ce-riffrec-feedback-analysisSkill
- ce-setupSkill
- ce-simplify-codeSkill
- ce-strategySkill
- ce-sweepSkill
- ce-test-browserSkill
- ce-test-xcodeSkill
- ce-workSkill
- ce-worktreeSkill
- lfgSkill
- wtfSkill
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

