Multi-persona document review that runs specialized reviewer agents in parallel to catch issues in requirements and planning docs. The interesting part is the two-tier classification: some problems get auto-fixed silently, others surface as strategic questions for you to decide. Headless mode flips it into a pure data pipeline that returns structured findings instead of asking for approval. Built by the Every team as part of their compound engineering plugin, which makes sense given their focus on knowledge work tooling. Most useful when you need more than a spell check but don't want to manually coordinate feedback from security, UX, and technical reviewers yourself.

skills.sh installs
562
GitHub stars
26K
last updated
Aug 21, 2026

Install

$ npx -y skills add everyinc/compound-engineering-plugin --skill document-review --agent claude-code

Installs into .claude/skills of the current project.

Files

Multi-persona document review that runs specialized reviewer agents in parallel to catch issues in requirements and planning docs. The interesting part is the two-tier classification: some problems get auto-fixed silently, others surface as strategic questions for you to decide. Headless mode flips it into a pure data pipeline that returns structured findings instead of asking for approval. Built by the Every team as part of their compound engineering plugin, which makes sense given their focus on knowledge work tooling. Most useful when you need more than a spell check but don't want to manually coordinate feedback from security, UX, and technical reviewers yourself.

Browse the repository on GitHub

Sponsors

Details

Repository
github.com/everyinc/compound-engineering-plugin
Categories
Git & Pull Requests, Code Review & Quality, Productivity & Planning, Automation & Workflows
First seen
Apr 16, 2026

More from everyinc/compound-engineering-plugin

All 78
1secondsky avatarcode-reviewsecondsky/claude-skillsCode review practices with technical rigor and verification gates. Use for receiving feedback, requesting code-reviewer subagent reviews, or preventing false co548skills.sh installs
2sickn33 avatarcode-review-excellencesickn33/antigravity-awesome-skillscode review excellence543skills.sh installs
3sickn33 avatarusing-git-worktreessickn33/antigravity-awesome-skillsusing git worktrees535skills.sh installs
4rshankras avatarrelease-reviewrshankras/claude-code-apple-skillsSenior developer-level release review for macOS/iOS apps. Identifies security, privacy, UX, and distribution issues with actionable fixes. Use when preparing an529skills.sh installs
5wanshuiyin avatarauto-review-loop-llmwanshuiyin/auto-claude-code-research-in-sleepAutonomous research review loop using any OpenAI-compatible LLM API. Configure via llm-chat MCP server or environment variables. Trigger with "auto review loop 525skills.sh installs
6evoscientist avatarpaper-reviewevoscientist/evoskillsGuides self-review of YOUR OWN academic paper before submission with adversarial stress-testing. Core method: 5-aspect checklist (contribution sufficiency, writ521skills.sh installs