{"id":"de2ff7fb-10b1-48c4-bae9-964d4ff1fe73","shortId":"QHHhTM","kind":"skill","title":"Run multi-agent code review rounds with structured reviewer discourse before human approval","tagline":"Use Open Code Review when an agent needs several reviewer personas to inspect a diff, debate findings, and synthesize review output before a human approves, posts, or acts on the review.","description":"# Run multi-agent code review rounds with structured reviewer discourse before human approval\n\nUse Open Code Review when an agent needs several reviewer personas to inspect a diff, debate findings, and synthesize review output before a human approves, posts, or acts on the review.\n\n## Prerequisites\n\nNode.js 20+, Git, and a supported AI coding assistant such as Claude Code, Cursor, Windsurf, or another OCR-supported tool. GitHub CLI auth is also needed if you want to post reviews back to pull requests.\n\n## Installation\n\nRequirements and caveats from upstream:\n- **Prerequisites**: GitHub CLI (gh) installed and authenticated, open PR on current branch.\n\nBasic usage or getting-started notes:\n- The dashboard is the recommended way to run reviews, browse results, and manage your workflow. Launch it with ocr dashboard.\n- ### Run reviews and maps\n- <img src=\"assets/ocr-tool-example-translated-human-review.png\" alt=\"Human-voice review posted to GitHub PR\" width=\"700\" />\n\n- Source: https://github.com/spencermarx/open-code-review\n- Extracted from upstream docs: https://raw.githubusercontent.com/spencermarx/open-code-review/HEAD/README.md\n\n## Documentation\n\n- https://github.com/spencermarx/open-code-review#readme\n\n## Source\n\n- [Agent Skill Exchange](https://agentskillexchange.com/skills/run-multi-agent-code-review-rounds-with-structured-reviewer-discourse-before-human-approval/)","tags":["run","multi","agent","code","review","rounds","with","structured","reviewer","discourse","before","human"],"capabilities":["skill","source-agentskillexchange","skill-run-multi-agent-code-review-rounds-with-structured-reviewer-discourse-before-human-approval","topic-agent-skills","topic-ai-agents","topic-ai-tools","topic-awesome-list","topic-claude-code","topic-codex","topic-cursor","topic-llm","topic-mcp","topic-npx-skills","topic-openclaw","topic-skills-catalog"],"categories":["skills"],"synonyms":[],"warnings":[],"endpointUrl":"https://skills.sh/agentskillexchange/skills/run-multi-agent-code-review-rounds-with-structured-reviewer-discourse-before-human-approval","protocol":"skill","transport":"skills-sh","auth":{"type":"none","details":{"cli":"npx skills add agentskillexchange/skills","source_repo":"https://github.com/agentskillexchange/skills","install_from":"skills.sh"}},"qualityScore":"0.454","qualityRationale":"deterministic score 0.45 from registry signals: · indexed on github topic:agent-skills · 8 github stars · SKILL.md body (1,389 chars)","verified":false,"liveness":"unknown","lastLivenessCheck":null,"agentReviews":{"count":0,"score_avg":null,"cost_usd_avg":null,"success_rate":null,"latency_p50_ms":null,"narrative_summary":null,"summary_updated_at":null},"enrichmentModel":"deterministic:skill-github:v1","enrichmentVersion":1,"enrichedAt":"2026-05-18T19:12:12.788Z","embedding":null,"createdAt":"2026-05-18T13:19:00.623Z","updatedAt":"2026-05-18T19:12:12.788Z","lastSeenAt":"2026-05-18T19:12:12.788Z","tsv":"'/skills/run-multi-agent-code-review-rounds-with-structured-reviewer-discourse-before-human-approval/)':199 '/spencermarx/open-code-review':181 '/spencermarx/open-code-review#readme':192 '/spencermarx/open-code-review/head/readme.md':188 '20':93 'act':42,87 'agent':4,21,49,66,194 'agentskillexchange.com':198 'agentskillexchange.com/skills/run-multi-agent-code-review-rounds-with-structured-reviewer-discourse-before-human-approval/)':197 'ai':98 'also':117 'anoth':108 'approv':14,39,59,84 'assist':100 'auth':115 'authent':141 'back':125 'basic':147 'branch':146 'brows':163 'caveat':132 'claud':103 'cli':114,137 'code':5,17,50,62,99,104 'current':145 'cursor':105 'dashboard':155,173 'debat':30,75 'diff':29,74 'discours':11,56 'doc':185 'document':189 'exchang':196 'extract':182 'find':31,76 'get':151 'getting-start':150 'gh':138 'git':94 'github':113,136 'github.com':180,191 'github.com/spencermarx/open-code-review':179 'github.com/spencermarx/open-code-review#readme':190 'human':13,38,58,83 'inspect':27,72 'instal':129,139 'launch':169 'manag':166 'map':177 'multi':3,48 'multi-ag':2,47 'need':22,67,118 'node.js':92 'note':153 'ocr':110,172 'ocr-support':109 'open':16,61,142 'output':35,80 'persona':25,70 'post':40,85,123 'pr':143 'prerequisit':91,135 'pull':127 'raw.githubusercontent.com':187 'raw.githubusercontent.com/spencermarx/open-code-review/head/readme.md':186 'recommend':158 'request':128 'requir':130 'result':164 'review':6,10,18,24,34,45,51,55,63,69,79,90,124,162,175 'round':7,52 'run':1,46,161,174 'sever':23,68 'skill':195 'skill-run-multi-agent-code-review-rounds-with-structured-reviewer-discourse-before-human-approval' 'sourc':178,193 'source-agentskillexchange' 'start':152 'structur':9,54 'support':97,111 'synthes':33,78 'tool':112 'topic-agent-skills' 'topic-ai-agents' 'topic-ai-tools' 'topic-awesome-list' 'topic-claude-code' 'topic-codex' 'topic-cursor' 'topic-llm' 'topic-mcp' 'topic-npx-skills' 'topic-openclaw' 'topic-skills-catalog' 'upstream':134,184 'usag':148 'use':15,60 'want':121 'way':159 'windsurf':106 'workflow':168","prices":[{"id":"de915448-c604-4706-81db-9cc1664567df","listingId":"de2ff7fb-10b1-48c4-bae9-964d4ff1fe73","amountUsd":"0","unit":"free","nativeCurrency":null,"nativeAmount":null,"chain":null,"payTo":null,"paymentMethod":"skill-free","isPrimary":true,"details":{"org":"agentskillexchange","category":"skills","install_from":"skills.sh"},"createdAt":"2026-05-18T13:19:00.623Z"}],"sources":[{"listingId":"de2ff7fb-10b1-48c4-bae9-964d4ff1fe73","source":"github","sourceId":"agentskillexchange/skills/run-multi-agent-code-review-rounds-with-structured-reviewer-discourse-before-human-approval","sourceUrl":"https://github.com/agentskillexchange/skills/tree/main/skills/run-multi-agent-code-review-rounds-with-structured-reviewer-discourse-before-human-approval","isPrimary":false,"firstSeenAt":"2026-05-18T13:19:00.623Z","lastSeenAt":"2026-05-18T19:12:12.788Z"}],"details":{"listingId":"de2ff7fb-10b1-48c4-bae9-964d4ff1fe73","quickStartSnippet":null,"exampleRequest":null,"exampleResponse":null,"schema":null,"openapiUrl":null,"agentsTxtUrl":null,"citations":[],"useCases":[],"bestFor":[],"notFor":[],"kindDetails":{"org":"agentskillexchange","slug":"run-multi-agent-code-review-rounds-with-structured-reviewer-discourse-before-human-approval","github":{"repo":"agentskillexchange/skills","stars":8,"topics":["agent-skills","ai-agents","ai-tools","awesome-list","claude-code","codex","cursor","llm","mcp","npx-skills","openclaw","skills-catalog"],"license":"mit","html_url":"https://github.com/agentskillexchange/skills","pushed_at":"2026-05-18T19:02:17Z","description":"The open catalog of AI agent skills — 2,000+ security-scanned skills for Claude Code, Cursor, Codex, and more.","skill_md_sha":"29373cd5ffacaaa38a3343f36e063a515dd6a7a5","skill_md_path":"skills/run-multi-agent-code-review-rounds-with-structured-reviewer-discourse-before-human-approval/SKILL.md","default_branch":"main","skill_tree_url":"https://github.com/agentskillexchange/skills/tree/main/skills/run-multi-agent-code-review-rounds-with-structured-reviewer-discourse-before-human-approval"},"layout":"multi","source":"github","category":"skills","frontmatter":{"name":"Run multi-agent code review rounds with structured reviewer discourse before human approval","description":"Use Open Code Review when an agent needs several reviewer personas to inspect a diff, debate findings, and synthesize review output before a human approves, posts, or acts on the review."},"skills_sh_url":"https://skills.sh/agentskillexchange/skills/run-multi-agent-code-review-rounds-with-structured-reviewer-discourse-before-human-approval"},"updatedAt":"2026-05-18T19:12:12.788Z"}}