{"id":"794abb4e-0614-42c2-9424-84732f4a0f83","shortId":"qZY3tX","kind":"skill","title":"multi-agent-brainstorming","tagline":"Simulate a structured peer-review process using multiple specialized agents to validate designs, surface hidden assumptions, and identify failure modes before implementation.","description":"# Multi-Agent Brainstorming (Structured Design Review)\n\n## Purpose\n\nTransform a single-agent design into a **robust, review-validated design**\nby simulating a formal peer-review process using multiple constrained agents.\n\nThis skill exists to:\n- surface hidden assumptions\n- identify failure modes early\n- validate non-functional constraints\n- stress-test designs before implementation\n- prevent idea swarm chaos\n\nThis is **not parallel brainstorming**.\nIt is **sequential design review with enforced roles**.\n\n---\n\n## Operating Model\n\n- One agent designs.\n- Other agents review.\n- No agent may exceed its mandate.\n- Creativity is centralized; critique is distributed.\n- Decisions are explicit and logged.\n\nThe process is **gated** and **terminates by design**.\n\n---\n\n## Agent Roles (Non-Negotiable)\n\nEach agent operates under a **hard scope limit**.\n\n### 1️⃣ Primary Designer (Lead Agent)\n\n**Role:**\n- Owns the design\n- Runs the standard `brainstorming` skill\n- Maintains the Decision Log\n\n**May:**\n- Ask clarification questions\n- Propose designs and alternatives\n- Revise designs based on feedback\n\n**May NOT:**\n- Self-approve the final design\n- Ignore reviewer objections\n- Invent requirements post-lock\n\n---\n\n### 2️⃣ Skeptic / Challenger Agent\n\n**Role:**\n- Assume the design will fail\n- Identify weaknesses and risks\n\n**May:**\n- Question assumptions\n- Identify edge cases\n- Highlight ambiguity or overconfidence\n- Flag YAGNI violations\n\n**May NOT:**\n- Propose new features\n- Redesign the system\n- Offer alternative architectures\n\nPrompting guidance:\n> “Assume this design fails in production. Why?”\n\n---\n\n### 3️⃣ Constraint Guardian Agent\n\n**Role:**\n- Enforce non-functional and real-world constraints\n\nFocus areas:\n- performance\n- scalability\n- reliability\n- security & privacy\n- maintainability\n- operational cost\n\n**May:**\n- Reject designs that violate constraints\n- Request clarification of limits\n\n**May NOT:**\n- Debate product goals\n- Suggest feature changes\n- Optimize beyond stated requirements\n\n---\n\n### 4️⃣ User Advocate Agent\n\n**Role:**\n- Represent the end user\n\nFocus areas:\n- cognitive load\n- usability\n- clarity of flows\n- error handling from user perspective\n- mismatch between intent and experience\n\n**May:**\n- Identify confusing or misleading aspects\n- Flag poor defaults or unclear behavior\n\n**May NOT:**\n- Redesign architecture\n- Add features\n- Override stated user goals\n\n---\n\n### 5️⃣ Integrator / Arbiter Agent\n\n**Role:**\n- Resolve conflicts\n- Finalize decisions\n- Enforce exit criteria\n\n**May:**\n- Accept or reject objections\n- Require design revisions\n- Declare the design complete\n\n**May NOT:**\n- Invent new ideas\n- Add requirements\n- Reopen locked decisions without cause\n\n---\n\n## The Process\n\n### Phase 1 — Single-Agent Design\n\n1. Primary Designer runs the **standard `brainstorming` skill**\n2. Understanding Lock is completed and confirmed\n3. Initial design is produced\n4. Decision Log is started\n\nNo other agents participate yet.\n\n---\n\n### Phase 2 — Structured Review Loop\n\nAgents are invoked **one at a time**, in the following order:\n\n1. Skeptic / Challenger\n2. Constraint Guardian\n3. User Advocate\n\nFor each reviewer:\n- Feedback must be explicit and scoped\n- Objections must reference assumptions or decisions\n- No new features may be introduced\n\nPrimary Designer must:\n- Respond to each objection\n- Revise the design if required\n- Update the Decision Log\n\n---\n\n### Phase 3 — Integration & Arbitration\n\nThe Integrator / Arbiter reviews:\n- the final design\n- the Decision Log\n- unresolved objections\n\nThe Arbiter must explicitly decide:\n- which objections are accepted\n- which are rejected (with rationale)\n\n---\n\n## Decision Log (Mandatory Artifact)\n\nThe Decision Log must record:\n\n- Decision made\n- Alternatives considered\n- Objections raised\n- Resolution and rationale\n\nNo design is considered valid without a completed log.\n\n---\n\n## Exit Criteria (Hard Stop)\n\nYou may exit multi-agent brainstorming **only when all are true**:\n\n- Understanding Lock was completed\n- All reviewer agents have been invoked\n- All objections are resolved or explicitly rejected\n- Decision Log is complete\n- Arbiter has declared the design acceptable\n- \nIf any criterion is unmet:\n- Continue review\n- Do NOT proceed to implementation\nIf this skill was invoked by a routing or orchestration layer, you MUST report the final disposition explicitly as one of: APPROVED, REVISE, or REJECT, with a brief rationale.\n---\n\n## Failure Modes This Skill Prevents\n\n- Idea swarm chaos\n- Hallucinated consensus\n- Overconfident single-agent designs\n- Hidden assumptions\n- Premature implementation\n- Endless debate\n\n---\n\n## Key Principles\n\n- One designer, many reviewers\n- Creativity is centralized\n- Critique is constrained\n- Decisions are explicit\n- Process must terminate\n\n---\n\n## Final Reminder\n\nThis skill exists to answer one question with confidence:\n\n> “If this design fails, did we do everything reasonable to catch it early?”\n\nIf the answer is unclear, **do not exit this skill**.\n\n## When to Use\nThis skill is applicable to execute the workflow or actions described in the overview.\n\n## Limitations\n- Use this skill only when the task clearly matches the scope described above.\n- Do not treat the output as a substitute for environment-specific validation, testing, or expert review.\n- Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.","tags":["multi","agent","brainstorming","antigravity","awesome","skills","sickn33","agent-skills","agentic-skills","ai-agent-skills","ai-agents","ai-coding"],"capabilities":["skill","source-sickn33","skill-multi-agent-brainstorming","topic-agent-skills","topic-agentic-skills","topic-ai-agent-skills","topic-ai-agents","topic-ai-coding","topic-ai-workflows","topic-antigravity","topic-antigravity-skills","topic-claude-code","topic-claude-code-skills","topic-codex-cli","topic-codex-skills"],"categories":["antigravity-awesome-skills"],"synonyms":[],"warnings":[],"endpointUrl":"https://skills.sh/sickn33/antigravity-awesome-skills/multi-agent-brainstorming","protocol":"skill","transport":"skills-sh","auth":{"type":"none","details":{"cli":"npx skills add sickn33/antigravity-awesome-skills","source_repo":"https://github.com/sickn33/antigravity-awesome-skills","install_from":"skills.sh"}},"qualityScore":"0.700","qualityRationale":"deterministic score 0.70 from registry signals: · indexed on github topic:agent-skills · 37911 github stars · SKILL.md body (5,410 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":"2026-05-18T18:51:24.878Z","embedding":null,"createdAt":"2026-04-18T20:36:18.336Z","updatedAt":"2026-05-18T18:51:24.878Z","lastSeenAt":"2026-05-18T18:51:24.878Z","tsv":"'1':374,379,425 '1️⃣':146 '2':387,410,428 '2️⃣':193 '3':394,431,472 '3️⃣':240 '4':399 '4️⃣':286 '5️⃣':335 'accept':348,495,570 'action':697 'add':329,364 'advoc':288,433 'agent':3,15,30,40,60,103,106,109,133,139,150,196,243,289,338,377,406,414,537,550,625 'altern':171,229,512 'ambigu':214 'answer':657,677 'applic':691 'approv':181,604 'arbit':337,477,488,565 'arbitr':474 'architectur':230,328 'area':255,296 'artifact':504 'ask':165,735 'aspect':318 'assum':198,233 'assumpt':21,67,209,446,628 'base':174 'behavior':324 'beyond':283 'boundari':743 'brainstorm':4,31,91,158,385,538 'brief':610 'case':212 'catch':672 'caus':370 'central':116,641 'challeng':195,427 'chang':281 'chao':86,619 'clarif':166,271,737 'clariti':300 'clear':710 'cognit':297 'complet':358,391,526,547,564 'confid':661 'confirm':393 'conflict':341 'confus':315 'consensus':621 'consid':513,522 'constrain':59,644 'constraint':76,241,253,269,429 'continu':576 'cost':263 'creativ':114,639 'criteria':346,529,746 'criterion':573 'critiqu':117,642 'debat':276,632 'decid':491 'decis':120,162,343,368,400,448,469,483,501,506,510,561,645 'declar':355,567 'default':321 'describ':698,714 'design':18,33,41,48,80,95,104,132,148,154,169,173,184,200,235,266,353,357,378,381,396,456,464,481,520,569,626,636,664 'disposit':599 'distribut':119 'earli':71,674 'edg':211 'end':293 'endless':631 'enforc':98,245,344 'environ':726 'environment-specif':725 'error':303 'everyth':669 'exceed':111 'execut':693 'exist':63,655 'exit':345,528,534,682 'experi':312 'expert':731 'explicit':122,440,490,559,600,647 'fail':202,236,665 'failur':24,69,612 'featur':224,280,330,451 'feedback':176,437 'final':183,342,480,598,651 'flag':217,319 'flow':302 'focus':254,295 'follow':423 'formal':52 'function':75,248 'gate':128 'goal':278,334 'guardian':242,430 'guidanc':232 'hallucin':620 'handl':304 'hard':143,530 'hidden':20,66,627 'highlight':213 'idea':84,363,617 'identifi':23,68,203,210,314 'ignor':185 'implement':27,82,582,630 'initi':395 'input':740 'integr':336,473,476 'intent':310 'introduc':454 'invent':188,361 'invok':416,553,587 'key':633 'layer':593 'lead':149 'limit':145,273,702 'load':298 'lock':192,367,389,545 'log':124,163,401,470,484,502,507,527,562 'loop':413 'made':511 'maintain':160,261 'mandat':113 'mandatori':503 'mani':637 'match':711 'may':110,164,177,207,220,264,274,313,325,347,359,452,533 'mislead':317 'mismatch':308 'miss':748 'mode':25,70,613 'model':101 'multi':2,29,536 'multi-ag':28,535 'multi-agent-brainstorm':1 'multipl':13,58 'must':438,444,457,489,508,595,649 'negoti':137 'new':223,362,450 'non':74,136,247 'non-funct':73,246 'non-negoti':135 'object':187,351,443,461,486,493,514,555 'offer':228 'one':102,417,602,635,658 'oper':100,140,262 'optim':282 'orchestr':592 'order':424 'output':720 'overconfid':216,622 'overrid':331 'overview':701 'own':152 'parallel':90 'particip':407 'peer':9,54 'peer-review':8,53 'perform':256 'permiss':741 'perspect':307 'phase':373,409,471 'poor':320 'post':191 'post-lock':190 'prematur':629 'prevent':83,616 'primari':147,380,455 'principl':634 'privaci':260 'proceed':580 'process':11,56,126,372,648 'produc':398 'product':238,277 'prompt':231 'propos':168,222 'purpos':35 'question':167,208,659 'rais':515 'rational':500,518,611 'real':251 'real-world':250 'reason':670 'record':509 'redesign':225,327 'refer':445 'reject':265,350,498,560,607 'reliabl':258 'remind':652 'reopen':366 'report':596 'repres':291 'request':270 'requir':189,285,352,365,466,739 'resolut':516 'resolv':340,557 'respond':458 'review':10,34,46,55,96,107,186,412,436,478,549,577,638,732 'review-valid':45 'revis':172,354,462,605 'risk':206 'robust':44 'role':99,134,151,197,244,290,339 'rout':590 'run':155,382 'safeti':742 'scalabl':257 'scope':144,442,713 'secur':259 'self':180 'self-approv':179 'sequenti':94 'simul':5,50 'singl':39,376,624 'single-ag':38,375,623 'skeptic':194,426 'skill':62,159,386,585,615,654,684,689,705 'skill-multi-agent-brainstorming' 'source-sickn33' 'special':14 'specif':727 'standard':157,384 'start':403 'state':284,332 'stop':531,733 'stress':78 'stress-test':77 'structur':7,32,411 'substitut':723 'success':745 'suggest':279 'surfac':19,65 'swarm':85,618 'system':227 'task':709 'termin':130,650 'test':79,729 'time':420 'topic-agent-skills' 'topic-agentic-skills' 'topic-ai-agent-skills' 'topic-ai-agents' 'topic-ai-coding' 'topic-ai-workflows' 'topic-antigravity' 'topic-antigravity-skills' 'topic-claude-code' 'topic-claude-code-skills' 'topic-codex-cli' 'topic-codex-skills' 'transform':36 'treat':718 'true':543 'unclear':323,679 'understand':388,544 'unmet':575 'unresolv':485 'updat':467 'usabl':299 'use':12,57,687,703 'user':287,294,306,333,432 'valid':17,47,72,523,728 'violat':219,268 'weak':204 'without':369,524 'workflow':695 'world':252 'yagni':218 'yet':408","prices":[{"id":"71f8f6a6-12a2-40e4-9048-7f707c5a94d5","listingId":"794abb4e-0614-42c2-9424-84732f4a0f83","amountUsd":"0","unit":"free","nativeCurrency":null,"nativeAmount":null,"chain":null,"payTo":null,"paymentMethod":"skill-free","isPrimary":true,"details":{"org":"sickn33","category":"antigravity-awesome-skills","install_from":"skills.sh"},"createdAt":"2026-04-18T20:36:18.336Z"}],"sources":[{"listingId":"794abb4e-0614-42c2-9424-84732f4a0f83","source":"github","sourceId":"sickn33/antigravity-awesome-skills/multi-agent-brainstorming","sourceUrl":"https://github.com/sickn33/antigravity-awesome-skills/tree/main/skills/multi-agent-brainstorming","isPrimary":false,"firstSeenAt":"2026-04-18T21:41:06.811Z","lastSeenAt":"2026-05-18T18:51:24.878Z"},{"listingId":"794abb4e-0614-42c2-9424-84732f4a0f83","source":"skills_sh","sourceId":"sickn33/antigravity-awesome-skills/multi-agent-brainstorming","sourceUrl":"https://skills.sh/sickn33/antigravity-awesome-skills/multi-agent-brainstorming","isPrimary":true,"firstSeenAt":"2026-04-18T20:36:18.336Z","lastSeenAt":"2026-05-07T22:40:42.678Z"}],"details":{"listingId":"794abb4e-0614-42c2-9424-84732f4a0f83","quickStartSnippet":null,"exampleRequest":null,"exampleResponse":null,"schema":null,"openapiUrl":null,"agentsTxtUrl":null,"citations":[],"useCases":[],"bestFor":[],"notFor":[],"kindDetails":{"org":"sickn33","slug":"multi-agent-brainstorming","github":{"repo":"sickn33/antigravity-awesome-skills","stars":37911,"topics":["agent-skills","agentic-skills","ai-agent-skills","ai-agents","ai-coding","ai-workflows","antigravity","antigravity-skills","claude-code","claude-code-skills","codex-cli","codex-skills","cursor","cursor-skills","developer-tools","gemini-cli","gemini-skills","kiro","mcp","skill-library"],"license":"mit","html_url":"https://github.com/sickn33/antigravity-awesome-skills","pushed_at":"2026-05-18T08:24:49Z","description":"Installable GitHub library of 1,400+ agentic skills for Claude Code, Cursor, Codex CLI, Gemini CLI, Antigravity, and more. Includes installer CLI, bundles, workflows, and official/community skill collections.","skill_md_sha":"a435e3052026f58d1270e8547fbc50eecd8a5e4d","skill_md_path":"skills/multi-agent-brainstorming/SKILL.md","default_branch":"main","skill_tree_url":"https://github.com/sickn33/antigravity-awesome-skills/tree/main/skills/multi-agent-brainstorming"},"layout":"multi","source":"github","category":"antigravity-awesome-skills","frontmatter":{"name":"multi-agent-brainstorming","description":"Simulate a structured peer-review process using multiple specialized agents to validate designs, surface hidden assumptions, and identify failure modes before implementation."},"skills_sh_url":"https://skills.sh/sickn33/antigravity-awesome-skills/multi-agent-brainstorming"},"updatedAt":"2026-05-18T18:51:24.878Z"}}