[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M72YYEXC58DGHVT5R1VM7EMZ":3,"skill-same:01M72YYEXC58DGHVT5R1VM7EMZ":46},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":26,"commitSha":27,"skillDirectory":28,"forksCount":29,"repositoryHtmlUrl":30,"repositoryHomepageUrl":6,"ownerHtmlUrl":31,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":32,"install":33,"resources":45},"01M72YYEXC58DGHVT5R1VM7EMZ","validation-sprint",null,"Run a multi-agent validation sprint to answer: Should I build this?","enigmaicon-eng\u002FAI-Enterprise-OS","enigmaicon-eng","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F269773191?v=4","01M72YXXYN7Q7BYRHV8RAVYNWD","01M72YXXZPW35H56D6F1XSK84D",2,"MIT","https:\u002F\u002Fgithub.com\u002Fenigmaicon-eng\u002FAI-Enterprise-OS\u002Fblob\u002Fmain\u002Fagents\u002Fplugins\u002Fagent-teams\u002Fskills\u002Fvalidation-sprint\u002FSKILL.md",[],[],"2026-11-11 15:11:14",false,"---\nname: validation-sprint\ndescription: \"Run a multi-agent validation sprint to answer: Should I build this?\"\nuser-invocable: true\ndisable-model-invocation: true\nargument-hint: '\"\u003Cidea description>\"'\nallowed-tools: Read, Glob, Grep, Task\n---\n\n# Validation Sprint\n\nRun a multi-agent validation sprint to answer: **\"Should I build this?\"** Three agents investigate in parallel, cross-examine each other's findings, and deliver a go\u002Fno-go verdict.\n\n## Usage\n\n```bash\n\u002Fagent-teams:validation-sprint \"AI-powered code review tool for solo developers\"\n```\n\n---\n\n## Overview\n\nThis command spawns three teammates with competing perspectives to stress-test a product idea:\n\n- **idea-researcher**: Investigates the user problem (pain severity, frequency, workarounds)\n- **market-researcher**: Investigates the market opportunity (size, competition, timing)\n- **idea-skeptic**: Tries to kill the idea (finds structural reasons it should fail)\n\nAfter parallel investigation, agents cross-examine each other's findings. The lead synthesizes everything into a **Validation Verdict** with scores and a BUILD \u002F DON'T BUILD \u002F NEEDS MORE EVIDENCE recommendation.\n\n**What you get:**\n\n- Three independent perspectives on your idea\n- Cross-examination that surfaces blind spots\n- Scored verdict (User Problem, Market Opportunity, Defensibility)\n- Key risks with mitigations\n- Specific next steps\n\n---\n\n## Idea Under Investigation\n\n$ARGUMENTS\n\n---\n\n## Instructions\n\n### Pre-Flight Check\n\nBefore starting, verify Agent Teams is available in your Claude Code version.\nIf teammates cannot be spawned, display:\n\n```\nThis command requires Claude Code's Agent Teams feature.\nCheck https:\u002F\u002Fdocs.anthropic.com\u002Fen\u002Fdocs\u002Fclaude-code for setup instructions.\n```\n\nIf not available, stop.\n\n---\n\n### Phase 1: Briefing\n\n1. Check for existing product context:\n   - Read `.claude\u002Fproduct-context\u002Fproduct-info.md` if it exists\n   - Read `.claude\u002Fproduct-context\u002Fcompetitive-landscape.md` if it exists\n   - Read `.claude\u002Fproduct-context\u002Fcustomer-segments.md` if it exists\n\n2. Display briefing:\n\n```\n── Validation Sprint ──────────────────────────────────────\n\nIdea: [parsed idea description]\n\nAssembling your validation team:\n  1. idea-researcher   → Investigating the user problem\n  2. market-researcher → Researching the market opportunity\n  3. idea-skeptic      → Trying to kill this idea\n\nPhase 1: Parallel Investigation (3 agents working simultaneously)\nPhase 2: Cross-Examination (agents challenge each other)\nPhase 3: Synthesis (final verdict with scores)\n\nStarting investigation...\n───────────────────────────────────────────────────────────\n```\n\n---\n\n### Phase 2: Parallel Investigation\n\nSpawn 3 teammates simultaneously using Agent Teams:\n\n**Teammate 1: idea-researcher**\n\n```\nPrompt: \"Investigate the user problem behind this idea: [idea description].\n\n[Include any product context found in Phase 1]\n\nYour job: Determine if this is a real, painful problem for real people.\nAssess pain severity, frequency, existing workarounds, and who feels this most.\nUse your research-ops expertise. Search for evidence in forums, review sites,\nand community discussions.\n\nDeliver your findings in the standard idea-researcher output format.\nInclude confidence levels and evidence gaps.\"\n```\n\n**Teammate 2: market-researcher**\n\n```\nPrompt: \"Research the market opportunity for this idea: [idea description].\n\n[Include any product context found in Phase 1]\n\nYour job: Assess market size, competitive landscape, and timing.\nUse WebSearch to find real data on competitors, pricing, and market indicators.\nEstimate TAM\u002FSAM\u002FSOM with transparent methodology.\n\nDeliver your findings in the standard market-researcher validation sprint format.\nInclude source URLs and data gaps.\"\n```\n\n**Teammate 3: idea-skeptic**\n\n```\nPrompt: \"Try to kill this idea: [idea description].\n\n[Include any product context found in Phase 1]\n\nYour job: Find every structural reason this idea should NOT be built.\nUse your attack patterns: vitamin vs painkiller, feature vs product,\ntemporary differentiation, vague target market, incumbent response,\nTAM inflation, switching costs.\n\nDeliver at least 3 specific attacks in the standard idea-skeptic output format.\nRate each attack's severity. Be honest about which attacks are strong vs weak.\"\n```\n\nWait for all three teammates to complete their investigations.\n\n---\n\n### Phase 3: Cross-Examination\n\nSend each agent the other two agents' findings for one round of structured challenges.\n\n**To idea-researcher:**\n\n```\n\"Here are your teammates' findings. Review them and provide your challenges.\n\nMARKET RESEARCHER'S FINDINGS:\n[market-researcher output]\n\nSKEPTIC'S CASE:\n[idea-skeptic output]\n\nChallenge their findings from the user problem perspective. Cite specific\nclaims from their reports. Use the cross-examination patterns from the\nteam-coordination skill. Focus your 2-3 strongest challenges.\"\n```\n\n**To market-researcher:**\n\n```\n\"Here are your teammates' findings. Review them and provide your challenges.\n\nIDEA RESEARCHER'S FINDINGS:\n[idea-researcher output]\n\nSKEPTIC'S CASE:\n[idea-skeptic output]\n\nChallenge their findings from the market perspective. Cite specific claims\nfrom their reports. Use the cross-examination patterns from the team-coordination\nskill. Focus your 2-3 strongest challenges.\"\n```\n\n**To idea-skeptic:**\n\n```\n\"Here are your teammates' findings. Review them and provide your challenges.\n\nIDEA RESEARCHER'S FINDINGS:\n[idea-researcher output]\n\nMARKET RESEARCHER'S FINDINGS:\n[market-researcher output]\n\nUpdate your case based on their evidence. Which of your attacks still stand?\nWhich are weakened? Do their findings reveal new vulnerabilities? Cite specific\nevidence from their reports.\"\n```\n\nWait for all three cross-examination responses.\n\n---\n\n### Phase 4: Synthesis\n\nAs the lead agent, compile all findings into the Validation Verdict.\n\n1. Read all investigation reports and cross-examination responses.\n\n2. Invoke the `team-deliverables` skill for the validation verdict template.\n\n3. Score each dimension (1-10) using the rubrics from `team-deliverables`:\n   - **User Problem**: Based primarily on idea-researcher's findings\n   - **Market Opportunity**: Based primarily on market-researcher's findings\n   - **Defensibility**: Based on all three perspectives, weighted by skeptic's attacks\n\n4. Determine verdict:\n   - **BUILD**: All scores 6+, no fatal skeptic attacks standing, convergence across agents\n   - **DON'T BUILD**: Any score below 4, or fatal skeptic attacks unanswered\n   - **NEEDS MORE EVIDENCE**: Scores 4-6 range with significant evidence gaps\n\n5. Fill in the validation verdict template with:\n   - Executive summary\n   - Scores with justifications\n   - Evidence from each agent\n   - Cross-examination highlights (where they agreed, where they disagreed)\n   - Key risks with mitigations\n   - Specific next steps based on verdict\n   - Dissenting views if any agent strongly disagreed with the verdict\n\n6. Present the completed verdict to the user.\n\n---\n\n### Phase 5: Cleanup\n\n1. Shut down all three teammates.\n\n2. Offer to save the verdict:\n\n```\nValidation sprint complete.\n\nWould you like me to save this verdict to:\n  .claude\u002Fproduct-context\u002Fvalidation-[idea-slug].md\n\nThis will be available to other PM agents for future reference.\n```\n\n3. If user accepts, save the verdict file. If not, done.\n\n---\n\n## Error Handling\n\n- If a teammate fails to produce output, note the gap in the synthesis and proceed with available findings. Don't fail the entire sprint.\n- If WebSearch is unavailable, market-researcher should note data limitations and work with available information.\n- If the idea description is too vague, ask the user for clarification before spawning teammates.\n\n## Related\n\n- `\u002Fagent-teams:prd-stress-test` - After validation, stress-test the PRD\n- `\u002Fagent-teams:competitive-war-room` - Deep-dive specific competitors\n","# Validation Sprint\n\nRun a multi-agent validation sprint to answer: **\"Should I build this?\"** Three agents investigate in parallel, cross-examine each other's findings, and deliver a go\u002Fno-go verdict.\n\n## Usage\n\n```bash\n\u002Fagent-teams:validation-sprint \"AI-powered code review tool for solo developers\"\n```\n\n---\n\n## Overview\n\nThis command spawns three teammates with competing perspectives to stress-test a product idea:\n\n- **idea-researcher**: Investigates the user problem (pain severity, frequency, workarounds)\n- **market-researcher**: Investigates the market opportunity (size, competition, timing)\n- **idea-skeptic**: Tries to kill the idea (finds structural reasons it should fail)\n\nAfter parallel investigation, agents cross-examine each other's findings. The lead synthesizes everything into a **Validation Verdict** with scores and a BUILD \u002F DON'T BUILD \u002F NEEDS MORE EVIDENCE recommendation.\n\n**What you get:**\n\n- Three independent perspectives on your idea\n- Cross-examination that surfaces blind spots\n- Scored verdict (User Problem, Market Opportunity, Defensibility)\n- Key risks with mitigations\n- Specific next steps\n\n---\n\n## Idea Under Investigation\n\n$ARGUMENTS\n\n---\n\n## Instructions\n\n### Pre-Flight Check\n\nBefore starting, verify Agent Teams is available in your Claude Code version.\nIf teammates cannot be spawned, display:\n\n```\nThis command requires Claude Code's Agent Teams feature.\nCheck https:\u002F\u002Fdocs.anthropic.com\u002Fen\u002Fdocs\u002Fclaude-code for setup instructions.\n```\n\nIf not available, stop.\n\n---\n\n### Phase 1: Briefing\n\n1. Check for existing product context:\n   - Read `.claude\u002Fproduct-context\u002Fproduct-info.md` if it exists\n   - Read `.claude\u002Fproduct-context\u002Fcompetitive-landscape.md` if it exists\n   - Read `.claude\u002Fproduct-context\u002Fcustomer-segments.md` if it exists\n\n2. Display briefing:\n\n```\n── Validation Sprint ──────────────────────────────────────\n\nIdea: [parsed idea description]\n\nAssembling your validation team:\n  1. idea-researcher   → Investigating the user problem\n  2. market-researcher → Researching the market opportunity\n  3. idea-skeptic      → Trying to kill this idea\n\nPhase 1: Parallel Investigation (3 agents working simultaneously)\nPhase 2: Cross-Examination (agents challenge each other)\nPhase 3: Synthesis (final verdict with scores)\n\nStarting investigation...\n───────────────────────────────────────────────────────────\n```\n\n---\n\n### Phase 2: Parallel Investigation\n\nSpawn 3 teammates simultaneously using Agent Teams:\n\n**Teammate 1: idea-researcher**\n\n```\nPrompt: \"Investigate the user problem behind this idea: [idea description].\n\n[Include any product context found in Phase 1]\n\nYour job: Determine if this is a real, painful problem for real people.\nAssess pain severity, frequency, existing workarounds, and who feels this most.\nUse your research-ops expertise. Search for evidence in forums, review sites,\nand community discussions.\n\nDeliver your findings in the standard idea-researcher output format.\nInclude confidence levels and evidence gaps.\"\n```\n\n**Teammate 2: market-researcher**\n\n```\nPrompt: \"Research the market opportunity for this idea: [idea description].\n\n[Include any product context found in Phase 1]\n\nYour job: Assess market size, competitive landscape, and timing.\nUse WebSearch to find real data on competitors, pricing, and market indicators.\nEstimate TAM\u002FSAM\u002FSOM with transparent methodology.\n\nDeliver your findings in the standard market-researcher validation sprint format.\nInclude source URLs and data gaps.\"\n```\n\n**Teammate 3: idea-skeptic**\n\n```\nPrompt: \"Try to kill this idea: [idea description].\n\n[Include any product context found in Phase 1]\n\nYour job: Find every structural reason this idea should NOT be built.\nUse your attack patterns: vitamin vs painkiller, feature vs product,\ntemporary differentiation, vague target market, incumbent response,\nTAM inflation, switching costs.\n\nDeliver at least 3 specific attacks in the standard idea-skeptic output format.\nRate each attack's severity. Be honest about which attacks are strong vs weak.\"\n```\n\nWait for all three teammates to complete their investigations.\n\n---\n\n### Phase 3: Cross-Examination\n\nSend each agent the other two agents' findings for one round of structured challenges.\n\n**To idea-researcher:**\n\n```\n\"Here are your teammates' findings. Review them and provide your challenges.\n\nMARKET RESEARCHER'S FINDINGS:\n[market-researcher output]\n\nSKEPTIC'S CASE:\n[idea-skeptic output]\n\nChallenge their findings from the user problem perspective. Cite specific\nclaims from their reports. Use the cross-examination patterns from the\nteam-coordination skill. Focus your 2-3 strongest challenges.\"\n```\n\n**To market-researcher:**\n\n```\n\"Here are your teammates' findings. Review them and provide your challenges.\n\nIDEA RESEARCHER'S FINDINGS:\n[idea-researcher output]\n\nSKEPTIC'S CASE:\n[idea-skeptic output]\n\nChallenge their findings from the market perspective. Cite specific claims\nfrom their reports. Use the cross-examination patterns from the team-coordination\nskill. Focus your 2-3 strongest challenges.\"\n```\n\n**To idea-skeptic:**\n\n```\n\"Here are your teammates' findings. Review them and provide your challenges.\n\nIDEA RESEARCHER'S FINDINGS:\n[idea-researcher output]\n\nMARKET RESEARCHER'S FINDINGS:\n[market-researcher output]\n\nUpdate your case based on their evidence. Which of your attacks still stand?\nWhich are weakened? Do their findings reveal new vulnerabilities? Cite specific\nevidence from their reports.\"\n```\n\nWait for all three cross-examination responses.\n\n---\n\n### Phase 4: Synthesis\n\nAs the lead agent, compile all findings into the Validation Verdict.\n\n1. Read all investigation reports and cross-examination responses.\n\n2. Invoke the `team-deliverables` skill for the validation verdict template.\n\n3. Score each dimension (1-10) using the rubrics from `team-deliverables`:\n   - **User Problem**: Based primarily on idea-researcher's findings\n   - **Market Opportunity**: Based primarily on market-researcher's findings\n   - **Defensibility**: Based on all three perspectives, weighted by skeptic's attacks\n\n4. Determine verdict:\n   - **BUILD**: All scores 6+, no fatal skeptic attacks standing, convergence across agents\n   - **DON'T BUILD**: Any score below 4, or fatal skeptic attacks unanswered\n   - **NEEDS MORE EVIDENCE**: Scores 4-6 range with significant evidence gaps\n\n5. Fill in the validation verdict template with:\n   - Executive summary\n   - Scores with justifications\n   - Evidence from each agent\n   - Cross-examination highlights (where they agreed, where they disagreed)\n   - Key risks with mitigations\n   - Specific next steps based on verdict\n   - Dissenting views if any agent strongly disagreed with the verdict\n\n6. Present the completed verdict to the user.\n\n---\n\n### Phase 5: Cleanup\n\n1. Shut down all three teammates.\n\n2. Offer to save the verdict:\n\n```\nValidation sprint complete.\n\nWould you like me to save this verdict to:\n  .claude\u002Fproduct-context\u002Fvalidation-[idea-slug].md\n\nThis will be available to other PM agents for future reference.\n```\n\n3. If user accepts, save the verdict file. If not, done.\n\n---\n\n## Error Handling\n\n- If a teammate fails to produce output, note the gap in the synthesis and proceed with available findings. Don't fail the entire sprint.\n- If WebSearch is unavailable, market-researcher should note data limitations and work with available information.\n- If the idea description is too vague, ask the user for clarification before spawning teammates.\n\n## Related\n\n- `\u002Fagent-teams:prd-stress-test` - After validation, stress-test the PRD\n- `\u002Fagent-teams:competitive-war-room` - Deep-dive specific competitors\n",{"name":5,"description":7,"allowed-tools":23,"argument-hint":24,"user-invocable":25,"disable-model-invocation":25},"Read, Glob, Grep, Task","\"\u003Cidea description>\"",true,"main","a4b48842f3e48549adf3dc335a8837c66da99497","agents\u002Fplugins\u002Fagent-teams\u002Fskills\u002Fvalidation-sprint",0,"https:\u002F\u002Fgithub.com\u002Fenigmaicon-eng\u002FAI-Enterprise-OS","https:\u002F\u002Fgithub.com\u002Fenigmaicon-eng","2026-05-17 16:00:01",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":25},[35,38,41],{"tool":36,"command":37},"npx","npx skills add enigmaicon-eng\u002FAI-Enterprise-OS --skill validation-sprint",{"tool":39,"command":40},"bunx","bunx skills add enigmaicon-eng\u002FAI-Enterprise-OS --skill validation-sprint",{"tool":42,"command":43},"pnpm","pnpm dlx skills add enigmaicon-eng\u002FAI-Enterprise-OS --skill validation-sprint","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fenigmaicon-eng\u002FAI-Enterprise-OS\u002Fblob\u002Fmain\u002Fagents\u002Fplugins\u002Fagent-teams\u002Fskills\u002Fvalidation-sprint\u002FSKILL.md",[],[47,54,61,68,75,82],{"skillNo":48,"name":49,"nameZh":6,"description":50,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":51,"categories":52,"keywords":53,"publishedAt":18},"01M72ZGWW03JSE1T3TKK5NZ11Y","writing-skills","Use when creating new skills, editing existing skills, or verifying skills work before deployment","https:\u002F\u002Fgithub.com\u002Fenigmaicon-eng\u002FAI-Enterprise-OS\u002Fblob\u002Fmain\u002Fexamples\u002Fsuperpowers\u002Fskills\u002Fwriting-skills\u002FSKILL.md",[],[],{"skillNo":55,"name":56,"nameZh":6,"description":57,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":58,"categories":59,"keywords":60,"publishedAt":18},"01M72ZGT3FJT7QRM1VNQRKR0XD","writing-plans","Use when you have a spec or requirements for a multi-step task, before touching code","https:\u002F\u002Fgithub.com\u002Fenigmaicon-eng\u002FAI-Enterprise-OS\u002Fblob\u002Fmain\u002Fexamples\u002Fsuperpowers\u002Fskills\u002Fwriting-plans\u002FSKILL.md",[],[],{"skillNo":62,"name":63,"nameZh":6,"description":64,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":65,"categories":66,"keywords":67,"publishedAt":18},"01M72ZGQ69DCF0SBP9JXFPWKJS","verification-before-completion","Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always","https:\u002F\u002Fgithub.com\u002Fenigmaicon-eng\u002FAI-Enterprise-OS\u002Fblob\u002Fmain\u002Fexamples\u002Fsuperpowers\u002Fskills\u002Fverification-before-completion\u002FSKILL.md",[],[],{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"publishedAt":18},"01M72ZGNF126QT0MQ2D3DNGZRN","using-superpowers","Use when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions","https:\u002F\u002Fgithub.com\u002Fenigmaicon-eng\u002FAI-Enterprise-OS\u002Fblob\u002Fmain\u002Fexamples\u002Fsuperpowers\u002Fskills\u002Fusing-superpowers\u002FSKILL.md",[],[],{"skillNo":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"publishedAt":18},"01M72ZGHVJ9S0YXMNBHQGQ95BY","using-git-worktrees","Use when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallback","https:\u002F\u002Fgithub.com\u002Fenigmaicon-eng\u002FAI-Enterprise-OS\u002Fblob\u002Fmain\u002Fexamples\u002Fsuperpowers\u002Fskills\u002Fusing-git-worktrees\u002FSKILL.md",[],[],{"skillNo":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"publishedAt":18},"01M72ZGFNZCHFY2FS3ZD9MCYV9","test-driven-development","Use when implementing any feature or bugfix, before writing implementation code","https:\u002F\u002Fgithub.com\u002Fenigmaicon-eng\u002FAI-Enterprise-OS\u002Fblob\u002Fmain\u002Fexamples\u002Fsuperpowers\u002Fskills\u002Ftest-driven-development\u002FSKILL.md",[],[]]