[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M75C0W2P92V1M0YE6EQ314ST":3,"skill-same:01M75C0W2P92V1M0YE6EQ314ST":46},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"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":23,"commitSha":24,"skillDirectory":25,"forksCount":26,"repositoryHtmlUrl":27,"repositoryHomepageUrl":28,"ownerHtmlUrl":29,"ownerBlogUrl":30,"ownerDescription":6,"updatedAt":31,"install":32,"resources":45},"01M75C0W2P92V1M0YE6EQ314ST","caio-review",null,"\u002Fcs:caio-review \u003Cplan> — Eval-demanding Chief AI Officer interrogation of any plan that involves AI: model selection, risk classification, cost economics, or AI hiring.","agisota\u002Fold-one","agisota","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F121413592?v=4","01M75B4BRNT67EC1NDRT8QZEP2","01M75B4BS7QR9VP580MSCPTS3X",3,"MIT","https:\u002F\u002Fgithub.com\u002Fagisota\u002Fold-one\u002Fblob\u002Fmain\u002Fskills\u002Fcaio-review\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: \"caio-review\"\ndescription: \"\u002Fcs:caio-review \u003Cplan> — Eval-demanding Chief AI Officer interrogation of any plan that involves AI: model selection, risk classification, cost economics, or AI hiring.\"\n---\n\n# \u002Fcs:caio-review — CAIO Forcing Questions\n\n**Command:** `\u002Fcs:caio-review \u003Cplan>`\n\nThe eval-demanding CAIO pressure-tests any plan that involves AI. Six questions before any AI feature ships, any multi-year vendor commitment, or any AI team expansion.\n\n## When to Run\n\n- Before shipping any new AI-powered feature\n- Before signing a multi-year AI vendor contract (API or self-hosted infra)\n- Before EU launch of any AI feature\n- Before a major AI team hire (especially ML engineer or research scientist)\n- Before a fine-tuning project commitment\n- Before adopting AI in a regulated domain (employment, credit, healthcare, education, etc.)\n- When the founder uses the word \"AI\" near \"competitive advantage\" or \"moat\"\n\n## The Six CAIO Questions\n\n### 1. What does this AI need to be good at, and how would you measure it?\n**No eval set = no ship.** Before any AI feature deploys, define the eval criteria.\n- 50-100 representative inputs minimum\n- Expected outputs OR rubric for grading\n- Edge cases: ambiguous, adversarial, format-edge\n- If you can't write down what \"good\" looks like, you don't have a feature; you have a vibe.\n\n### 2. What's the SLO on hallucination \u002F error rate, and what's the fallback?\n**Every AI feature has a failure mode. Plan for it.**\n- Quantified SLO: \"\u003C5% hallucination on factual queries\"\n- Detection mechanism: monitoring, sampling, customer feedback loop\n- Fallback: human-in-loop review, lower-risk default response, refuse-to-answer\n- Blast radius if SLO breached: how many users affected, what is the cost?\n\n### 3. What's the risk tier under EU AI Act, and is conformity assessment required?\n**Run `ai_risk_classifier.py` if any EU residents are affected OR domain is regulated.**\n- PROHIBITED → cannot launch in EU; re-scope\n- HIGH → conformity assessment + EU DB registration + 10 Articles of obligations (3-12 months, $50-200K)\n- LIMITED → transparency obligations (chatbot disclosure, AI-generated content marking)\n- MINIMAL → no specific obligations; NIST AI RMF voluntary\n\n### 4. API, fine-tune, or build?\n**Run `model_buildvsbuy_calculator.py` for the specific use case.**\n- 80% of B2B SaaS use cases: API\n- 15%: fine-tune (when domain-specific behavior + labeled data + ML team + high volume)\n- \u003C1%: build from scratch\n- Decision must consider economic breakeven AND practical feasibility (data, team, compliance)\n\n### 5. What's the 12-month cost trajectory at expected scale?\n**Run `ai_cost_economics.py` for the workload.**\n- API: variable, scales linearly\n- Self-hosted: mostly fixed, breakeven typically 1-10B tokens\u002Fmonth for 70B-class\n- Hidden costs of self-hosted: ops, monitoring, model updates, capacity, failover, security\n- Hidden costs of API: vendor lock-in, capability drift, rate limits, data residency\n- Prompt caching is the most underrated lever; check provider support\n\n### 6. What role unblocks this — and have we hired prerequisites first?\n**Map AI capability to specific role. Founders confuse AI engineer \u002F ML engineer \u002F research scientist.**\n- AI engineer: applied + full-stack + prompts + evals + deployment (most startups need this)\n- ML engineer: fine-tuning + retraining infra (only after platform engineer + labeled data)\n- Research scientist: model invention (only if model IS the product)\n- Don't hire research scientist as first AI hire — they need infrastructure to be productive\n\n## Workflow\n\n```bash\n# 1. Model selection check\npython ..\u002F..\u002F..\u002Fskills\u002Fchief-ai-officer-advisor\u002Fscripts\u002Fmodel_buildvsbuy_calculator.py use_case.json\n\n# 2. Regulatory classification\npython ..\u002F..\u002F..\u002Fskills\u002Fchief-ai-officer-advisor\u002Fscripts\u002Fai_risk_classifier.py use_case.json\n\n# 3. Cost projection\npython ..\u002F..\u002F..\u002Fskills\u002Fchief-ai-officer-advisor\u002Fscripts\u002Fai_cost_economics.py workload.json\n```\n\n## Output Format\n\n```markdown\n# CAIO Review: \u003Cplan>\n**Date:** YYYY-MM-DD\n\n## The Decision Being Made\n[one sentence — which CAIO decision: model selection | risk classification | economics | next hire]\n\n## Eval Discipline\n- Eval set committed: yes\u002Fno\n- SLO defined: \u003Cmetric> \u003C \u003Cthreshold>\n- Fallback behavior: \u003Cone line>\n\n## Model Selection (if applicable)\n- Recommended: API \u002F FINE_TUNE \u002F BUILD\n- 3-year TCO: $X (chosen path) vs $Y (alternatives)\n- Breakeven: \u003Cvolume>\n\n## Risk Classification (if applicable)\n- EU AI Act tier: PROHIBITED \u002F HIGH \u002F LIMITED \u002F MINIMAL\n- Conformity assessment required: yes\u002Fno\n- US state triggers: [list]\n- Required controls open: N\n\n## Cost Economics (if applicable)\n- Monthly cost at current volume: $X\n- Breakeven for self-hosted migration: \u003Cvolume>\n- Migration cost if applicable: $X (3-6 months)\n\n## Org (if applicable)\n- Next hire: \u003Crole>\n- Why this, not the alternative: \u003Cone line>\n- Prerequisite hires in place: yes\u002Fno\n\n## Verdict\n🟢 SHIP | 🟡 SHARPEN | 🔴 BLOCK\n\n## Next Steps\n[3 concrete actions]\n```\n\n## Routing\n\n- `\u002Fcs:cdo-review` — for any training-data implications\n- `\u002Fcs:gc-review` — for AI vendor contracts, output liability, training-data licensing\n- `\u002Fcs:ciso-review` — for prompt injection \u002F jailbreak \u002F training-data poisoning threat model\n- `\u002Fcs:cfo-review` — for multi-year vendor or GPU commitment TCO\n- `\u002Fcs:chro-review` — for AI team hires (comp, ladder, leveling)\n- `\u002Fcs:decide` — log the verdict\n- `\u002Fcs:freeze 60` — on multi-year AI commitments\n\n## Related\n\n- Agent: [`cs-caio-advisor`](..\u002F..\u002Fagents\u002Fcs-caio-advisor.md)\n- Skill: [`chief-ai-officer-advisor`](..\u002F..\u002F..\u002Fskills\u002Fchief-ai-officer-advisor\u002FSKILL.md)\n- Adjacent: `..\u002F..\u002F..\u002Fskills\u002Fchief-data-officer-advisor\u002F` (training data rights, data strategy)\n\n---\n\n**Version:** 1.0.0\n","# \u002Fcs:caio-review — CAIO Forcing Questions\n\n**Command:** `\u002Fcs:caio-review \u003Cplan>`\n\nThe eval-demanding CAIO pressure-tests any plan that involves AI. Six questions before any AI feature ships, any multi-year vendor commitment, or any AI team expansion.\n\n## When to Run\n\n- Before shipping any new AI-powered feature\n- Before signing a multi-year AI vendor contract (API or self-hosted infra)\n- Before EU launch of any AI feature\n- Before a major AI team hire (especially ML engineer or research scientist)\n- Before a fine-tuning project commitment\n- Before adopting AI in a regulated domain (employment, credit, healthcare, education, etc.)\n- When the founder uses the word \"AI\" near \"competitive advantage\" or \"moat\"\n\n## The Six CAIO Questions\n\n### 1. What does this AI need to be good at, and how would you measure it?\n**No eval set = no ship.** Before any AI feature deploys, define the eval criteria.\n- 50-100 representative inputs minimum\n- Expected outputs OR rubric for grading\n- Edge cases: ambiguous, adversarial, format-edge\n- If you can't write down what \"good\" looks like, you don't have a feature; you have a vibe.\n\n### 2. What's the SLO on hallucination \u002F error rate, and what's the fallback?\n**Every AI feature has a failure mode. Plan for it.**\n- Quantified SLO: \"\u003C5% hallucination on factual queries\"\n- Detection mechanism: monitoring, sampling, customer feedback loop\n- Fallback: human-in-loop review, lower-risk default response, refuse-to-answer\n- Blast radius if SLO breached: how many users affected, what is the cost?\n\n### 3. What's the risk tier under EU AI Act, and is conformity assessment required?\n**Run `ai_risk_classifier.py` if any EU residents are affected OR domain is regulated.**\n- PROHIBITED → cannot launch in EU; re-scope\n- HIGH → conformity assessment + EU DB registration + 10 Articles of obligations (3-12 months, $50-200K)\n- LIMITED → transparency obligations (chatbot disclosure, AI-generated content marking)\n- MINIMAL → no specific obligations; NIST AI RMF voluntary\n\n### 4. API, fine-tune, or build?\n**Run `model_buildvsbuy_calculator.py` for the specific use case.**\n- 80% of B2B SaaS use cases: API\n- 15%: fine-tune (when domain-specific behavior + labeled data + ML team + high volume)\n- \u003C1%: build from scratch\n- Decision must consider economic breakeven AND practical feasibility (data, team, compliance)\n\n### 5. What's the 12-month cost trajectory at expected scale?\n**Run `ai_cost_economics.py` for the workload.**\n- API: variable, scales linearly\n- Self-hosted: mostly fixed, breakeven typically 1-10B tokens\u002Fmonth for 70B-class\n- Hidden costs of self-hosted: ops, monitoring, model updates, capacity, failover, security\n- Hidden costs of API: vendor lock-in, capability drift, rate limits, data residency\n- Prompt caching is the most underrated lever; check provider support\n\n### 6. What role unblocks this — and have we hired prerequisites first?\n**Map AI capability to specific role. Founders confuse AI engineer \u002F ML engineer \u002F research scientist.**\n- AI engineer: applied + full-stack + prompts + evals + deployment (most startups need this)\n- ML engineer: fine-tuning + retraining infra (only after platform engineer + labeled data)\n- Research scientist: model invention (only if model IS the product)\n- Don't hire research scientist as first AI hire — they need infrastructure to be productive\n\n## Workflow\n\n```bash\n# 1. Model selection check\npython ..\u002F..\u002F..\u002Fskills\u002Fchief-ai-officer-advisor\u002Fscripts\u002Fmodel_buildvsbuy_calculator.py use_case.json\n\n# 2. Regulatory classification\npython ..\u002F..\u002F..\u002Fskills\u002Fchief-ai-officer-advisor\u002Fscripts\u002Fai_risk_classifier.py use_case.json\n\n# 3. Cost projection\npython ..\u002F..\u002F..\u002Fskills\u002Fchief-ai-officer-advisor\u002Fscripts\u002Fai_cost_economics.py workload.json\n```\n\n## Output Format\n\n```markdown\n# CAIO Review: \u003Cplan>\n**Date:** YYYY-MM-DD\n\n## The Decision Being Made\n[one sentence — which CAIO decision: model selection | risk classification | economics | next hire]\n\n## Eval Discipline\n- Eval set committed: yes\u002Fno\n- SLO defined: \u003Cmetric> \u003C \u003Cthreshold>\n- Fallback behavior: \u003Cone line>\n\n## Model Selection (if applicable)\n- Recommended: API \u002F FINE_TUNE \u002F BUILD\n- 3-year TCO: $X (chosen path) vs $Y (alternatives)\n- Breakeven: \u003Cvolume>\n\n## Risk Classification (if applicable)\n- EU AI Act tier: PROHIBITED \u002F HIGH \u002F LIMITED \u002F MINIMAL\n- Conformity assessment required: yes\u002Fno\n- US state triggers: [list]\n- Required controls open: N\n\n## Cost Economics (if applicable)\n- Monthly cost at current volume: $X\n- Breakeven for self-hosted migration: \u003Cvolume>\n- Migration cost if applicable: $X (3-6 months)\n\n## Org (if applicable)\n- Next hire: \u003Crole>\n- Why this, not the alternative: \u003Cone line>\n- Prerequisite hires in place: yes\u002Fno\n\n## Verdict\n🟢 SHIP | 🟡 SHARPEN | 🔴 BLOCK\n\n## Next Steps\n[3 concrete actions]\n```\n\n## Routing\n\n- `\u002Fcs:cdo-review` — for any training-data implications\n- `\u002Fcs:gc-review` — for AI vendor contracts, output liability, training-data licensing\n- `\u002Fcs:ciso-review` — for prompt injection \u002F jailbreak \u002F training-data poisoning threat model\n- `\u002Fcs:cfo-review` — for multi-year vendor or GPU commitment TCO\n- `\u002Fcs:chro-review` — for AI team hires (comp, ladder, leveling)\n- `\u002Fcs:decide` — log the verdict\n- `\u002Fcs:freeze 60` — on multi-year AI commitments\n\n## Related\n\n- Agent: [`cs-caio-advisor`](..\u002F..\u002Fagents\u002Fcs-caio-advisor.md)\n- Skill: [`chief-ai-officer-advisor`](..\u002F..\u002F..\u002Fskills\u002Fchief-ai-officer-advisor\u002FSKILL.md)\n- Adjacent: `..\u002F..\u002F..\u002Fskills\u002Fchief-data-officer-advisor\u002F` (training data rights, data strategy)\n\n---\n\n**Version:** 1.0.0\n",{"name":5,"description":7},"main","f37de8f681f0c0ca0e0ebab6e5fddf764ca7553d","skills\u002Fcaio-review",1,"https:\u002F\u002Fgithub.com\u002Fagisota\u002Fold-one","https:\u002F\u002Fagisota.github.io\u002Fold-one\u002F","https:\u002F\u002Fgithub.com\u002Fagisota","pzd.world","2026-07-04 22:32:06",{"source":8,"skillName":5,"commands":33,"prompt":43,"zipAvailable":44},[34,37,40],{"tool":35,"command":36},"npx","npx skills add agisota\u002Fold-one --skill caio-review",{"tool":38,"command":39},"bunx","bunx skills add agisota\u002Fold-one --skill caio-review",{"tool":41,"command":42},"pnpm","pnpm dlx skills add agisota\u002Fold-one --skill caio-review","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fagisota\u002Fold-one\u002Fblob\u002Fmain\u002Fskills\u002Fcaio-review\u002FSKILL.md",true,[],[47,54,61,70,77,84],{"skillNo":48,"name":49,"nameZh":6,"description":50,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":51,"categories":52,"keywords":53,"publishedAt":18},"01M75KRGZWQWE9JDBS6RX42NWV","zoom-out","Tell the agent to zoom out and give broader context or a higher-level perspective. Use when you're unfamiliar with a section of code or need to understand how it fits into the bigger picture.","https:\u002F\u002Fgithub.com\u002Fagisota\u002Fold-one\u002Fblob\u002Fmain\u002Fskills\u002Fzoom-out\u002FSKILL.md",[],[],{"skillNo":55,"name":56,"nameZh":6,"description":57,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":58,"categories":59,"keywords":60,"publishedAt":18},"01M75KRCZHKE0ZYAQFFYHS0YNP","zeroize-audit","Detects missing zeroization of sensitive data in source code and identifies zeroization removed by compiler optimizations, with assembly-level analysis, and control-flow verification. Use for auditing C\u002FC++\u002FRust code handling secrets, keys, passwords, or other sensitive data.","https:\u002F\u002Fgithub.com\u002Fagisota\u002Fold-one\u002Fblob\u002Fmain\u002Fskills\u002Fzeroize-audit\u002FSKILL.md",[],[],{"skillNo":62,"name":63,"nameZh":6,"description":64,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":65,"licenseFileUrl":66,"sourceHtmlUrl":67,"categories":68,"keywords":69,"publishedAt":18},"01M75KR94KYQ30DTE1P9WNDAE0","yeet","Use only when the user explicitly asks to stage, commit, push, and open a GitHub pull request in one flow using the GitHub CLI (`gh`).","Apache-2.0","https:\u002F\u002Fgithub.com\u002Fagisota\u002Fold-one\u002Fblob\u002Fmain\u002Fskills\u002Fyeet\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fagisota\u002Fold-one\u002Fblob\u002Fmain\u002Fskills\u002Fyeet\u002FSKILL.md",[],[],{"skillNo":71,"name":72,"nameZh":6,"description":73,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":74,"categories":75,"keywords":76,"publishedAt":18},"01M75KR3H13YJ9QHMD49818FA1","yara-rule-authoring","Guides authoring of high-quality YARA-X detection rules for malware identification. Use when writing, reviewing, or optimizing YARA rules. Covers naming conventions, string selection, performance optimization, migration from legacy YARA, and false positive reduction. Triggers on: YARA, YARA-X, malware detection, threat hunting, IOC, signature, crx module, dex module.","https:\u002F\u002Fgithub.com\u002Fagisota\u002Fold-one\u002Fblob\u002Fmain\u002Fskills\u002Fyara-rule-authoring\u002FSKILL.md",[],[],{"skillNo":78,"name":79,"nameZh":6,"description":80,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":81,"categories":82,"keywords":83,"publishedAt":18},"01M75KQMPY8A4Y8XTDD2DT0M9T","x-twitter-growth","X\u002FTwitter growth engine for building audience, crafting viral content, and analyzing engagement. Use when the user wants to grow on X\u002FTwitter, write tweets or threads, analyze their X profile, research competitors on X, plan a posting strategy, or optimize engagement. Complements social-content (generic multi-platform) with X-specific depth: algorithm mechanics, thread engineering, reply strategy, profile optimization, and competitive intelligence via web search.","https:\u002F\u002Fgithub.com\u002Fagisota\u002Fold-one\u002Fblob\u002Fmain\u002Fskills\u002Fx-twitter-growth\u002FSKILL.md",[],[],{"skillNo":85,"name":86,"nameZh":6,"description":87,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":88,"categories":89,"keywords":90,"publishedAt":18},"01M75KQHNZ0ANZNJGZY6M8MDAK","x-api","X\u002FTwitter API integration for posting tweets, threads, reading timelines, search, and analytics. Covers OAuth auth patterns, rate limits, and platform-native content posting. Use when the user wants to interact with X programmatically.","https:\u002F\u002Fgithub.com\u002Fagisota\u002Fold-one\u002Fblob\u002Fmain\u002Fskills\u002Fx-api\u002FSKILL.md",[],[]]