Claude Skill MartBrowse skillsQuick linesLearn by videoTerminal guideWhat is a Skill?
 
← Back to list

CAIO Review — AI Plan Interrogation

Pressure-tests any AI plan with six Chief AI Officer questions — evals, hallucination SLO, EU AI Act tier, build-vs-buy, cost curve, next hire — and returns a SHIP/SHARPEN/BLOCK verdict.

UtilitiesAdvanced★ 24,151⑂ 3,405AI score 7/10Last updated: Aug 9, 2026

What it does

  • Interrogates any AI-involving plan with six forcing questions: ① eval criteria and measurement, ② hallucination/error SLO plus fallback, ③ EU AI Act risk tier, ④ API vs fine-tune vs build, ⑤ 12-month cost trajectory, ⑥ which role actually unblocks the work.
  • Enforces a hard gate — no eval set, no ship — requiring 50–100 representative inputs, expected outputs or a rubric, and adversarial/format edge cases.
  • Classifies the use case as PROHIBITED / HIGH / LIMITED / MINIMAL under the EU AI Act and flags conformity-assessment obligations, timelines, and cost ranges.
  • Runs the companion Python calculators (build-vs-buy, risk classifier, cost economics) to produce 3-year TCO, breakeven volume, and migration cost.
  • Emits a fixed markdown report ending in 🟢 SHIP / 🟡 SHARPEN / 🔴 BLOCK plus three concrete next steps, with routing to CDO/CISO/CFO/GC reviews.

Who it's for

  • Founders, PMs, and eng leads about to ship an AI feature
  • Teams weighing a multi-year API or GPU commitment, or a self-hosting migration
  • Companies launching AI in the EU or in regulated domains (hiring, credit, health, education)
  • Leaders making a first AI hire and unsure about AI vs ML engineer vs research scientist

Examples

  1. "We're launching an AI resume screener in the EU" → HIGH-risk tier, conformity assessment + EU database registration, 3–12 months and $50–200K, verdict 🔴 BLOCK with a re-scoping plan.
  2. "500M tokens/month summarization — should we fine-tune?" → explains why ~80% of B2B cases stay on API, shows self-hosting breakeven, and pushes prompt caching first.
  3. "Our first AI hire will be a research scientist" → flags missing platform engineering and labeled data, recommends an AI engineer instead with a one-line rationale.

· · · Install guide · · ·

Try it now, no install

Paste this into Claude to use the skill without installing anything.

Read the instructions in this file and follow them to help me:
https://raw.githubusercontent.com/alirezarezvani/claude-skills/HEAD/.gemini/skills/caio-review/SKILL.md

What I want: (describe your task here)

If Claude can't open the link, open it yourself and paste the contents instead.

↓ If it works for you, download the ZIP below and install it. Then it runs on its own — no pasting each time.

Install in the Claude app (no terminal)
  1. Download the ZIP with the button below.
  2. In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
  3. Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
↓ Download ZIP
Install in Claude Code

Let Claude do it — paste this into Claude Code

Install the skill I found on Claude Skill Mart.
Copy the .gemini/skills/caio-review folder from the GitHub repo alirezarezvani/claude-skills into my ~/.claude/skills/caio-review/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

git clone https://github.com/alirezarezvani/claude-skills.git && mkdir -p ~/.claude/skills && cp -r claude-skills/.gemini/skills/caio-review ~/.claude/skills/ && cp -r claude-skills/skills/chief-ai-officer-advisor ~/.claude/skills/

⚠ This is a third-party skill. Check the source repository before installing.

  1. Open a terminal.
  2. Clone the repo: git clone https://github.com/alirezarezvani/claude-skills.git
  3. Create the skills folder: mkdir -p ~/.claude/skills
  4. Copy this skill: cp -r claude-skills/.gemini/skills/caio-review ~/.claude/skills/
  5. Important: also copy the companion skill that holds the calculators: cp -r claude-skills/skills/chief-ai-officer-advisor ~/.claude/skills/
  6. Verify Python is available with python3 --version (needed for the .py scripts).
  7. Restart Claude Code and ask something like "Run a CAIO review on our AI feature launch plan".
  8. If a script path fails, update the ../../../skills/... references in SKILL.md to ~/.claude/skills/chief-ai-officer-advisor/scripts/....
View source on GitHub ↗License: MIT