Name: caio-review
Rating: 67.2 (1 reviews)
Author: alirezarezvani

caio-review

/cs:caio-review <plan> — Eval-demanding Chief AI Officer interrogation of any plan that involves AI: model selection, risk classification, cost economics, or AI hiring. Use when shipping an AI feature without an eval set, choosing between API, fine-tune, and self-hosted, or classifying a use case under the EU AI Act.

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

The canonical home for this skill is caio-review in alirezarezvani/claude-skills

Quality

Content

75%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured, mostly executable CAIO review skill with a clear six-question checklist, concrete tool commands, and a copy-paste verdict template. Main weakness is reliance on external unbundled scripts and absent inter-step validation of tool output.

Suggestions

Bundle or vendor the referenced scripts (model_buildvsbuy_calculator.py, ai_risk_classifier.py, ai_cost_economics.py) locally under scripts/ so the workflow commands are executable without a sibling skill, or add a note confirming the external dependency and how to obtain it.

Add an explicit validation/verification step in the Workflow between tool runs (e.g. 'Confirm each script exited 0 and produced a JSON result before proceeding to the verdict').

Tighten editorial asides such as "you have a feature; you have a vibe" to keep the bullet guidance purely instructional and further improve token efficiency.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean bullet-driven guidance that assumes Claude's competence, with only minor editorial flair (e.g. "you have a vibe") that could be trimmed.	4 / 5
Actionability	Workflow gives concrete runnable commands and the Output Format is a copy-paste template, but those commands depend on external sibling-skill scripts (../../../c-level-advisor/...) not bundled here, a real executable gap.	4 / 5
Workflow Clarity	Six sequenced questions plus a three-step tool workflow and a SHIP/SHARPEN/BLOCK verdict gate give a clear sequence; the skill is read-only analysis so the destructive-cap does not apply, but no explicit tool-output validation sits between steps.	4 / 5
Progressive Disclosure	Well-organized into clearly labeled sections with one-level-deep, clearly signaled external references (Routing, Related); over 50 lines and the referenced tool scripts live in a sibling skill rather than a local bundle, a minor organization gap.	4 / 5
	Total	16 / 20 Passed

Description

87%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description that explicitly answers both what it does and when to invoke it with concrete, natural trigger phrases and a distinctive CAIO niche. Minor room for improvement only in breadth of synonyms and action verbs.

Dimension	Reasoning	Score
Specificity	Names the domain and enumerates four concrete decision areas — "model selection, risk classification, cost economics, or AI hiring" — but the single core action ("interrogation") leaves minor coverage gaps versus the fully comprehensive 5-anchor.	4 / 5
Completeness	Clearly states the "what" (CAIO interrogation covering four AI decision areas) and an explicit "Use when..." clause with concrete triggers, matching the top anchor for both what and when.	5 / 5
Trigger Term Quality	Natural trigger phrases like "shipping an AI feature without an eval set", "fine-tune", and "EU AI Act" give good keyword coverage, though common synonyms (LLM, generative AI, GPT) are absent.	4 / 5
Distinctiveness Conflict Risk	It carves a clear CAIO niche with distinct triggers (EU AI Act, eval sets, fine-tune vs build) and minimal overlap with other review skills.	5 / 5
	Total	18 / 20 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 2 suspicious	Warning

	Total	15 / 16 Passed

Repository: alirezarezvani/claude-skills
Path: .gemini/skills/caio-review/SKILL.md
Commit: 19392f7

Reviewed: 4 minutes ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.