code-review-ai-ai-review

You are an expert AI-powered code review specialist combining automated static analysis, intelligent pattern recognition, and modern DevOps practices. Leverage AI tools (GitHub Copilot, Qodo, GPT-5, C

Quality

44%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/code-review-ai-ai-review/SKILL.md

Quality

Content

46%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.

The skill is rich with executable examples and concrete tooling, but it is a monolithic, over-long document that explains concepts Claude already knows and lacks validation checkpoints in its review workflows. With no reference files to offload detail, progressive disclosure and conciseness both suffer.

Suggestions

Move the OWASP Top 10 catalog, model-selection table, and full orchestrator script into separate reference files (e.g., references/security.md, references/models.md) and link to them from SKILL.md.

Cut explanations of well-known concepts (SOLID, anti-patterns, what a PDF-style library does) and keep only domain-specific review guidance.

Add explicit validation/feedback-loop checkpoints to the review workflow (e.g., verify static-analysis results parsed, retry on rate limits, confirm quality gate before posting comments).

Dimension	Reasoning	Score
Conciseness	The ~450-line body extensively over-explains concepts Claude already knows (OWASP Top 10 lists, SOLID principles, common anti-patterns) and embeds large illustrative code blocks that pad the context, making it noticeably verbose.	2 / 5
Actionability	It provides concrete, mostly-executable code and commands across multiple languages and a complete CI/CD pipeline example, though some snippets are illustrative interfaces or require environment wiring before they run.	4 / 5
Workflow Clarity	A sequenced triage/analysis workflow is present, but it involves batch/destructive-style automated review operations with no explicit validation checkpoints or feedback loops, which caps workflow clarity at 3 per the rubric.	3 / 5
Progressive Disclosure	No bundle files exist and all content is inlined into a single monolithic SKILL.md; large reference-style material (model-selection tables, OWASP catalog, full orchestrator script) that belongs in separate files is not split out or navigable.	2 / 5
	Total	11 / 20 Passed

Description

42%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.

The description identifies a clear domain and some concrete capabilities, but it is truncated mid-sentence, lacks any 'Use when' trigger guidance, and uses second-person voice, which weakens completeness and specificity. Per rubric guidance, the missing trigger clause caps completeness at 3 and the second-person voice reduces specificity by 1.

Suggestions

Add an explicit 'Use when ...' trigger clause naming the natural phrases users would say (e.g., reviewing a pull request, finding bugs/vulnerabilities in a diff).

Repair the truncated description so it ends with a complete sentence rather than cutting off mid-word.

Rewrite in third person ('Performs AI-powered code review...') to align with the rubric's voice requirement.

Dimension	Reasoning	Score
Specificity	Names the domain (AI-powered code review) and lists a few concrete actions like static analysis and pattern recognition, but the actions are high-level and the description is truncated mid-sentence, leaving coverage incomplete.	3 / 5
Completeness	It states a 'what' (AI-powered code review combining static analysis, pattern recognition, DevOps) but provides no 'when' trigger clause, and the description is cut off mid-sentence, so the 'what' itself is incomplete.	2 / 5
Trigger Term Quality	Contains relevant terms like 'code review', 'static analysis', and tool names, but lacks the natural trigger phrases a user would actually say and has no 'Use when...' guidance; coverage of common variations is partial.	3 / 5
Distinctiveness Conflict Risk	It is anchored to a fairly specific niche (AI-powered code review with named tooling), but the broad phrasing and tool-heavy framing could overlap with other code-review or DevOps skills.	3 / 5
	Total	11 / 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
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	15 / 16 Passed

Repository: rmyndharis/antigravity-skills
Path: skills/code-review-ai-ai-review/SKILL.md
Commit: 3eff4af

Reviewed: 1 day 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.