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

37%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

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

Quality

Content

45%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 content is rich with executable multi-language examples but is severely over-long, front-loads general knowledge Claude already has, and bundles everything into one monolithic file with no real progressive disclosure. The workflow is sequenced but lacks explicit validation checkpoints for a merge-blocking operation.

Suggestions

Move the bulk into separate bundle files (e.g. references/security-checklist.md, references/model-selection.md, scripts/code_review_orchestrator.py) and keep SKILL.md as a concise overview with one-level-deep links, as no references/ or scripts/ bundle currently exists.

Cut general knowledge padding — SOLID principles, the OWASP Top 10 enumeration, and tool-list catalogs — since Claude already knows these; keep only the skill-specific orchestration and routing logic.

Add explicit validation/feedback-loop steps to the workflow (e.g. 'Verify static-analysis results parsed before AI review', 'Re-validate after fixes', 'Confirm quality gate passed before approving') given this is a merge-blocking operation.

Dimension	Reasoning	Score
Conciseness	The body runs ~450 lines and largely catalogues tool lists, model tiers, OWASP entries, and lengthy code scaffolding that Claude already knows (e.g. enumerating SOLID principles, OWASP Top 10, secret-scanning jq pipes), which is noticeable padding rather than lean skill-specific guidance.	2 / 5
Actionability	It provides mostly executable, copy-paste-ready examples across Python/TypeScript/Go/YAML/Bash (orchestrator, routing, review-comment schema, GitHub Actions workflow), with only minor gaps such as placeholder engine classes and missing implementations.	4 / 5
Workflow Clarity	A sequence exists (Initial Triage → Static Analysis → AI Review → Post Comments → Quality Gate) and the example does post comments and gate on critical issues, but there are no explicit validation checkpoints or feedback loops between static analysis and AI review, and for an operation that blocks merges the verification is only an implicit count check.	3 / 5
Progressive Disclosure	It is a monolithic single-file dump: no references/, scripts/, or assets/ bundle exists, yet the body inlines large reference-style content (full OWASP list, model-selection table, complete orchestrator script) that should live in separate files; the one in-body pointer ('open resources/implementation-playbook.md') targets a file that does not exist, so references are effectively absent.	2 / 5
	Total	11 / 20 Passed

Description

30%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 is a verbose role-statement that names the domain and tools but omits a 'Use when...' trigger clause and is truncated mid-sentence, undermining both completeness and specificity. It reads more like a persona preamble than a tight capability+trigger description.

Suggestions

Rewrite as a third-person capability statement with concrete actions (e.g. 'Reviews pull requests for bugs, security vulnerabilities, and performance regressions by combining static analysis tools with LLM reasoning'), then add an explicit trigger: 'Use when the user asks to review a diff, PR, or code change.'

Remove the truncated tail and the first-person/second-person framing ('You are...', 'Leverage AI tools...') in favor of third-person voice per the rubric.

Replace generic jargon ('intelligent pattern recognition', 'modern DevOps practices') with the natural terms a user would actually say ('code review', 'PR review', 'find security issues in my code').

Dimension	Reasoning	Score
Specificity	Names the domain (code review) and references specific tools, but the actions are generic ('combining automated static analysis, intelligent pattern recognition') rather than concrete skills a user would invoke, and the description is truncated mid-sentence so coverage is incomplete.	2 / 5
Completeness	A partial 'what' is present but there is no 'Use when...' trigger clause at all, capping completeness at 3; combined with the description being cut off mid-word ('GPT-5, C'), the 'what' itself is incomplete, pulling it below the midpoint to 2.	2 / 5
Trigger Term Quality	It relies on technical jargon ('static analysis', 'pattern recognition', 'DevOps practices') and product names rather than the natural phrases a user would say ('review my PR', 'find bugs in this diff', 'check my code'); there is no user-voiced trigger.	2 / 5
Distinctiveness Conflict Risk	The code-review niche is reasonably specific and tooling-named, so it is distinguishable from unrelated skills, but 'AI-powered code review' overlaps heavily with built-in/general code-review capabilities and similar skills, leaving moderate conflict risk.	3 / 5
	Total	9 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	14 / 16 Passed

Repository: sickn33/agentic-awesome-skills
Path: skills/code-review-ai-ai-review/SKILL.md
Commit: b1aebac

Reviewed: ~17 hours 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.