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

38%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 body is a monolithic dump of domain knowledge, illustrative code, and dated model recommendations, padded with concepts Claude already knows. It does contain a usable workflow skeleton and some executable snippets, but the only reference points to a nonexistent file and no validation feedback loops are defined. Splitting into reference files with verified paths and cutting the background material would substantially improve it.

Suggestions

Trim background knowledge Claude already has (OWASP Top 10 list, SOLID definitions, N+1 explanation) and remove the duplicated frontmatter-description opening paragraph.

Replace pseudocode examples (ReviewRoutingStrategy, MicroserviceReviewChecklist) with either fully executable code or concise bullet guidance, and fix the Python orchestrator's undefined methods (get_pr_diff, to_github_comment).

Actually create the referenced bundle file (or fix the path) and move the architecture, security, and performance sections into one-level-deep reference files linked from a concise SKILL.md overview.

Add explicit validation/feedback steps for batch comment posting and for what to do when the quality gate fails or a PR is routed to human review.

Dimension	Reasoning	Score
Conciseness	The ~450-line body extensively restates knowledge Claude already has (the full OWASP Top 10 list, SOLID principles, N+1 query definitions), duplicates the frontmatter description as the opening paragraph, and embeds time-sensitive model/version lists ('Model Selection (2025)', 'claude-3.7-sonnet', 'GPT-5') outside any deprecated-section framing. This matches 'noticeably verbose; several unnecessary explanations or padded sections'.	2 / 5
Actionability	There is real concrete material (the GitHub Actions YAML, the trufflehog/jq pipeline, the Python orchestrator), but the orchestrator calls undefined methods (get_pr_diff, issue.to_github_comment) and the ReviewRoutingStrategy and Go checklist examples are illustrative pseudocode rather than executable code — 'some concrete guidance but incomplete'.	3 / 5
Workflow Clarity	A sequence is present (Initial Triage -> Multi-Tool Static Analysis -> AI-Assisted Review -> Comment Generation -> CI/CD) and the CI Quality Gate is one checkpoint, but there are no validate-fix-retry feedback loops for the batch operation of posting review comments, nor guidance for what to do when routing returns HumanReviewRequired or static analysis fails. This fits 'steps listed but validation gaps'.	3 / 5
Progressive Disclosure	The skill is a monolithic single file with no bundle directories (references/, scripts/, assets/ all absent); the sole reference, 'resources/implementation-playbook.md', does not exist, and hundreds of lines of architecture, security, and performance detail that clearly belong in separate reference files are inlined. This matches 'minimal structure; content that clearly belongs in separate files is inlined'.	2 / 5
	Total	10 / 20 Passed

Description

36%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 truncated mid-sentence, written in second person, and leans on buzzwords rather than concrete capabilities. It identifies a plausible niche (AI-assisted code review) but omits any 'when to use' trigger guidance and natural trigger phrases. A rewrite in third person with concrete actions and explicit use-when triggers would move it up two levels.

Suggestions

Complete the truncated description and rewrite it in third person with concrete actions (e.g., 'Runs multi-tool static analysis (CodeQL, Semgrep, SonarQube) and AI-assisted review of pull requests, and posts structured severity-rated comments').

Add an explicit trigger clause, e.g., 'Use when reviewing a pull request, scanning a diff for bugs or vulnerabilities, or setting up automated code review in CI.'

Cut buzzwords like 'intelligent pattern recognition' and 'modern DevOps practices' in favor of natural user phrases such as 'code review', 'PR review', and 'security scan'.

Dimension	Reasoning	Score
Specificity	The description names the domain and tools ('automated static analysis', 'GitHub Copilot, Qodo, GPT-5') but actions are buzzword-level ('intelligent pattern recognition') and the text is truncated mid-sentence at 'C'. It is written in second person ('You are an expert...', 'Leverage AI tools'), which reduces the base score of 3 by 1 per the judging guidelines.	2 / 5
Completeness	The 'what' is vague and buzzwordy ('combining automated static analysis, intelligent pattern recognition, and modern DevOps practices') and cut off mid-list, and there is no 'Use when...' clause or equivalent trigger guidance. This fits the 'vague what and no when' anchor rather than anchor 3, whose 'what' is a clear list of concrete actions.	2 / 5
Trigger Term Quality	'code review' and 'static analysis' are natural phrases a user might say, but common variations like 'pull request', 'PR review', 'lint', or 'vulnerability scan' are absent, matching the 'some relevant keywords but missing common variations' anchor.	3 / 5
Distinctiveness Conflict Risk	'AI-powered code review specialist' identifies a niche, but the broad framing around 'modern DevOps practices' and generic static analysis creates overlap risk with existing code-review and linting skills, matching 'somewhat specific but could still overlap'.	3 / 5
	Total	10 / 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: 7b534bc

Reviewed: 5 days 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.