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

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

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

Quality

Content

36%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 has reasonable section structure but is largely generic and tautological, with an empty workflow section and concrete guidance replaced by pointers to non-existent files. Actionability and workflow sequencing are the weakest dimensions.

Suggestions

Replace the empty 'Automated Code Review Workflow' with an explicit numbered sequence (triage -> run static analysis -> AI-assisted review -> route findings) with a validation/verification checkpoint.

Add concrete, executable content: example review commands for Semgrep/CodeQL, a sample structured review-comment format, and an actual checklist rather than 'Apply relevant best practices'.

Either create the referenced sub-skills/*.md and resources/implementation-playbook.md files or remove the broken links; replace the tautological 'Use this skill when' bullets with real trigger conditions.

Dimension	Reasoning	Score
Conciseness	The body is short, but it repeats the description verbatim in the opening paragraph and fills the 'Use this skill when' / 'Do not use' sections with tautological restatements of the skill name ('Working on ai-powered code review specialist tasks'), so it could be tightened meaningfully.	3 / 5
Actionability	Guidance is high-level ('Clarify goals', 'Apply relevant best practices', 'Provide actionable steps') with no executable code, commands, or concrete checklists; the only semi-concrete content is a list of analysis categories, and the referenced playbook/sub-skills files do not exist.	2 / 5
Workflow Clarity	The 'Automated Code Review Workflow' header is empty with no steps beneath it, and the 'Instructions' steps are generic and unordered with no validation checkpoints; only a rough analyze-then-comment sequence is implied.	2 / 5
Progressive Disclosure	The 13 named sub-skill links are well-signaled one-level-deep references in concept, but the referenced ./sub-skills/*.md and resources/implementation-playbook.md files do not exist, so the navigation structure is broken rather than genuinely progressive.	3 / 5
	Total	10 / 20 Passed

Description

53%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 conveys a clear domain and specific tooling but is truncated mid-sentence and lacks any explicit 'when to use' trigger, capping completeness. Second-person voice and missing natural trigger phrases further limit the score.

Suggestions

Complete the truncated description and add an explicit trigger clause, e.g. 'Use when the user asks to review a pull request, find bugs/vulnerabilities in a diff, or run static analysis on code changes.'

Switch to third-person voice ('Reviews code...', 'Identifies...') instead of 'You are...' / 'Leverage...'.

Add natural user phrasings such as 'code review', 'PR review', 'review my diff', 'find bugs and vulnerabilities'.

Dimension	Reasoning	Score
Specificity	Names the domain (AI code review) and several specific capabilities plus concrete tools (static analysis, pattern recognition, DevOps, Copilot, Qodo, GPT-5), but the field is truncated mid-sentence ('...GPT-5, C') and lists capability categories rather than concrete review actions; reduced one point for second-person voice ('You are an expert...', 'Leverage...').	3 / 5
Completeness	It states clearly what the skill does (AI-powered code review combining analysis tools) but includes no 'Use when...' trigger clause, which caps completeness at 3 per the rubric; the truncation also leaves the 'when' entirely unaddressed.	3 / 5
Trigger Term Quality	'code review' and 'static analysis' are natural terms, but common user phrasings like 'review my PR', 'pull request review', 'find bugs in this diff', or 'security review' are absent and the truncated tail may have dropped intended keywords.	3 / 5
Distinctiveness Conflict Risk	'AI-powered code review specialist' with named static-analysis/AI tools carves a mostly distinct niche, with only minor overlap risk against a generic code-review skill.	4 / 5
	Total	13 / 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
relative_links	Relative link issues: 13 missing	Warning

	Total	14 / 16 Passed

Repository: Dokhacgiakhoa/Agent-Skills-4-Vibe-Coding-CLI
Path: .agent/skills/code-review-ai-ai-review/SKILL.md
Commit: c4a059b

Reviewed: 1 hour 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.