code-review

Comprehensive code review assistant that analyzes code quality, security, and best practices

Quality

46%

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 ./resources/skills/code-review/SKILL.md

Quality

Content

42%

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

The body is well-organized and concise but stays at the level of a topic outline, offering no concrete code, commands, or verification steps to actually perform a review. It reads more like a checklist of concerns than actionable guidance.

Suggestions

Add a concrete worked example showing a short code snippet with annotated findings (Critical/Major/Minor) in the prescribed output format.

Provide a concrete review checklist or specific commands (e.g., how to inspect a git diff, run linters) instead of abstract category lists.

Include a validation/feedback step, e.g. "after suggesting fixes, re-check that the corrected code resolves the issue".

Drop glosses of well-known terms like "DRY (Don't Repeat Yourself)" and "OWASP Top 10" since Claude already knows them.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean, listing categories rather than explaining concepts, but glosses like "DRY (Don't Repeat Yourself) principle" and "OWASP Top 10 vulnerabilities" over-explain material Claude already knows. Not 3 due to those unnecessary expansions; not 1 because it is not verbose or padded with concept introductions.	2 / 3
Actionability	The body is an abstract topic outline ("Algorithm efficiency", "Caching opportunities", "Input validation") with no concrete code, commands, checklists, or examples — it describes rather than instructs. Not 2 because there is no concrete or even pseudocode-level guidance; nothing is executable.	1 / 3
Workflow Clarity	The "Review Output Format" provides an ordered output sequence (Summary, Issues, Suggestions, Positive) but there is no review process with validation or re-check checkpoints after fixes. Not 3 because no explicit validation/feedback loop exists; not 1 because a sequence is present.	2 / 3
Progressive Disclosure	The skill is a single ~45-line file with no bundle files, organized into clear sections (Review Focus Areas, Review Output Format, Usage). Per the scoring notes, an under-50-line skill with no need for external references can score 3 with well-organized sections. Not 2 because organization is clean; not 1 because it is not a monolithic wall of text.	3 / 3
	Total	8 / 12 Passed

Description

50%

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 names a clear domain and a few facets but leans on the vague verb "analyzes" and lacks any explicit when-to-use trigger clause. It is adequate but generic, sitting at the midpoint across all dimensions.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user asks for a code review, PR review, feedback on an implementation, or a security audit."

Replace the single vague verb "analyzes" with several concrete actions such as "reviews code for readability, flags security vulnerabilities, and suggests refactors".

Include natural user phrasings ("review my code", "PR review", "security audit") to improve trigger term coverage and distinctiveness.

Dimension	Reasoning	Score
Specificity	"analyzes code quality, security, and best practices" names the domain and several aspects but relies on a single vague verb ("analyzes") and abstract "best practices" rather than listing multiple concrete actions. Not 3 because no list of specific concrete actions; not 1 because it does name the domain and some areas.	2 / 3
Completeness	It states what the skill does ("analyzes code quality, security, and best practices") but provides no "Use when..." clause or equivalent explicit trigger guidance, capping completeness at 2 per the judging guideline. Not 3 because the when is absent, not 1 because the what is present and reasonably stated.	2 / 3
Trigger Term Quality	"code review assistant" includes the natural keyword "code review" plus "security", but common variations users actually say ("PR review", "review my code", "security audit") are missing. Not 3 due to thin coverage; not 1 because it is not pure jargon and does include a relevant natural term.	2 / 3
Distinctiveness Conflict Risk	"Comprehensive code review" is a recognizable niche, but "code quality, security, and best practices" could overlap with general linting/development skills and there are no distinct explicit triggers. Not 3 due to lack of distinct triggers; not 1 because code review is a specific, non-generic niche.	2 / 3
	Total	8 / 12 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: ThinkInAIXYZ/deepchat
Path: resources/skills/code-review/SKILL.md
Commit: b8dbc89

Reviewed: about 7 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.