code-review

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

Quality

56%

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

71%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 concise and well-structured for a simple instruction-style skill, with clear focus areas and a defined output format. Its main weakness is actionability: it tells Claude what categories to check but not how to check them with specific techniques or examples.

Suggestions

Add 1-2 concrete techniques or example commands per focus area (e.g., for Security: 'grep for eval/exec, check auth middleware scopes').

Include a small worked example of the output format showing a sample issue categorized by severity with a suggested fix.

Trim the framing opener 'You are an expert code reviewer. When this skill is activated, you should:' to save tokens.

Dimension	Reasoning	Score
Conciseness	The body is a lean, well-organized set of bullet lists with no padding or explanation of concepts Claude already knows; the only minor slack is the framing opener 'You are an expert code reviewer. When this skill is activated, you should:', placing it just below the maximally tight anchor 5.	4 / 5
Actionability	The checklist names concrete review targets (input validation, OWASP Top 10, DRY, query optimization) and a clear output format (Summary, Issues by severity, Suggestions with code examples, Positive Aspects), but it gives no specific techniques, commands, or worked examples for performing each check; anchor 3 (concrete guidance but incomplete) fits better than 4 (mostly executable).	3 / 5
Workflow Clarity	As a simple single-purpose skill, the sequence — review the listed focus areas, then produce the structured output — is clear and unambiguous with no destructive/batch operation requiring validation; it does not reach 5 because there is no explicit step sequencing or checkpoint beyond listing categories then the output format.	4 / 5
Progressive Disclosure	The skill is under 50 lines, needs no external references, and is organized into clear sections (Review Focus Areas, Review Output Format, Usage), meeting the rubric's simple-skill exception for a top score on progressive disclosure.	5 / 5
	Total	16 / 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 states a clear purpose and domain but is missing an explicit 'Use when' trigger clause and relies on abstract verbs rather than concrete actions, capping completeness and trigger quality. It is serviceable but generic for a skill description.

Suggestions

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

Replace abstract verbs with concrete actions: 'reviews code for readability, flags security vulnerabilities, and suggests targeted improvements'.

Include natural synonyms and trigger terms users actually say ('review my code', 'code review', 'audit this code').

Dimension	Reasoning	Score
Specificity	Quotes 'analyzes code quality, security, and best practices' name the domain and several categories, but the actions ('analyzes') are abstract rather than concrete operations like 'flags vulnerabilities' or 'suggests fixes'; fits anchor 3 (clear domain, generic actions) better than 2 (minimal actions) or 4 (several specific actions).	3 / 5
Completeness	A clear 'what' is present ('analyzes code quality, security, and best practices') but there is no 'Use when...' or equivalent trigger clause, which per the rubric caps completeness at 3; it does not reach 4 because the 'when' is entirely absent rather than weakly implied.	3 / 5
Trigger Term Quality	The phrase 'code review assistant' supplies one relevant term but the description lacks natural trigger phrases a user would say ('review my code', 'audit this code'); anchor 2 (one or two generic keywords, missing natural phrases) is the best fit, below 3 (some relevant keywords with variations).	2 / 5
Distinctiveness Conflict Risk	'code review' denotes a recognizable niche but the broad phrasing ('code quality, security, and best practices') could overlap with general review or security-audit skills; anchor 3 (somewhat specific but overlap risk) fits better than 4 (mostly distinct).	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
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: fa769d4

Reviewed: 2 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.