code-review

Review code changes between commits for security, logic, performance, and style issues

Quality

55%

Does it follow best practices?

Impact

Pending

No eval scenarios have been run

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./plugins/git-workflow/skills/code-review/SKILL.md

Quality

Discovery

32%

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 provides a reasonable overview of the skill's purpose but lacks explicit trigger guidance, which is critical for skill selection. It names relevant categories of issues but doesn't specify concrete actions or include a 'Use when...' clause to help Claude know when to activate this skill over others.

Suggestions

Add a 'Use when...' clause with explicit triggers like 'Use when the user asks to review a PR, check a diff, analyze commits, or review code changes'

Include common user terms like 'PR', 'pull request', 'diff', 'git log', 'code review' to improve trigger matching

Specify concrete actions such as 'identifies security vulnerabilities, flags logic errors, suggests performance improvements, and checks style consistency'

Dimension	Reasoning	Score
Specificity	Names the domain (code review) and lists categories of issues (security, logic, performance, style), but doesn't describe concrete actions like 'identify vulnerabilities', 'suggest fixes', or 'annotate diffs'.	2 / 3
Completeness	Describes what the skill does but completely lacks a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill.	1 / 3
Trigger Term Quality	Includes relevant terms like 'code changes', 'commits', 'review', but misses common variations users might say like 'PR review', 'pull request', 'diff', 'code review', or 'git diff'.	2 / 3
Distinctiveness Conflict Risk	The focus on 'commits' and 'code changes' provides some distinction, but 'security, logic, performance, and style issues' could overlap with general code review or linting skills.	2 / 3
	Total	7 / 12 Passed

Implementation

77%

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

This is a well-structured, actionable skill with clear workflow steps and good error handling. The main weakness is verbosity - the execution instructions section largely duplicates what's already conveyed in the examples and could be condensed or moved to a separate reference file. The categorized review criteria and output format template are particularly strong.

Suggestions

Move the detailed 'Execution Instructions for Claude Code' section to a separate IMPLEMENTATION.md file, keeping only a brief reference in the main skill

Condense the argument parsing section - Claude can infer the logic from the examples without explicit pseudocode

Dimension	Reasoning	Score
Conciseness	The skill is reasonably efficient but includes some redundancy - the execution instructions repeat information already covered in the examples and arguments sections. The detailed step-by-step bash commands could be more condensed since Claude knows git operations.	2 / 3
Actionability	Provides fully executable bash commands, concrete git operations, specific output format templates, and clear examples. The Task tool delegation syntax is copy-paste ready with exact parameter names.	3 / 3
Workflow Clarity	Clear 6-step numbered sequence with explicit validation (step 2 verifies commits exist), categorized analysis priorities, and defined output format. Error handling section provides recovery guidance for common failures.	3 / 3
Progressive Disclosure	Content is well-organized with clear sections and tables, but everything is inline in one file. The detailed execution instructions could be split to a separate reference file, keeping SKILL.md as a concise overview with the usage examples.	2 / 3
	Total	10 / 12 Passed

Validation

90%

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 — 10 / 11 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	10 / 11 Passed

Repository: jpoutrin/product-forge
Commit: 0ebe7ae

Reviewed: 29 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.