code-review-excellence

Master effective code review practices to provide constructive feedback, catch bugs early, and foster knowledge sharing while maintaining team morale. Use when reviewing pull requests, establishing review standards, or mentoring developers.

1.25x

Quality

73%

Does it follow best practices?

Impact

85%

1.25x

Average score across 6 eval scenarios

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/code-review-excellence/SKILL.md

The canonical home for this skill is code-review-excellence in wshobson/agents

Quality

Content

62%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 delivers a clear, actionable review workflow with excellent sequencing, checklists, and templates, but it is a verbose monolith that spends many lines on programming pitfalls and review fundamentals Claude already knows. Splitting reference material into bundle files would address both the conciseness and progressive-disclosure weaknesses.

Suggestions

Move the Language-Specific Patterns (Python/TypeScript pitfalls), security checklists, and the PR review comment template into separate files under references/ with clearly signaled one-level-deep links from SKILL.md.

Cut sections that restate well-known knowledge — the Goals/Not-the-Goals lists, mutable default arguments, `any` avoidance, and prop mutation examples — down to terse reminders or drop them, since Claude already knows these pitfalls.

Trim generic best-practice lines (e.g., "Build Rapport: Emoji, praise, and empathy matter") and consolidate the overlapping checklists (Review Scope vs. Technique 1 vs. Pattern 3) into a single reference checklist to reduce token cost.

Dimension	Reasoning	Score
Conciseness	Several sections restate knowledge Claude already has — "Goals of Code Review" lists, mutable default arguments, avoiding `any`, prop mutation, and generic "Good Feedback is: Specific and actionable..." definitions — making the body noticeably verbose with several padded sections rather than only some unnecessary explanation (anchor 3).	2 / 5
Actionability	Concrete artifacts abound: ❌/✅ phrasing examples, a severity-label scheme, executable Python/TypeScript snippets, and a copy-paste PR review comment template, but a few platitudes ("Build Rapport: Emoji, praise, and empathy matter") leave minor gaps versus fully copy-paste-ready anchor 5.	4 / 5
Workflow Clarity	The review process is four explicitly sequenced phases with time budgets, validation checkpoints (CI/CD status, PR-size split check), an explicit decision step with three outcomes, checklists for complex processes, and a disagreement-handling feedback loop — matching anchor 5.	5 / 5
Progressive Disclosure	There are no bundle files at all and 530 lines are inlined monolithically; language-specific patterns, security checklists, and templates clearly belong in separate reference files. Header structure is good, matching anchor 3 (content that should be separate is inline) rather than anchor 2 (minimal structure), and the under-50-lines simple-skill exception does not apply.	3 / 5
	Total	14 / 20 Passed

Description

83%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.

A strong description with an explicit what-and-when structure and concrete trigger phrases. Its main weaknesses are the slightly generic opening ("Master effective code review practices") and missing common trigger variations like "PR" or "reviewing code changes".

Dimension	Reasoning	Score
Specificity	The description lists several concrete actions — "provide constructive feedback, catch bugs early, and foster knowledge sharing while maintaining team morale" — though the opening "Master effective code review practices" is slightly generic, leaving minor gaps versus the comprehensive anchor 5.	4 / 5
Completeness	It explicitly answers both what ("provide constructive feedback, catch bugs early, foster knowledge sharing while maintaining team morale") and when ("Use when reviewing pull requests, establishing review standards, or mentoring developers") with three concrete trigger phrases, matching the anchor 5 example structure exactly.	5 / 5
Trigger Term Quality	Natural phrases users would say are present ("code review", "pull requests", "review standards", "mentoring developers"), but common variations such as "PR", "reviewing code changes", or "code quality" are missing, matching the good-coverage-with-gaps anchor 4 rather than the comprehensive anchor 5.	4 / 5
Distinctiveness Conflict Risk	"Code review" is a clear niche with distinct triggers like "reviewing pull requests" and "establishing review standards", but "mentoring developers" is broad enough to overlap with a general mentoring skill, so it fits mostly-distinct anchor 4 rather than minimal-conflict anchor 5.	4 / 5
	Total	17 / 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
skill_md_line_count	SKILL.md is long (530 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: crafter-station/petdex
Path: .agents/skills/code-review-excellence/SKILL.md
Commit: 7e32703

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.