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.

1.28x

Quality

67%

Does it follow best practices?

Impact

86%

1.28x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./tests/ext_conformance/artifacts/agents-wshobson/developer-essentials/skills/code-review-excellence/SKILL.md

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

Quality

Content

56%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 content is well-structured with concrete examples, checklists, and a clear phased workflow, making it actionable and easy to follow. Its weaknesses are verbosity from re-teaching basic programming concepts Claude already knows, and progressive-disclosure problems where referenced bundle files are missing and large reference-grade content is inlined.

Suggestions

Move the language-specific patterns and the full security/performance/testing checklists into the referenced bundle files (references/common-bugs-checklist.md, references/security-review-guide.md) and keep only brief pointers inline, which also requires actually creating those files.

Trim or remove sections that re-teach knowledge Claude already has (mutable defaults, bare except, 'any' types, emoji/rapport advice) to recover token budget.

Either create the advertised bundle files (references/*, assets/*, scripts/pr-analyzer.py) or remove their references from the Resources section so signaled paths are real.

Dimension	Reasoning	Score
Conciseness	The ~530-line body extensively explains concepts Claude already knows (basic Python mutable-default and bare-except pitfalls, TypeScript 'any' avoidance, generic praise/emoji advice), and re-teaches review fundamentals, which is noticeably verbose with several padded sections rather than lean.	2 / 5
Actionability	It provides concrete bad/good code snippets, severity labels, checklists, and a copy-paste PR review comment template, giving mostly executable guidance with only minor gaps (the referenced pr-analyzer.py tool does not actually exist).	4 / 5
Workflow Clarity	The Review Process is a clearly sequenced four-phase workflow with time budgets and a final decision step; it has minor validation gaps (no explicit 'confirm understanding with author' checkpoint) but is well-structured overall.	4 / 5
Progressive Disclosure	There is section structure and a clearly listed Resources section, but large blocks that belong in separate files (language-specific patterns, the full security checklist) are inlined, and the referenced bundle files (references/, assets/, scripts/) do not actually exist on disk.	3 / 5
	Total	13 / 20 Passed

Description

78%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 clearly and explicitly covers both capability and trigger conditions with natural, distinct language, making it strong on completeness and trigger quality. Its main weakness is that the stated actions are aspirational behavioral goals rather than concrete technical operations.

Suggestions

Tighten specificity by stating concrete technical actions (e.g., 'analyze diffs, flag security/performance issues, suggest refactors') instead of soft goals like 'foster knowledge sharing' or 'maintain team morale'.

Add common synonyms such as 'PR', 'diff', or 'code changes' to broaden trigger-term coverage for natural phrasings users actually say.

Dimension	Reasoning	Score
Specificity	The description names the code-review domain and several actions ('provide constructive feedback, catch bugs early, and foster knowledge sharing'), but these are soft behavioral goals rather than concrete technical operations, so it sits at the '1-2 concrete actions, not comprehensive' anchor rather than the 4-anchor's specific technical actions.	3 / 5
Completeness	It explicitly answers both 'what' ('Master effective code review practices to provide constructive feedback, catch bugs early...') and 'when' ('Use when reviewing pull requests, establishing review standards, or mentoring developers') with concrete trigger phrases, matching the top anchor.	5 / 5
Trigger Term Quality	It includes natural terms users would say ('reviewing pull requests', 'code review', 'establishing review standards', 'mentoring developers') with good coverage, missing only a few common synonyms like 'PR', 'diff', or 'code changes'.	4 / 5
Distinctiveness Conflict Risk	Code review is a clear niche with distinct triggers, but the broadening phrases ('mentoring developers', 'foster knowledge sharing', 'maintaining team morale') create minor overlap with general collaboration or mentoring skills.	4 / 5
	Total	16 / 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
skill_md_line_count	SKILL.md is long (539 lines); consider splitting into references/ and linking	Warning
referenced_paths_exist	Referenced path issues: 6 missing	Warning

	Total	14 / 16 Passed

Repository: Dicklesworthstone/pi_agent_rust
Path: tests/ext_conformance/artifacts/agents-wshobson/developer-essentials/skills/code-review-excellence/SKILL.md
Commit: 6453c0b

Reviewed: about 9 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.