code-review-general

General code review process: priority ordering, what to block on, how to give actionable feedback

Quality

58%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./skills/code-review-general/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 identifies its domain (code review) and lists a few high-level aspects it covers, but remains too abstract and lacks explicit trigger guidance. It reads more like a topic summary than a skill selection description, missing the 'Use when...' clause and natural user-facing trigger terms that would help Claude reliably select it.

Suggestions

Add an explicit 'Use when...' clause, e.g., 'Use when the user asks for help reviewing code, giving PR feedback, or prioritizing review comments.'

Include natural trigger terms users would say, such as 'PR review', 'pull request', 'code feedback', 'review comments', 'code critique'.

Make the actions more concrete, e.g., 'Guides priority ordering of review findings (security > correctness > style), identifies blocking vs. non-blocking issues, and formats review comments with specific fix suggestions.'

Dimension	Reasoning	Score
Specificity	Names the domain (code review) and some actions (priority ordering, blocking decisions, giving actionable feedback), but these are somewhat abstract rather than concrete specific actions like 'flag security vulnerabilities' or 'suggest refactoring patterns'.	2 / 3
Completeness	Describes what the skill covers (code review process elements) but completely lacks any 'Use when...' clause or explicit trigger guidance for when Claude should select this skill. Per rubric guidelines, a missing 'Use when...' clause caps completeness at 2, and the 'what' is also only moderately clear, warranting a 1.	1 / 3
Trigger Term Quality	Includes 'code review' which is a natural trigger term, and 'actionable feedback' is relevant. However, it misses common variations like 'PR review', 'pull request', 'review comments', 'code feedback', or 'review checklist'.	2 / 3
Distinctiveness Conflict Risk	The 'code review process' framing is somewhat specific but could overlap with skills about coding standards, linting, PR workflows, or general feedback-giving skills. The lack of explicit scope boundaries increases conflict risk.	2 / 3
	Total	7 / 12 Passed

Implementation

85%

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, concise code review skill that efficiently communicates priority ordering, blocking criteria, and tone guidelines. Its main weakness is the lack of a concrete example showing a sample review comment (quoting a line, explaining the problem, offering an alternative), which would elevate actionability. Overall it's a strong instruction-only skill that respects Claude's intelligence.

Suggestions

Add one concrete example in the Tone section showing a sample review comment: a code snippet, the problem identified, and the suggested fix — this would demonstrate the 'quote the line, explain the problem, offer an alternative' pattern.

Dimension	Reasoning	Score
Conciseness	Every line earns its place. No unnecessary explanations of what code review is or why it matters — it jumps straight into prioritized, actionable guidance. The categorization (Red Flags, Structural Issues, Suggestions) is tight and avoids redundancy.	3 / 3
Actionability	The guidance is specific and concrete (e.g., 'hardcoded secrets', 'silent exception swallowing'), but it lacks concrete examples of review comments — showing a before/after code snippet with a sample review comment would make it fully actionable. The Tone section says 'quote the specific line' and 'offer a concrete alternative' but doesn't demonstrate this with an example.	2 / 3
Workflow Clarity	The priority ordering (1-5) provides a clear sequence for conducting reviews. The three-tier severity system (must fix / should fix / consider) with clear categorization of what belongs in each tier gives an unambiguous workflow. For a non-destructive instruction skill, this level of clarity is sufficient without explicit validation checkpoints.	3 / 3
Progressive Disclosure	For a concise, single-purpose skill under 50 lines with no need for external references, the content is well-organized into clearly labeled sections with logical progression. The reference to a security skill checklist is a clean one-level-deep pointer.	3 / 3
	Total	11 / 12 Passed

Validation

100%

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 — 11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository: ucdavis/ai-skills-registry
Commit: c0b2e4b

Reviewed: about 14 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.