requesting-code-review

Use when completing tasks, implementing major features, or before merging to verify work meets requirements

1.29x

Quality

62%

Does it follow best practices?

Impact

92%

1.29x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/requesting-code-review/SKILL.md

The canonical home for this skill is jbvc/requesting-code-review

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 content is a clear, actionable playbook for requesting code review with concrete commands and a useful example. Its main weakness is progressive disclosure: it points to a code-reviewer.md template that is not present in the bundle.

Suggestions

Add the referenced code-reviewer.md template file to the bundle so the "fill template" instruction resolves.

Show the full Task-tool dispatch invocation as a copy-pasteable example rather than only describing it.

Trim the dialogue Example and merge "Integration with Workflows" into "When to Request Review" to reduce redundancy.

Dimension	Reasoning	Score
Conciseness	The body is largely lean with concrete commands and lists, though the multi-line dialogue Example and the partly redundant "Integration with Workflows" section could be trimmed.	4 / 5
Actionability	It gives executable git commands (git rev-parse) and a concrete placeholder template for dispatch, but the actual Task-tool dispatch call is described rather than shown as a complete copy-paste command.	4 / 5
Workflow Clarity	The three-step sequence (get SHAs, dispatch, act on feedback) is clear with a triage feedback step, but there is no explicit validation checkpoint before acting on review results.	4 / 5
Progressive Disclosure	Sections are well-organized and the code-reviewer.md template is referenced one level deep, but no bundle file exists and the referenced code-reviewer.md is missing, so navigation leads to a broken reference.	3 / 5
	Total	15 / 20 Passed

Description

53%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 signals when to use the skill but is vague about what it concretely does, never naming code review or subagent dispatch. It is functional but would benefit from stating the concrete action and tighter trigger terms.

Suggestions

Name the concrete action explicitly, e.g. "Dispatches a code-reviewer subagent to review your changes".

Add natural trigger phrases users actually say, such as "code review", "review my code", or "before opening a PR".

Tighten the "what" so it is distinguishable from generic verification/testing skills.

Dimension	Reasoning	Score
Specificity	The only stated action is "to verify work meets requirements", which is generic; it names the review/verification domain but provides no concrete actions like dispatching a reviewer or analyzing a diff.	2 / 5
Completeness	It has both a "what" (verify work meets requirements) and an explicit multi-part "when" (completing tasks, implementing major features, before merging), though the "what" could be more concrete.	4 / 5
Trigger Term Quality	Phrases like "completing tasks", "implementing major features", and "before merging" are relevant trigger contexts, but common natural synonyms (e.g. "code review", "review my code", "before PR") are missing.	3 / 5
Distinctiveness Conflict Risk	Anchored to task/feature/merge milestones it is somewhat specific, but "verify work meets requirements" is broad and could overlap with testing, linting, or deployment-verification skills.	3 / 5
	Total	12 / 20 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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: roman01la/skills-agents
Path: skills/requesting-code-review/SKILL.md
Commit: aa6f9d3

Reviewed: 6 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.