CtrlK
BlogDocsLog inGet started
Tessl Logo

code-review

How to review code; a pull request, feature branch, local changes etc.

83

1.14x
Quality

73%

Does it follow best practices?

Impact

100%

1.14x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/code-review/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

86%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 is an efficient, well-organized instruction skill that gives Claude clear focus areas and a concrete glossary invocation, with no padding. It could push actionability higher by adding brief examples of how to phrase constructive feedback.

Suggestions

Add one short example of constructive vs. unhelpful feedback phrasing to make the "be constructive" directive more actionable.

Lightly sequence the bullet list into a suggested review order (e.g., correctness first, then performance, then style) to clarify the workflow.

Optionally note how to prioritize or triage findings by severity so Claude knows what to surface first.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence — it lists review focus areas without explaining what code quality or security mean, and every line earns its place.

5 / 5

Actionability

Concrete directives like invoking the glossary via the Skill tool and consulting CLAUDE.md give actionable guidance, though the feedback categories themselves remain somewhat abstract without examples of how to phrase feedback.

4 / 5

Workflow Clarity

The single action (provide structured review feedback) is clear and the focus areas are listed, but the bullets are not sequenced into a prioritized review process with explicit checkpoints.

4 / 5

Progressive Disclosure

As a short, single-purpose skill under 50 lines with no need for external references, its well-organized intro, bullet list, and closing notes are appropriately structured for its size.

5 / 5

Total

18

/

20

Passed

Description

61%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 names a clear domain and a few concrete review targets with natural trigger terms, but it lacks an explicit "Use when..." clause and specific review actions. It is distinct but could be sharper on triggers and specificity.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user asks to review a PR, feature branch, or local changes."

Replace the generic verb "review" with concrete actions such as "analyzes diffs, flags bugs, and suggests improvements".

Include common synonyms users say, like "PR", "diff", or "code review", to broaden trigger coverage.

DimensionReasoningScore

Specificity

The phrase "review code; a pull request, feature branch, local changes" names the domain and several concrete review objects, but the action itself stays generic ("review") rather than enumerating specific actions.

3 / 5

Completeness

It states clearly what the skill does ("How to review code") and implies the when via the listed objects, but there is no explicit "Use when..." trigger clause, which caps completeness at 3.

3 / 5

Trigger Term Quality

"pull request", "feature branch", and "local changes" are natural phrases users would say, though common synonyms like "PR", "diff", or "code review" are missing.

4 / 5

Distinctiveness Conflict Risk

"review code" carves out a clear niche distinct from authoring skills, with only minor overlap risk against linting or formatting skills.

4 / 5

Total

14

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
MetaMask/ocap-kernel
Reviewed

Table of Contents

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.