CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

code-review

Review code for quality, maintainability, and correctness

Quality

60%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

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

Quality

Content

57%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 concise and cleanly organized but offers almost nothing Claude doesn't already know: it reads as a generic checklist of questions rather than instructions for how to actually conduct a review. Concrete techniques, examples, or a sequenced review workflow would substantially raise its value.

Suggestions

Replace abstract questions with concrete guidance, e.g. how to spot injection vulnerabilities or examples of good vs. bad feedback comments.

Add a sequenced review workflow (read the diff -> trace data flow -> report findings by severity) so the skill instructs rather than merely prompts.

Include one or two example reviews or feedback phrasings that demonstrate the desired specificity and tone.

DimensionReasoningScore

Conciseness

The body is a lean checklist with no padding, but several questions ("Is the code easy to understand?", "Are there any obvious bugs?") restate review fundamentals Claude already knows, matching the 'efficient with minor trimming possible' anchor rather than fully lean.

4 / 5

Actionability

Guidance is abstract throughout ("Are there any injection vulnerabilities?", "Is user input validated?") with no concrete commands, examples, or specific techniques; the categorized checklist and feedback section provide high-level hints but not executable steps, matching anchor 2.

2 / 5

Workflow Clarity

Checklist items are listed and grouped by category with an implicit review-then-feedback flow, but the review process itself has no sequence and no validation checkpoints, matching the 'steps listed but checkpoints missing' anchor.

3 / 5

Progressive Disclosure

The skill is under 50 lines, well-organized into clear ## and ### sections, and needs no external references; per the rubric's simple-skill guideline this earns a 5 with well-organized sections alone.

5 / 5

Total

14

/

20

Passed

Description

45%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 is serviceable but generic: it states a clear domain and focus areas yet offers no trigger guidance and no concrete actions. Adding a 'Use when...' clause with natural trigger phrases (e.g. reviewing a PR, diff, or staged changes) would address its main gaps.

Suggestions

Add an explicit 'Use when...' clause, e.g. "Use when reviewing code, pull requests, diffs, or when the user mentions code quality or maintainability."

Replace abstract attributes with one or two concrete actions, such as "Reviews code changes and diffs for bugs, maintainability issues, and security risks".

Include natural trigger variations users actually say (PR review, diff, code quality, lint feedback) to improve trigger term coverage.

DimensionReasoningScore

Specificity

"Review code for quality, maintainability, and correctness" names the domain but the action is generic ("Review code") and the three focus areas are abstract attributes, matching anchor 2 ('names the domain but actions are minimal or generic'); it lacks concrete actions like analyzing diffs or checking for injection flaws, so it is not a 3.

2 / 5

Completeness

The description gives a clear 'what' but no 'when' guidance at all, which per the judging guidelines caps completeness at 3; this exactly matches anchor 3 ('has a clear what but when is missing or only weakly implied').

3 / 5

Trigger Term Quality

"code", "review", and "quality" are natural user terms, but common variations such as "PR", "diff", "pull request", or "lint" are missing, matching anchor 3 ('some relevant keywords but missing common variations or synonyms'); coverage is too thin for a 4.

3 / 5

Distinctiveness Conflict Risk

"Review code for quality, maintainability, and correctness" is domain-limited but broad enough to overlap with linting, security-review, and refactoring skills, matching anchor 3 ('somewhat specific but could still overlap with similar skills'); it is not entirely generic (rule out 2) but has no distinct niche triggers (rule out 4).

3 / 5

Total

11

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository

PrefectHQ/fastmcp

Path

examples/skills/sample_skills/code-review/SKILL.md

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.