CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

code-quality-review

Reviews code quality, naming structures, control flow patterns, abstraction complexity, duplication, and maintainability. Use during general refactoring.

Quality

72%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

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

Quality

Content

65%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.

A concise, well-structured body whose repository-protocol section carries genuinely non-obvious specifics. The checklist half, however, stays at the level of generic directives without concrete criteria or examples, and the workflow lacks explicit checkpoints and a defined output format.

Suggestions

Add concrete thresholds or examples to the checklist (e.g., what counts as a bloated function, patterns of duplication to consolidate) so the review is executable rather than directional.

Specify the review sequence with checkpoints: what to verify before starting, how to record findings during review, and what the 'Review record' comment should contain.

Clarify how findings map to checklist categories so the posted Review record is structured and consistent.

DimensionReasoningScore

Conciseness

The ~25-line body is lean and assumes competence (e.g., "Duplication (DRY): Consolidate duplicate helper logic" explains nothing Claude already knows). It sits at anchor 4 rather than 5 because the opening line "Use this skill when auditing source files for maintainability, readability, and structural patterns" restates the frontmatter description and could be trimmed; it is above anchor 3 since there is no real padding or unnecessary explanation.

4 / 5

Actionability

The Repository Review Protocol section is concrete ("Follow `AGENTS.md` review throttling and `docs/codex-review-protocol.md`", "post one `Review record` comment on the PR", "never edit the frozen `docs/branch-review-ledger.md`"), but the core checklist is abstract direction ("Simplify nested conditionals, deeply nested loops", "Remove unused functions") with no examples, thresholds, or how-to steps. This matches anchor 3 (some concrete guidance but incomplete, missing key details) — above anchor 2 because of the specific protocol instructions, below anchor 4 because the central review guidance lacks executable detail.

3 / 5

Workflow Clarity

A rough pre/during/post sequence exists ("before starting" protocol checks → checklist review → "After a completed PR review, post one `Review record` comment"), but checkpoints are implicit: there are no exit criteria, no guidance on what to do with findings, and no structure for the review record itself. Anchor 3 (steps present but checkpoints missing or implicit) fits; it is above anchor 2 because the sequence and its boundaries are stated, and below anchor 4 because key checkpoints are absent.

3 / 5

Progressive Disclosure

The skill is under 50 lines, no bundle files (references/, scripts/, assets/) exist, and the content is well organized into a Protocol section and a two-part checklist — matching the simple-skill exception where well-organized sections alone warrant a 5. References to repo docs (AGENTS.md, docs/codex-review-protocol.md, pull-request-workflow.md) are clearly signaled and one level deep.

5 / 5

Total

15

/

20

Passed

Description

67%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.

A solid third-person description that states concrete capability facets and includes an explicit 'Use when' clause, placing it above typical descriptions. Its main weakness is a narrow trigger clause ('Use during general refactoring') that omits natural phrases like 'code review', 'code smells', or 'readability'.

Suggestions

Broaden the trigger clause, e.g., 'Use when the user asks for a code review, mentions code smells, readability, or cleanup, or during general refactoring.'

Consider naming what the review produces (e.g., findings/report) to sharpen the 'what' side of the description.

DimensionReasoningScore

Specificity

"Reviews code quality, naming structures, control flow patterns, abstraction complexity, duplication, and maintainability" names six concrete facets of the domain. It falls at anchor 4 (several specific items, minor gaps) rather than 5 because a single verb covers all facets and there are no output-side actions (e.g., what the review produces); it is well above anchor 3's '1-2 concrete actions'.

4 / 5

Completeness

It clearly answers 'what' ("Reviews code quality, naming structures, control flow patterns, abstraction complexity, duplication, and maintainability") and explicitly answers 'when' ("Use during general refactoring"). Anchor 4 fits because the 'when' clause is present but single-scoped and could be more concrete with multiple trigger phrases, which is what separates it from anchor 5; it is above anchor 3 since 'when' is explicitly stated, not merely implied.

4 / 5

Trigger Term Quality

The only explicit trigger phrase is "Use during general refactoring", plus domain nouns like "code quality" and "maintainability". This matches anchor 3 (some relevant keywords but missing common variations) — users would naturally say "code review", "code smells", "readability", or "clean up this code", none of which appear — so it does not reach anchor 4's 'good keyword coverage'.

3 / 5

Distinctiveness Conflict Risk

The quality/maintainability focus ("duplication, and maintainability") carves out a niche distinct from correctness- or security-focused review skills, and "Use during general refactoring" scopes the trigger. Minor overlap risk remains with generic code-review skills, matching anchor 4 rather than anchor 5's 'minimal conflict risk'.

4 / 5

Total

15

/

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

relative_links

Relative link issues: 1 suspicious

Warning

Total

15

/

16

Passed

Repository

BigSimmo/PsychSift

Path

.cursor/skills/code-quality-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.