CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

flutter-code-review

Review Flutter and Dart diffs, commits, pull requests, focused code scopes, or completed implementations for concrete defects and regression risks. Use for an explicit change review or bounded delivery review; report evidence without edits. Not for broad threat audits, performance diagnosis, or test authoring.

Quality

88%

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

The canonical home for this skill is thiennc-tesoglobal/flutter-skills

SKILL.md
Quality
Evals
Security

Quality

Content

92%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.

An exemplary instruction-only skill body: lean, policy-dense, with a clearly sequenced review workflow, an explicit pre-response validation loop on findings, and correctly split one-level-deep reference files with conditional loading guidance. The only notable gap is the absence of a worked example showing the expected finding format.

DimensionReasoningScore

Conciseness

The 40-line body is dense and padded nowhere: it explains no framework basics and every sentence adds review-specific policy (e.g. "Treat compatibility and safety claims as proof obligations", "accepting an old input alone does not prove backward compatibility"), fully assuming Claude's competence.

5 / 5

Actionability

Concrete, executable instruction-only guidance — numbered boundary steps, an explicit output spec ("name the affected file and tight line range, explain the failure path and impact, and propose a proportionate correction"), and specific validation behaviors ("test ordering and boundary conditions") — with the minor gap that no worked example of a formatted finding is provided, so it stops short of anchor 5's copy-paste-ready bar.

4 / 5

Workflow Clarity

The sequence (establish boundary → review by risk → load references conditionally → output) is clear and capped by an explicit validation checkpoint with recovery actions: "Before responding, challenge and deduplicate the candidate findings. Drop any claim defeated by a guard, ownership rule, version constraint, test, or framework guarantee." Error paths are handled ("If there are no actionable findings, say so directly") and the read-only scope means the destructive/batch cap does not apply.

5 / 5

Progressive Disclosure

A lean overview with two well-signaled, one-level-deep references (both verified to exist as substantive files with no nested links), each carrying an explicit loading condition ("Read [Flutter review checklist]... only for the technical domains touched by the change"), matching the clear-overview anchor exactly.

5 / 5

Total

19

/

20

Passed

Description

78%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 strong, well-scoped description that names the domain, lists concrete review targets, and includes both a positive "Use for" trigger and explicit exclusions. Its main weakness is that the trigger phrasing is written in skill-author terms ("bounded delivery review") rather than the natural language a user would utter when needing a code review.

Suggestions

Rewrite the 'when' clause around natural user utterances, e.g. "Use when the user asks to review a PR, diff, commit, or completed Flutter feature" instead of "Use for an explicit change review or bounded delivery review".

Include the literal phrase "code review" (the most common trigger term for this skill) in the description, since it currently appears only as the skill name and the variant "change review".

Add one or two everyday synonyms such as "bugs" alongside "concrete defects and regression risks" to broaden natural keyword coverage.

DimensionReasoningScore

Specificity

Concrete actions are stated ("Review Flutter and Dart diffs, commits, pull requests, focused code scopes, or completed implementations for concrete defects and regression risks", "report evidence without edits") with comprehensive coverage of review targets, but the description rests on roughly two verbs (review, report) rather than the multiple distinct concrete actions of the anchor-5 example.

4 / 5

Completeness

Both what and when are explicit ("Use for an explicit change review or bounded delivery review" plus "Not for..." exclusions), but the when-clause uses abstract phrasing ("bounded delivery review") instead of concrete user trigger phrases, fitting anchor 4's "'when' could be more explicit or specific" rather than anchor 5.

4 / 5

Trigger Term Quality

Good natural keyword coverage ("review", "diffs", "commits", "pull requests", "Flutter", "Dart"), but a few natural terms users would actually say are missing — the literal phrase "code review" appears only indirectly as "explicit change review", and everyday terms like "bug" only as "concrete defects".

4 / 5

Distinctiveness Conflict Risk

Clear Flutter/Dart change-review niche with distinct triggers and an explicit negative boundary ("Not for broad threat audits, performance diagnosis, or test authoring"), giving minimal conflict risk with adjacent skills.

5 / 5

Total

17

/

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

thienqo/flutter-skills

Path

skills/flutter-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.