CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

cleanup-code-inspections

Reduce technical debt and improve code quality by systematically resolving static analysis warnings.

Quality

74%

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 ./.agents/skills/cleanup-code-inspections/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 a compact, highly actionable workflow with concrete commands, an exact IDE navigation path, and explicit verification steps — a strong example of an instruction-only skill done right. Its only flaws are minor redundancy (repeated purpose statement and duplicated Gradle verification commands) and the absence of an explicit failure-recovery loop in the verify step.

Suggestions

Collapse the intro and Objective sections into one statement of purpose — the same sentence currently appears twice in the body.

State the duplicate './gradlew test' / './gradlew verifyPlugin' baseline once (step 1) and reference it in step 6, freeing tokens for an explicit recovery instruction such as 'If tests fail, revert the refactor and re-apply fixes individually'.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence, but 'Reduce technical debt and improve code quality by systematically resolving static analysis warnings.' is repeated verbatim in both the intro and Objective sections, and the './gradlew test' / './gradlew verifyPlugin' pair appears in both step 1 and step 6 — minor trimming opportunities that keep it below anchor 5.

4 / 5

Actionability

Fully executable guidance throughout: exact Gradle commands ('./gradlew test', './gradlew verifyPlugin', './gradlew testClasses'), the IDE menu path 'Analyze > Inspect Code...' with the 'Default' profile, named inspection categories, concrete quick-fix examples, the '//noinspection [ID] - [Reason]' suppression syntax, and a sample commit message.

5 / 5

Workflow Clarity

A clear 7-step sequence with a baseline stability check and an explicit verification step (testClasses, full tests, re-run analysis for reduced 'Yellow code'). It falls short of anchor 5 only because there is no explicit error-recovery loop (e.g., 'if tests fail, revert the refactor') — checkpoints are present but the retry path is implicit.

4 / 5

Progressive Disclosure

The skill is under 50 lines, has no need for external reference files (none exist in the bundle), and is organized into clear, well-labeled sections; per the rubric's simple-skill guidance this earns a 5 on structure alone.

5 / 5

Total

18

/

20

Passed

Description

50%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 concise and in third person with a clear 'what', but it is essentially a single sentence with no 'when to use' guidance and thin trigger-term coverage. It sits squarely at the midpoint: comprehensible but not self-selecting for the right moments or easily distinguished from sibling cleanup skills.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user asks to fix lint/static analysis warnings, clean up code inspections, or reduce technical debt in an IntelliJ/Gradle project.'

Enumerate the concrete actions the skill performs (run IDE inspections, apply quick-fixes, suppress false positives, verify with Gradle tests) to raise specificity.

Include natural synonyms and tool names users would say — 'inspections', 'lint', 'IntelliJ', 'Gradle' — to improve trigger term quality and distinctiveness.

DimensionReasoningScore

Specificity

Names the domain ('static analysis warnings', 'technical debt') and a concrete action ('systematically resolving static analysis warnings'), but does not list several specific capabilities such as running inspections, applying quick-fixes, or suppressing false positives, which anchor 4 requires.

3 / 5

Completeness

The 'what' is clear ('Reduce technical debt and improve code quality by systematically resolving static analysis warnings') but there is no 'Use when...' clause or equivalent trigger guidance, which caps completeness at 3 per the rubric guidelines.

3 / 5

Trigger Term Quality

Contains relevant keywords like 'technical debt', 'code quality', and 'static analysis warnings', but misses natural variations users would say such as 'fix lint warnings', 'clean up code', 'code inspections', 'IntelliJ inspections', or 'Gradle'.

3 / 5

Distinctiveness Conflict Risk

'Static analysis warnings' gives it a real niche, but the broad framing 'reduce technical debt and improve code quality' overlaps with general refactoring, code-review, and cleanup skills, so it is somewhat specific yet could still trigger for the wrong skill.

3 / 5

Total

12

/

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

flutter/flutter-intellij

Path

.agents/skills/cleanup-code-inspections/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.