Cleanup Code Inspections Agent Skill
Reduce technical debt and improve code quality by systematically resolving static analysis warnings.
Install
one command, takes just this skill from the repositorynpx skills add https://github.com/flutter/flutter-intellij --skill cleanup-code-inspectionsThe instruction itself
10 sections, as written by the authorSkill: Code Inspection & Cleanup
You are tasked with reducing technical debt and improving code quality by systematically resolving static analysis warnings.
Objective
Reduce technical debt and improve code quality by systematically resolving static analysis warnings.
Workflow Instructions
1. Baseline
- Run
./gradlew testand./gradlew verifyPluginto ensure the project is stable.
2. Run Inspection
- Execute
Analyze > Inspect Code...on the project (or a specific module) using the "Default" profile.
3. Prioritize
- Focus first on "Probable bugs", "Performance", and "Memory" categories.
4. Refactor
- Apply quick-fixes for obvious issues (e.g., "Result of method call ignored", "String concatenation in loop").
5. Suppress
- Explicitly suppress false positives with a comment and reason (e.g.,
//noinspection [ID] - [Reason]).
6. Verify
- Run
./gradlew testClassesto ensure safe refactoring. - Run
./gradlew testand./gradlew verifyPluginto ensure no regressions. - Re-run analysis to ensure the "Yellow code" count has decreased and no regressions were introduced.
7. Report & Review
- Summarize the inspections resolved.
- Test Location: Explicitly state *where* in the IDE the user should go to test the changed functionality (e.g., "Go to Preferences > Languages & Frameworks > Flutter").
- Action: Ask the user to review the changes closely.
- Do not commit or push.
- Provide a suggested Git commit message (e.g., "Cleanup: Resolve static analysis warnings in [Module]").
Other skills for the same job
different authors, same section of the catalogue
Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation
Use when completing tasks, implementing major features, or before merging to verify work meets requirements
Execute git commit with conventional commit message analysis, intelligent staging, and message generation. Use when user asks to commit changes, create a git commit, or mentions "/commit". Supports: (1) Auto-detecting type and scope from changes, (2) Generating conventional commit messages from diff, (3) Interactive commit with optional type/scope/description overrides, (4) Intelligent file staging for logical grouping
Comprehensive GitHub code review with AI-powered swarm coordination
Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.
Use this skill to review code. It supports both local changes (staged or working tree) and remote Pull Requests (by ID or URL). It focuses on correctness, maintainability, and adherence to project standards.
Refactor bloated AGENTS.md, CLAUDE.md, or similar agent instruction files to follow progressive disclosure principles. Splits monolithic files into organized, linked documentation.
Create high-quality git commits: review/stage intended changes, split into logical commits, and write clear commit messages (including Conventional Commits). Use when the user asks to commit, craft a commit message, stage changes, or split work into multiple commits.
How to use it
Take flutter/cleanup-code-inspections from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.