rafaeltonholo/svg-to-compose/self-review
Claude Code and agent skill by rafaeltonholo/svg-to-compose
- community
Checking that the SKILL.md file is still in the repository.
Perform a thorough self-review of pending changes before committing or opening a PR. Checks code quality, adherence to project conventions, test coverage, static analysis, and golden sample integrity. Use after completing a task and before requesting commit or PR creation.
Install
npx vskill@latest install rafaeltonholo/svg-to-compose/self-reviewSKILL.md
Self-Review
Overview
Systematically review all pending changes against this repository's standards before they are committed. Catch issues early — style violations, missing tests, broken golden samples, Detekt failures — so that PRs pass CI on the first try.
Workflow
- Read context — Load
.ai/guidelines.mdand theAGENTS.mdfor every
module touched by the changes.
- Enumerate changes — Run
git diff(staged + unstaged) andgit status
to build a complete picture of what changed.
- Review each file against the checklist below.
- Run verification commands to confirm nothing is broken.
- Report findings with actionable items, grouped by severity.
Review Checklist
Code Quality
- [ ] No
java.ioorjava.nioimports incommonMainsource sets. - [ ] File I/O uses Okio (
okio.Path,okio.FileSystem), not JVM APIs. - [ ] No new global state or singletons that could cause Kotlin/Native freezing
issues.
- [ ] Max line length is 120 characters.
- [ ] No
TODO/FIXME/STOPSHIPwithout a linked GitHub issue. - [ ] No hardcoded secrets, credentials, or local paths.
Architecture
- [ ] Core logic stays in
commonMain; platform code in appropriate source sets. - [ ] Build configuration uses convention plugins in
build-logic/, not duplicated
in module build.gradle.kts files.
- [ ] Dependencies added to
gradle/libs.versions.toml, not inlined. - [ ] New dependencies support all targets:
jvm,macosX64,macosArm64,
linuxX64, mingwX64.
Style & Conventions
- [ ] Follows
kotlin.code.style=official. - [ ] Make sure you followed SOLID principles.
- [ ] Make sure you followed DRY principle.
- [ ] Make sure you followed KISS principle.
- [ ] Make sure you followed YAGNI principle.
- [ ] Changes are minimal and focused — no unrelated refactors, no added
docstrings/comments on unchanged code.
- [ ] Public APIs you introduced must have KDocs.
- [ ] No unnecessary abstractions or over-engineering.
- [ ] Commit message follows Conventional Commits:
<type>(<scope>): <subject>. - [ ] Branch name follows
<type>/<short-topic>convention.
Testing
- [ ] New or changed behavior has corresponding tests.
- [ ] Tests are in
commonTest/and mirror the source package structure. - [ ] Tests use
kotlin.testAPIs with descriptive backtick names. - [ ] Parameterized tests use Burst where appropriate.
- [ ] No flaky patterns (time-dependent, random, unordered collection assertions).
Golden Samples
- [ ] If parser or generator logic changed, golden samples were regenerated and
diffed.
- [ ] Updated golden
.ktfiles are included in the changeset if output changed
intentionally.
- [ ] No unintended formatting or logic drift in generated output.
Static Analysis
- [ ]
./gradlew detektpasses with zero issues. - [ ] Cognitive complexity, cyclomatic complexity, and method/class length are
within thresholds.
Verification Commands
Run these in order, stopping at the first failure to fix before proceeding:
.github/actions/cli-integrity-check/script.sh . svg .github/actions/cli-integrity-check/script.sh . xml
require svgo to be installed
.github/actions/cli-integrity-check/script.sh . svg optimize
require avocado to be installed
.github/actions/cli-integrity-check/script.sh . xml optimize
Self-Review Report
Summary
<one-line summary of changes reviewed>
Blockers
- [ ] <description and file:line>
Warnings
- [ ] <description and file:line>
Nits
- [ ] <description and file:line>
Verification Results
- Detekt: PASS/FAIL
- Build: PASS/FAIL
- Tests: PASS/FAIL
- Golden samples: PASS/FAIL/N/A
Security
- Security scanPassed, 100 of 100Pattern checks on the skill's files.
- Model reviewNot runA model review is scheduled for the next rescan.
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryChecking.ai/skills/self-review/SKILL.md
Popularity
- Repository stars
- 221
- Repository forks
- 11
- 7-day trend score
- 27
Stars and forks are for the whole GitHub repository, not this skill alone. Refreshed 2 Sep 2026, 2 months ago.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/rafaeltonholo/svg-to-compose/self-review)