kmshdev/plugins/ios-review-and-refactor
- community
Checking that the SKILL.md file is still in the repository.
Review a completed iOS change with applicable formal gates, fix findings within the original scope, and verify the result.
Install
npx vskill@latest install kmshdev/plugins/ios-review-and-refactorSKILL.md
iOS review and refactor
Use this workflow only when the user requests a formal review and repair of completed iOS work. The three gate skills render verdicts; this workflow owns any subsequent edits. A routine feature request does not activate it automatically.
Select gates
| Changed surface | Gate | |
|---|---|---|
| Rendered SwiftUI screen or interaction | iOS design | |
| SwiftUI implementation | SwiftUI | |
| Swift language code | Swift |
Select only applicable gates. The rendered design gate requires simulator evidence; a code-only judgment cannot substitute for it. Record a named blocker when evidence cannot be captured.
Workflow
- Identify the user's intended change, fixed diff or file set, toolchain, deployment target, and available simulator. Record the review scope before dispatch.
- Finish implementation and affected verification first. Freeze a snapshot of the target. Do not run a gate while the target is changing.
- Read and invoke each selected gate according to its own protocol. Preserve its blind reviewer, evidence, and verdict requirements; do not combine their rule sets into one reviewer.
- Report each verdict. For failures, make the smallest in-scope changes that address the cited evidence. Leave out-of-scope observations for a later task.
- Rerun affected builds, tests, and captures. Freeze a new snapshot, then dispatch fresh reviews for affected gates. Keep the original scope fixed through each round.
- Stop when the selected gates pass, are not applicable, or have a concrete blocker. Report the final verdicts and any unresolved findings with evidence.
Treat a gate's fix list as review evidence, not permission to expand the work. Never describe an uncaptured UI gate as PASS.
Security
- Security scanPassed, 90 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingplugins/adversial-ios-review-and-refactor/skills/ios-review-and-refactor/SKILL.md
Popularity
- 7-day trend score
- 5
Not refreshed yet.
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/kmshdev/plugins/ios-review-and-refactor)