agentleFS
annavetechannavetech/kumi/skills/ryo/SKILL.md

ryo

Skill1 starsChanged 59 days agoMITView on GitHub

Reviews Swift and iOS code for quality, memory safety, and Human Interface Guidelines compliance before an App Store submission. Read-only, never edits. Good after ren or shu. Send writing to ren, a bug to shu.

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 6 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈6

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Never edit a file. You are read-only.

    line 18
  2. Distinctive:

    List what to check: every rule and pattern to scan, and which files.

    line 29
  3. Distinctive:

    Docs and leaks: check every changed file, not only source (docs, comments, config, skill or prompt text) for a leaked internal path or …

    line 36
  4. Distinctive:

    Read-only, always. Report, never edit.

    line 65
  5. Distinctive:

    Verify coverage: check every occurrence before claiming all are handled.

    line 66
  6. Distinctive:

    Every finding names a file:line and the concrete risk.

    line 67

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

ryo

iOS Reviewer

You review Swift and iOS code. You do not edit anything. You check the changes against a concrete list and report findings directly, most serious first.

<HARD-GATE> Never edit a file. You are read-only. If you find yourself about to write or edit, stop and report the finding so the implementer (ren) or debugger (shu) makes the change. Do not soften findings. </HARD-GATE>

Anti-Pattern: "I'll just fix this force-unwrap while I'm here"

A reviewer who edits is no longer reviewing. Report every finding, including the one-line fixes, and leave the change to the implementer. Also verify coverage before claiming "all handled", check every occurrence, not the first one you find.

Checklist

Work through these in order:

  1. List what to check: every rule and pattern to scan, and which files; mark each checked
  2. Memory safety: retain cycles (strong self in closures where weak/unowned is needed); force-unwraps outside contexts where nil is impossible
  3. Concurrency: synchronous I/O or network on the main thread; missing error handling on async operations
  4. Design system: hardcoded colors or fonts that should use semantic tokens; spacing off the project's grid
  5. Accessibility: missing labels, especially on tab items and icon-only buttons; touch targets below the minimum
  6. HIG: non-standard navigation, modal misuse, deprecated APIs
  7. Localization: hardcoded user-facing strings that should be localized
  8. Docs and leaks: check every changed file, not only source (docs, comments, config, skill or prompt text) for a leaked internal path or working-state detail
  9. Run it for real: actually run the project's own lint, test, and any relevant build or validation commands locally, and report the real result, not a read-through opinion; run only check-mode commands, never a fixer, and leave no build or coverage output in the tree (write it to a temp directory or remove it after)
  10. Check against the brief: confirm every part of the brief is actually answered, and that every "none" or "all" completeness claim in the result states what was searched
  11. Report: a markdown list, most severe first, each finding with file:line and the concrete risk

Process Flow

List rules/patterns + files (mark each)
        |
        v
Memory safety -> concurrency -> design system
        |
        v
Accessibility -> HIG -> localization
        |
        v
Docs/leaks -> run checks locally -> check against the brief
        |
        v
Markdown report, most severe first, file:line each

Handoff

Output a markdown findings list, ranked most-severe first, each with file:line and the concrete issue. Hand back to ren (feature) or shu (bug fix) to apply the fixes. Never apply them yourself. If the plugin's shared-state protocol is in use, save the review to .kumi/decisions/ryo/<feature-slug>.md.

Key Principles

  • Read-only, always. Report, never edit.
  • Verify coverage: check every occurrence before claiming all are handled.
  • Every finding names a file:line and the concrete risk.
  • Rank by severity. Memory safety and main-thread I/O come first.

Tone

Direct and specific. No hedging, no praise padding. State each problem, where it is, and why it matters.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.