KMPilot
CLAUDE.md56 starsChanged 3 months agoMITView on GitHub
NEVER edit feature/ files directly. ALWAYS invoke the required skill FIRST. IMPORTANT: Invoke the skill IMMEDIATELY upon recognizing feature work. Do NOT: - Read files first to "understand the codebase" - Explore the feature structure first - Plan the implementation first The skills contain workflows that handle exploration, planning, and implementation in the correct order. /using-design-system auto-activates for UI work and does not need explicit invocation. The design pipeline uses a blueprint artifact contract for decoupled skill coordination: Each skill…
We split this CLAUDE.md into the rules it gives an agent
2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
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
- Distinctive: line 18
Read files first to "understand the codebase"
- Distinctive: line 53
All rules, patterns, naming conventions, and feature structure: @.claude/skills/_shared/patterns.md
≈ “Common” is an estimate: at least 1 in 5 of the 25,680 CLAUDE.md 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.
Files
CLAUDE
STOP - Mandatory Workflow Rules
NEVER edit feature/ files directly. ALWAYS invoke the required skill FIRST.
| Action | Skill | Trigger Keywords |
| Create feature | /create-feature | "new feature", "add feature", "create" |
| Modify feature | /modify-feature | "add to", "change", "update", "fix", "modify" |
| Review feature | /review-feature | "review", "check", "audit" |
| Test feature | /test-feature | "test", "generate tests" |
| Design UI | /design-ui | "design screen", "Stitch", "design UI", "mockup" |
| Verify UI | /verify-ui | "verify UI", "audit UI", "check implementation" |
| Bridge iOS↔Kotlin | /bridge-swift | "iOS SDK", "Swift", "call Swift", "native framework", "MapKit", "biometrics", "Apple Pay" |
IMPORTANT: Invoke the skill IMMEDIATELY upon recognizing feature work. Do NOT:
- Read files first to "understand the codebase"
- Explore the feature structure first
- Plan the implementation first
The skills contain workflows that handle exploration, planning, and implementation in the correct order.
/using-design-system auto-activates for UI work and does not need explicit invocation.
Design Pipeline
The design pipeline uses a blueprint artifact contract for decoupled skill coordination:
/design-uidesigns screens in Stitch and produces a self-contained blueprint (setsblueprintConsumed: falseinstitch-project.json)/create-featureor/modify-featureauto-detect the blueprint and enter design-aware mode (setsblueprintConsumed: trueafter implementation)/verify-uiaudits the implementation against the Stitch design (three-way token audit)
Each skill is independently invocable — no skill calls another skill. The user controls the pipeline.
Platform Capabilities & Native Views (Rule 14)
Features needing a device capability (GPS, camera, BLE, biometrics) or a native view (map, camera preview, WebView) are handled inside /create-feature / /modify-feature — no separate command. Those skills classify the feature's Platform Profile (network / platform-capability / native-view / mixed) in Phase 2, then route work to platform (capability behind a commonMain DataSource → Either<T>, per-platform actuals incl. desktop) and ui-layer (the expect @Composable native-view interop). When an iOS actual needs Swift, they finish the Kotlin side and route you to /bridge-swift (the iOS-Swift leg). Full patterns: .claude/skills/create-feature/architecture/platform.md.
Build Commands
./gradlew :feature:{name}:assembleAndroidMain # Incremental build
./gradlew assembleDebug # Full build
./gradlew :feature:{name}:ktlintFormat # Format code
./gradlew :feature:{name}:desktopTest # Run testsArchitecture
KMP + Compose Multiplatform + Clean Architecture
All rules, patterns, naming conventions, and feature structure: @.claude/skills/_shared/patterns.md
Gotchas
- Package names: lowercase only (
productdetailnotproduct-detail) - Features NEVER depend on other features
- Specs live at
.claude/docs/{name}/spec.md - Core module tiers (generic vs
app/): the two-tier split applies to every core library module that holds project-specific content —:core:designsystem(designsystem.app:App*state screens + project composites/brand drawables),:core:data(data.app: project/domain persisted state and shared cross-feature remote — endpoints/wire models/datasource), and:core:common(common.app: project/example value types). Generic code must NEVER import its module's.apptier (stripped/neutralized byinstall.sh) — it's a package convention; the lone sanctioned exception isDataModules.ktreferencingappDataModule. Full map:_shared/patterns.md→ "Core Module Tiers" - Loading/Failed UI is shared: features call
AppLoadingState/AppErrorStatefromdesignsystem.app(copy + nav passed as params), never a privateLoadingContent/FailedContent. Empty state stays per-feature
Reference
- Example:
feature/dashboard/ - Versions:
gradle/libs.versions.toml - JVM: 21
Other versions1 project uses a version of this.
Word for word · 1
- ThisIsSadeghi/Loupe★ 1100% same
Edited · 0
None found.
Wrote their own version · 0
None found.
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository6 other files it gives its agents.
- bridge-swiftSkill
- create-featureSkill
- design-uiSkill
- modify-featureSkill
- using-design-systemSkill
- verify-uiSkill
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
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.

