github.com/meshtastic/Meshtastic-Android
| Skill | Added | Review |
|---|---|---|
baseline .claude/skills/baseline/SKILL.md Run the mandatory pre-push baseline verification for Meshtastic-Android — bootstrap, then spotlessApply/spotlessCheck/detekt/detektTypeResolved/assembleDebug/test/allTests (plus kmpSmokeCompile and sort-strings when relevant) via the gradle-runner subagent, restore the host-render screenshot diff, and report a single pass/fail. Use before every push. This is the check CI fails on when skipped. | 76 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 1bedc5d | |
ci-cost-control .skills/ci-cost-control/SKILL.md Keep GitHub Actions spend down on Meshtastic-Android - avoid redundant runs, cancel superseded ones, and pick the narrowest CI path for the change. Use this whenever you are about to push repeatedly, re-run a workflow, touch `.github/workflows/`, or someone asks why CI is slow, queued or expensive. | 75 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 1bedc5d | |
code-review .skills/code-review/SKILL.md Review a Meshtastic-Android change against KMP architecture, Compose Multiplatform and Modern Android Development conventions, starting from the four defect classes that keep recurring because neither the compiler, detekt nor spotless can see them. Use this for any PR review, for self-review before pushing, and whenever asked whether a change is safe to merge. | 68 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 1bedc5d | |
compose-ui .skills/compose-ui/SKILL.md Build shared Compose Multiplatform UI in Meshtastic-Android - adaptive layouts on Material 3 Adaptive, plus the string and resource rules. Use this whenever you add or change a composable, add a user-facing string, or work on tablet, desktop or landscape layout. Consult the bundled `strings-index.txt` rather than opening the raw `strings.xml`, which is guarded for size. | 69 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 1bedc5d | |
crashlytics-triage .claude/skills/crashlytics-triage/SKILL.md Triage current Meshtastic-Android crashes in Firebase Crashlytics — establish the right version filter (topVersions first, then topIssues filtered to "X.Y.Z (versionCode)"), fan out one crash-investigator subagent per top issue in parallel, and return a distilled verdict table. Use for "what's crashing", "triage Crashlytics", or "is build NNNN healthy" sweeps; for a single known issue id, dispatch crash-investigator directly instead. | 75 Impact — No eval scenarios have been run Securityby Low Low-risk findings worth noting Version: 1bedc5d | |
design-standards .skills/design-standards/SKILL.md Apply the Meshtastic design standards on Android - brand colors, Material 3 tokens, MeshtasticIcons and accessibility - with the upstream `meshtastic/design` standards as the source of truth. Use this whenever you choose a color, icon, spacing value or contrast level, and before claiming a screen matches the design. | 73 Impact — No eval scenarios have been run Securityby Low Low-risk findings worth noting Version: 1bedc5d | |
implement-feature .skills/implement-feature/SKILL.md The end-to-end workflow for adding a feature to Meshtastic-Android, in the order that keeps KMP source sets and the architecture intact. Use this whenever you start implementing a new feature or a sizeable behavior change, before writing any code. | 72 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 1bedc5d | |
kmp-architecture .skills/kmp-architecture/SKILL.md Kotlin Multiplatform source-set rules for Meshtastic-Android - where commonMain ends, how expect/actual is bridged, and the networking, database and platform-integration boundaries. Use this whenever you add a file to a KMP module, move code between source sets, or hit a compile error that appears on only one target. | 70 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 1bedc5d | |
navigation-and-di .skills/navigation-and-di/SKILL.md Koin Annotations dependency injection and JetBrains Navigation 3 in Meshtastic-Android, including the anti-patterns that compile cleanly and then fail at runtime. Use this whenever you add a screen, a route, a ViewModel or a Koin module, or when navigation or injection behaves unexpectedly. | 72 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 1bedc5d | |
new-branch .skills/new-branch/SKILL.md The canonical recipe for starting a fresh working branch off a freshly fetched `origin/main` in Meshtastic-Android. Use this whenever a unit of work starts - "new branch off main", "peel off a fresh branch", "dust off | 71 Impact — No eval scenarios have been run Securityby Low Low-risk findings worth noting Version: 1bedc5d | |
pr .claude/skills/pr/SKILL.md Push the current branch and open a draft PR for Meshtastic-Android the repo way — baseline verified first, body drafted per CONTRIBUTING.md (WHY-first, categorized changes, screenshots for UI work). Use whenever work is ready to go up as a PR. | 73 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 1bedc5d | |
proto-bump .claude/skills/proto-bump/SKILL.md Change the org.meshtastic:protobufs pin for Meshtastic-Android — to a tagged release or to a commit snapshot (X.Y.Z.N-g<sha>-SNAPSHOT) from protobufs master. Verifies with test/allTests (not compile alone) via the gradle-runner subagent, audits the new field surface, and opens a PR. Use to consume new proto changes, or to finish a Renovate protobufs bump that needs call-site work. | 75 Impact — No eval scenarios have been run Securityby Low Low-risk findings worth noting Version: 1bedc5d | |
run-meshtastic-android .claude/skills/run-meshtastic-android/SKILL.md Run, launch, drive, and screenshot the Meshtastic app — the Compose Desktop app via hot reload (semantic clicks, live reload, window screenshots) or the Android app on an emulator (scripted deeplink bring-up, uiautomator taps, screencap). Use when asked to run the app, verify a UI change in the real app, take a screenshot, or exercise a flow end to end against a simulated radio. | 75 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 1bedc5d | |
speckit .skills/speckit/SKILL.md The Spec Kit specification-driven workflow in Meshtastic-Android - how a feature description becomes a spec, a plan, tasks and an implementation, and what the constitution requires at each step. Use this when asked to write or update a spec, plan or tasks file, or when working anywhere under `specs/`. | 68 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 1bedc5d | |
testing-ci .skills/testing-ci/SKILL.md Decide what to run locally before pushing Meshtastic-Android, and read the CI pipeline. Use this whenever you finish a change and need the right verification for its change type, when a CI job fails or is skipped, or when you need to know why the merge queue behaved the way it did. | 64 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 1bedc5d |