A coordinated team of 53 Claude Code subagents that build, ship, and operate mobile apps end to end. Each agent owns a narrow slice of the lifecycle so that responsibility, expertise, and review checkpoints stay separated and observable.
Improve a SKILL.md file via static lint, fix proposal, rewrite, and re-test loop. Runs structural checks, proposes targeted fixes, applies them, re-tests, and either keeps or reverts based on score change.
Validates skill files for structural compliance and behavioral correctness in three modes (static lint / spec / audit). Use this before publishing skill changes or to audit the whole skill library for drift.
Run the critical-path smoke gate before QA hand-off. Executes the automated suite, verifies the core user flows defined in the QA plan, and produces a PASS/FAIL report. A failed smoke check means the build is not ready for QA.
Generate a soak-test protocol for extended app sessions. Defines what to observe and log during long sessions to surface memory leaks, battery drain, background-foreground crashes, and network flapping. Used in Polish and Release phases.
Generates a new sprint plan or updates an existing one based on the current milestone, completed work, and team capacity. Pulls context from production docs and the story backlog. Run at sprint start, sprint mid-correction, or after a milestone shift.
Fast sprint status check — reads the active sprint plan, scans story files for status, and produces a concise progress snapshot with burndown read and emerging risks. Use any time during a sprint for situational awareness.
First-time onboarding for the mobile app studio template. Asks where the user is starting from, classifies them, and routes them to the right next skill. Use this on the very first session, or whenever the project feels unmoored.
End-of-story completion review. Verifies each acceptance criterion against the implementation, surfaces deviations, prompts code review if not yet done, marks the story Complete, and surfaces the next ready story. Use after /code-review.
Validates that a story file is implementation-ready — checks for embedded TR-ID, ADR references, framework notes, clear acceptance criteria, no open design questions. Produces READY / NEEDS WORK / BLOCKED verdict. Use before /dev-story to confirm a story can be started safely.
Orchestrate the server / data side of a feature. Coordinates backend-engineer, api-designer, database-specialist, offline-sync-specialist, push-notification-specialist, and firebase-specialist for the data layer.
Orchestrate the content pipeline. Coordinates content-strategist, content-designer, localization-lead, and ux-designer to take a content brief from concept through written, localized, and shipped state.
Orchestrate a full design cycle. Coordinates lead-designer, ux-designer, visual-design-director, interaction-designer, and motion-designer to take a feature from brief through to implementation-ready specs.
Orchestrate the mobile UI build. Coordinates lead-developer, framework specialist (RN/Flutter/iOS/Android), state-management specialist, and animation-specialist to ship a feature's frontend layer end-to-end.
Orchestrate the live-ops team for post-launch content planning. Coordinates live-ops-designer, monetization-designer, analytics-engineer, community-manager, and content-strategist to plan a season, event, or live update.
Orchestrate the polish phase. Coordinates performance-analyst, accessibility-specialist, animation-specialist, qa-tester, and content-designer to harden a feature or area to release quality.
Orchestrate the QA team through a full testing cycle. Coordinates qa-lead (strategy + sign-off) and qa-tester (test cases + bug reports) for a sprint or feature. Covers plan, smoke gate, manual execution, bug filing, and sign-off.
Orchestrate the release team: release-manager, qa-lead, mobile-devops, and producer. Drives a release from candidate through certification, rollout, and post-launch monitoring.
Track, categorize, and prioritize technical debt across the codebase. Scans for debt indicators (TODO, FIXME, deprecated APIs, version-skew, dead flags, stale dependencies), maintains a debt register, and recommends repayment scheduling.
Quality review of test files and manual evidence docs. Goes beyond existence checks — evaluates assertion coverage, edge cases, naming conventions, and evidence completeness. Verdict: ADEQUATE / INCOMPLETE / MISSING per story. Run before QA sign-off or on demand.
Detect non-deterministic tests by reading CI run history. Aggregates pass rates per test, identifies intermittent failures, recommends quarantine or fix, and maintains a flaky-test registry. Best run during Polish phase or after a CI run streak.
Generates a framework-specific test helper library — factories, mocks, custom matchers, and shared assertion utilities — under tests/helpers/. Reduces boilerplate in new test files. Run after /test-setup once the project has a few real tests.
Scaffold the test framework and CI pipeline for the project. Creates the tests/ directory structure, framework-specific test runner, and GitHub Actions or Bitrise workflow. Run once during Technical Setup before the first sprint.
Generate a structured user-test (beta) report template OR analyze existing user-test notes into a structured format. Standardizes how qualitative feedback turns into actionable findings tied to PRDs and stories.
Section-by-section UX spec authoring for a single screen, flow, or HUD element. Reads concept, design bible, parent PRD, and platform conventions to produce design/ux/ .md. Run after the relevant PRD is approved and before stories cite UI behavior.
★not rated 40 4mo agoA61 tokens
originalMIT
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: