行動開發

Sync SpecWeave increments with JIRA epics/stories. Content flows SpecWeave→JIRA, status flows JIRA→SpecWeave. Activates ONLY when user asks questions about JIRA integration or needs help configuring JIRA sync. Does NOT activate for slash commands. For syncing, use /sw-jira:sync command instead. Coordinates with jira-mapper agent.

Expert in React Native 0.83+ native modules, Turbo Modules with Codegen, Fabric renderer, JSI (JavaScript Interface), New Architecture migration, bridging JavaScript and native code, iOS Swift modules, Android Kotlin modules, expo config plugins. Activates for native module, native code, bridge, turbo module, JSI, fabric, autolinking, custom native module, ios module, android module, swift, kotlin, objective-c, java native code, codegen, new architecture.

Expert in React Native 0.83+ and Expo SDK 54+ environment setup. Helps with Node.js 20+, Xcode 16.1+, Android Studio, watchman, CocoaPods, EAS Build, simulators, emulators, and troubleshooting. Activates for environment setup, installation issues, xcode setup, android studio, simulators, emulators, react-native init, expo init, development environment, SDK configuration, EAS Build, development builds.

Intelligently onboards brownfield projects by merging existing CLAUDE.md backups into SpecWeave structure. Extracts project-specific knowledge, domain context, team conventions, and technical details from backup CLAUDE.md files, then distributes content to appropriate SpecWeave folders without bloating CLAUDE.md. Activates for: merge docs, merge claude, onboard brownfield, import existing docs, claude backup, specweave merge-docs.

Intelligent multi-project specification splitting and organization. Analyzes user stories to map them to correct projects (FE, BE, MOBILE, INFRA) based on content, tech stack, and component architecture. Creates project-specific folder structure and splits monolithic specs. Activates for multi-project JIRA/GitHub setups, brownfield projects with multiple teams, microservices architecture. Keywords: multi-project, project mapping, spec splitting, JIRA projects, multiple projects, microservices, FE/BE/MOBILE split, intelligent classification.

BMAD (Best, Most Appropriate, Design) technology decision framework expert. Helps evaluate technology alternatives, analyze tradeoffs, calculate TCO, assess vendor lock-in, and make data-driven architecture decisions. Activates for technology choices, stack decisions, database selection, cloud provider comparison, framework evaluation, architecture decisions, BMAD, best practices, most appropriate, design decisions, technology tradeoffs.

Expert PM validation for increment closure with 3-gate quality checks (tasks, tests, documentation). Acts as final quality gate before closing increments. Validates task completion, test coverage, documentation updates, and detects scope creep. Activates for /done command, increment closure, close increment, validate increment, completion check, quality gate, PM approval, ready to close, scope creep detection, release validation, increment validation.

Identify and execute independent operations in parallel for 3-5x speedup. Auto-analyzes task dependencies, groups into batches, launches parallel Task() calls. Applies to /optimize (5 checks), /ship pre-flight (5 checks), /design-variations (N screens), /implement (task batching). Auto-triggers when detecting multiple independent operations in a phase.

Expert assistant for authoring Claude Code skills. Creates precise SKILL.md files with proper YAML frontmatter, validates naming conventions, and applies official best practices. Triggers on keywords: writing skills, creating skills, skill authoring, SKILL.md, new skill, skill template, skill validation, skill structure, create skill, update skill

Identify and execute independent operations in parallel for 3-5x speedup. Auto-analyzes task dependencies, groups into batches, launches parallel Task() calls. Applies to /optimize (5 checks), /ship pre-flight (5 checks), /implement (task batching), /prototype (N screens). Auto-triggers when detecting multiple independent operations in a phase.

Generates and updates the latest app changelog based on git history since the last version tag.

Prospective hindsight. Use pm: to assume failure has already happened and work backward to identify causes. Gary Klein's method for surfacing risks and blind spots.

Deploy TanStack Start applications to Cloudflare Workers/Pages with GitHub Actions, Doppler, Wrangler, database migrations, and rollback procedures. Use when deploying Grey Haven applications.

Add a new third-party dependency to the project following the version catalog and approval workflow.

Trace code execution paths and data flow. Use when user asks "how does X work", "what happens when X", "trace the flow of X", "where does data come from", or needs to understand feature implementation.

Comprehensive Chrome DevTools automation for performance testing, Core Web Vitals measurement (INP, LCP, CLS), network monitoring, accessibility validation, responsive testing, and browser automation. Uses Chrome DevTools Protocol via MCP to provide professional-grade web application testing, debugging, and analysis capabilities including performance tracing, HAR export, device emulation, and multi-page workflows.

Disciplined TDD workflow enforcing red-green-refactor cycle and the "iron law" of no production code without failing tests first. USE WHEN user wants to write tests first OR implement new feature with TDD OR fix bugs with test coverage OR explicitly requests TDD approach. Enforces systematic test-first development with verification at each step.

Skills for understanding and applying DOSDP (Dead Simple Ontology Design Patterns) to ensure consistent ontology term creation and maintenance. This skill is about recognizing patterns and ensuring consistency, not using dosdp-tools directly.

Android app development with gomobile, Gradle, and modern tooling. USE WHEN building Android apps, working with gomobile bindings, managing Android SDK/NDK, running emulators, debugging with adb, or publishing to Play Store.

Use when the user says "search internet" or for requests related to web research; it provides a structured approach to conducting comprehensive web research