Mobile

Refactor BDD implementation (scenarios, step definitions, feature code) to improve quality and eliminate tech debt while keeping scenarios passing. Use after implement-feature when scenarios are green.

Given a repo snapshot and a goal description, produce a structured, step-by-step plan of code changes: which files to touch, in what order, with risks and done-criteria. This skill does not modify files and does not execute code.

App Store Connect 자동화 스킬. JWT API와 Playwright 브라우저 자동화를 결합한 하이브리드 방식. 앱 정보 조회, 빌드 관리, TestFlight 배포, 스크린샷 업로드, 앱 제출 워크플로우 지원. jelly-ios-skill과 연동하여 iOS 빌드 후 자동 배포 가능.

Application monitoring, logging systems, and alerting

Automatically detect and add comprehensive documentation to code files across multiple languages (Python, JavaScript/TypeScript, C/C++, Dart/Flutter). Generate language-appropriate docstrings, comments, and examples following industry standards. Use when code files lack documentation, after implementing new features, or when requested to document code. Support single files and batch documentation.

Find CRPO-compliant positioning angles for therapy services that differentiate without overpromising. Use when positioning therapy services, creating service pages, crafting offers, or when copy isn't converting. Triggers on: find angles for [therapy service], how should I position [service], what's the hook, why isn't this converting, differentiate this service. Outputs 3-5 therapy-appropriate positioning options with headline directions for each. CRITICAL: All angles must be factual, verifiable, and avoid outcome guarantees per CRPO Standard 6.2.

Load executive candidate CSVs into Airtable People table with intelligent schema detection, flexible column mapping (20+ variations), duplicate checking, and bio file loading. Handles any CSV format with fuzzy matching. Dry-run preview mode for safe testing. Production-ready for FirstMark demo day.

Production-ready CI workflow examples with all security patterns applied. SHA pinning, minimal permissions, secret scanning, and language-specific variants.

Break out of stuckness through inversion, simplification, and fresh angles. Use when repeating approaches without progress.

Categorize extracted information into the appropriate knowledge base subdirectory (tasks, definitions, wiki, project-status, people, jira-drafts). Use when organizing extractions into the knowledge base.

Cross-functional initiative portfolio management for 15-25 concurrent strategic projects with health scoring, dependency mapping, resource conflict detection, and executive decision support

Automatically applies when profiling Python performance. Ensures proper use of profiling tools, async profiling, benchmarking, memory analysis, and optimization strategies.

Standardize how a single CLI command is executed in a repo: working dir, argv, timeout, env overrides – and capture exit code, logs, and a short human-readable summary.

Expose Prometheus metrics with counters, gauges, and histograms. Use for production monitoring and alerting.

Generate PROJECT-MAP.auto.scm by extracting structure from codebases. Invoke when user requests project mapping, structure extraction, or needs to create/update .phi maps.

PR を承認（approve）する。「PR 承認」「PR を approve」「approve して」「PR を通す」「LGTM」「PR OK」「マージ許可」などで起動。レビュー後に承認コメントを投稿。

Gather user design preferences before building UI.Use when: starting a project with visual interface (Web App, Mobile, Browser Extension).Triggers: "design preferences", "visual style", "choose theme", "design step".

Generates public/ directory with static assets including favicons, app icons, and site.webmanifest for Progressive Web App (PWA) support.

This skill should be used when designing training programs, individual workshop sessions, or learning modules using evidence-based frameworks. Use this skill to structure sessions with TBR 4Cs (Connection, Concepts, Concrete Practice, Conclusion), create learning objectives, apply brain-friendly principles, and design session flow.

Use when creating new skills, editing existing skills, or verifying skills work before deployment - applies TDD to process documentation by testing with subagents before writing, iterating until bulletproof against rationalization