Diagnose and eliminate flaky tests systematically.
Skills(SKILL.md)は、AIエージェント(Claude Code、Cursor、Codexなど)に特定の能力を追加するための設定ファイルです。
詳しく見る →Diagnose and eliminate flaky tests systematically.
flask
Flask framework workflow guidelines. Activate when working with Flask projects, flask run, or Flask-specific patterns.
flesh out our plan by filling in gaps and clearly building out the specfification
Track flight status, delays, and search routes. Uses FlightAware data.
Use when you need to run Flow type checking, or when seeing Flow type errors in React code.
Create scenario files for testing migrated Output SDK workflows. Use to set up test inputs in the scenarios/ subfolder.
Creer un nouveau flow d'automatisation de formulaire complet, incluant exploration du site web, implementation et tests. (project)
Conduct an extremely thorough interview about a task/spec and write refined details back.
Resume interrupted flow:work session from last checkpoint. Reads flow-progress.txt to restore context and continue work.
Enforces TDD Iron Law in flow-dev. NO PRODUCTION CODE WITHOUT A FAILING TEST FIRST.
Execute a plan file or Beads epic systematically with git setup, task tracking, quality checks, and commit workflow. Use when implementing a plan, working through a spec, following documented steps, or executing a Beads issue ID (e.g., bd-123, gno-45, app-12).
Refactor complex Android/KMP state management code to use FlowRedux state machine pattern. Use this when developers need to transform tangled state logic, multiple LiveData/StateFlow sources, or callback-heavy code into a clean, testable state machine architecture.
Summarize ETF net flows and derivatives context (OI Δ, funding, basis, skew, liquidation bands) from local JSON/CSV drops. Use at open/close or when assessing leverage resets.
Containerizing Flox environments with Docker/Podman. Use for creating container images, OCI exports, multi-stage builds, and deployment workflows.
Build adaptive and responsive Flutter UIs that work beautifully across all platforms and screen sizes. Use when creating Flutter apps that need to adapt layouts based on screen size, support multiple platforms including mobile tablet desktop and web, handle different input devices like touch mouse and keyboard, implement responsive navigation patterns, optimize for large screens and foldables, or use Capability and Policy patterns for platform-specific behavior.
Specialized skill for Flutter app development and Dart programming
Complete Flutter debugging toolkit combining PDCA methodology, Dart logging patterns, and MCP tools. Use when debugging Flutter apps - visual issues, runtime behavior, widget problems, or verifying fixes through device testing.
Configure Flutter for desktop platforms with platform channels and native integrations
Complete guide for using drift database library in Flutter applications. Use when building Flutter apps that need local SQLite database storage with type-safe queries, reactive streams, migrations, and efficient CRUD operations. Includes setup with drift_flutter package, StreamBuilder integration, Provider/Riverpod patterns, and Flutter-specific database management for mobile, web, and desktop platforms.
Integrate Duit framework into Flutter applications including setup, driver configuration, HTTP/WebSocket transports, custom widgets, and themes. Use when integrating backend-driven UI, configuring Duit, or adding Duit to Flutter applications.
Lightweight Flutter enterprise development skill focused on feature-based clean architecture. Use when user asks to: (1) Build enterprise Flutter apps with clean architecture, (2) Implement feature-based modular structure, (3) Set up scalable Flutter project organization, (4) Create maintainable enterprise codebase. Triggers: Flutter enterprise app, clean architecture Flutter, feature-based Flutter, enterprise Flutter structure, modular Flutter architecture
Expert in building cross-platform apps with Flutter 3+. Specializes in Dart, Riverpod, Flame (Game Engine), and FFI (Native Integration).
Comprehensive guide for Flutter navigation and routing including Navigator API, go_router, deep linking, passing/returning data, and web-specific navigation. Use when implementing screen transitions, configuring routing systems, setting up deep links, handling browser history, or managing navigation state in Flutter applications.
Comprehensive Flutter networking guidance including HTTP CRUD operations, WebSocket connections, authentication, error handling, and performance optimization. Use when Claude needs to implement HTTP requests GET POST PUT DELETE, WebSocket real-time communication, authenticated requests with headers and tokens, background parsing with isolates, REST API integration with proper error handling, or any network-related functionality in Flutter applications.
[Flutter] pub.dev package search skill. Quick package search, info lookup, version check, and dependency analysis. (project)
Comprehensive Flutter Supabase query testing: static validation, live testing, RLS verification, and CI integration. Use when validating queries before deployment, debugging query failures, or setting up query testing pipelines.
Expert knowledge in Flutter Riverpod state management (2025 best practices). Use when working with Riverpod, Flutter state management, AsyncNotifier, provider types, code generation with riverpod_generator, state synchronization, or when the user mentions data fetching, mutations, reactive state, performance optimization, or testing in Flutter apps. Covers AsyncNotifierProvider patterns, repository architecture, autoDispose, family providers, and common anti-patterns to avoid.
1. Identify which tests to run:
A comprehensive Flutter testing skill for creating, writing, and analyzing tests in any Flutter project. Provides guidance on test structure, mocking patterns, Riverpod testing, widget testing, and industry best practices for reliable, maintainable tests.
Comprehensive Flutter testing guidance covering unit tests, widget tests, and integration tests. Use when working with Flutter applications to write unit tests for functions/methods/classes, create widget tests to verify UI components, develop integration tests for end-to-end testing, mock dependencies and plugin interactions, debug common testing errors, test Flutter plugins with native code, and run tests in different build modes (debug, profile, release)
flutter-ui-components
Build complete UI screens by composing multiple uxscii components. Use when working with .uxm files, when user wants to create, scaffold, or build .uxm screens like login, dashboard, profile, settings, or checkout pages.
Import UI screenshots and generate uxscii components automatically using vision analysis. Use when user wants to import, convert, or generate .uxm components from screenshots or images.
Fly.io machines may be stopped. Before using `fly ssh console`, ensure a machine is running:
Setup backend project with Flyway SQL migrations, tini init system, and MySQL integration testing. Modifies existing Dockerfile from backend-docker skill.
Family Medicine Residency Excel-based scheduling. Use when working with academic year block schedule spreadsheets to assign faculty half-days (C, GME, DFM) and resident half-days, validate constraints, process FMIT/SAFP blocks, apply post-call rules, and meet AT coverage. Triggers: Block schedule, faculty scheduling, resident scheduling, half-day assignments, FMIT, clinic coverage, resident supervision, AY 25-26.
Financial Modeling Prep API for stocks, fundamentals, SEC filings, institutional holdings (13F), and congressional trading. Use when fetching financial statements, ratios, DCF valuations, insider/institutional ownership, or screening stocks.
Tenzir Python coding standards and tooling setup. Use when writing python code, running ruff/mypy/pytest, encountering pyproject.toml/uv.lock, or setting up a new Python project.
European football matches — upcoming games, results, and highlights for briefings.
Invoke FORCE_MANAGER for task force assembly and team composition decisions. Use when complex tasks require coordinated multi-agent teams with proper staffing and lifecycle management.
Use when analyzing critical documents, specifications, or large files (>3000 lines), before any synthesis or conclusions - enforces complete line-by-line reading with quantitative verification to prevent skimming that leads to incomplete understanding
Use to drive consistent forecast methodology, grading, and inspection
Use to stress-test predictions by assuming they failed and working backward to identify why. Invoke when confidence is high (>80% or <20%), need to identify tail risks and unknown unknowns, or want to widen overconfident intervals. Use when user mentions premortem, backcasting, what could go wrong, stress test, or black swans.
Multi-role requirement analysis and task breakdown workflow using 4 specialized AI agents (PM, UX, Tech, QA). Each agent conducts web research before analysis to gather industry best practices, case studies, and current trends. Supports Quick Mode (parallel, ~3 min, one Q&A session) and Deep Mode (serial, ~8 min, Q&A after EACH agent so answers inform subsequent analysis). Triggers on 'foreman-spec', 'spec feature', 'break down requirement', 'define tasks', 'spec this'.
Use when justifying technical debt to executives, calculating the cost of quality issues, translating tech metrics to business language, or planning quality budgets - uses research-backed formulas (2-3x defects, productivity multipliers) to convert code problems into dollars and ROI
Spawn parallel AI agents in new terminal windows for true concurrency
Minimal skill for testing context fork behavior. Do not use in production.
Use when user wants to create new autonomy branch from current commit or specific past iteration
Building create/edit forms with FormField components, validation integration, and save patterns