testing
Test development with pytest, fixtures, and integration testing. Use for writing tests, test patterns, coverage, parametrization, and debugging test failures.
Découvrez les skills Développement, comparez leurs dépôts et consultez leurs instructions.
Test development with pytest, fixtures, and integration testing. Use for writing tests, test patterns, coverage, parametrization, and debugging test failures.
Visual design for Guitar Tone Shootout - design tokens, colors, typography, component patterns, and aesthetic principles. Use for UI decisions and styling.
Chrome DevTools MCP for interactive debugging and development. Use for CSS inspection, network debugging, console access, performance profiling, and real-time development iteration.
Development hot reload behavior. Auto-triggered when discussing file watching, rebuilds, or dev server.
Jinja2 SSR pages with HTMX for interactivity, Alpine.js for UI state, and Tailwind CSS for styling. React islands only for complex interactive components (SignalChainBuilder).
HTMX patterns for server-driven interactivity, WebSocket real-time updates, and progressive enhancement
Generate epic progress reports. Use for epic status, story tracking, blocker detection, and progress summaries.
Micro-task development patterns with 50% context budget. Use for task decomposition, context management, escape hatch protocols, and orchestration patterns.
GitHub issue workflow management with gh CLI and native dependency tracking. Use for gh commands, finding next issues, viewing issue dependencies, and claiming issues.
FastAPI backend development with SQLAlchemy 2.0, Pydantic v2, and async Python. Use for API endpoints, database models, migrations, authentication, and background tasks.
Evaluate browser screenshots and page state for errors. Use when verifying features work correctly, detecting error conditions, or validating UI state during browser testing.
Dual-frontend architecture with Astro SSG for static pages and Jinja2/HTMX for dynamic pages. Both coexist intentionally.
Docker and Docker Compose configuration and troubleshooting. Use for containers, services, volumes, networking, health checks, and deployment patterns.
Playwright browser automation and E2E testing. Use for browser testing, screenshots, debugging, MCP tools, page objects, and visual verification.
Create and maintain well-structured Claude Code skills. Use when creating, updating, or improving skills in .claude/skills/.
Git worktree management with worktree.py CLI. Use for creating worktrees, teardown, merging PRs, syncing branches, and Docker service management.
AI-powered PR creation after spec completion. Analyzes spec metadata, git diffs, commit history, and journal entries to generate comprehensive PR descriptions with user approval before creation.
Spec-first development methodology that creates detailed specifications before coding. Creates structured specs with phases, file-level details, and verification steps. Includes automatic AI review, modificatio...
Fast-capture intake queue for ideas and follow-up tasks. Add items quickly, list pending items, or dismiss resolved ones.
Systematic test debugging with 5-phase investigation workflow. Use when debugging test failures, investigating complex errors, or when AI consultation would help. Uses native test commands with optional AI cons...
Safe refactoring operations using LSP for precise symbol resolution. Supports rename, extract function/method, and move symbol operations with automatic reference updates.
Review implementation fidelity against specifications by comparing actual code to spec requirements. Identifies deviations, assesses impact, and generates compliance reports for tasks, phases, or entire specs.
First-time setup for the foundry plugin (plugin:foundry@claude-foundry)
AI-powered research skill with five workflows - chat (single-model conversation), consensus (multi-model synthesis), thinkdeep (systematic investigation), ideate (creative brainstorming), and deep (multi-phase...
Le classement utilise les étoiles du dépôt GitHub indexé. Plusieurs skills peuvent partager ce nombre : ce n’est ni un nombre d’installations ni une note de qualité.