AIエージェントの能力を拡張するClaudeスキルの完全なコレクションをご覧ください。
Automates the end-to-end lifecycle of GitHub Pull Requests by monitoring CI/CD status, fixing regressions, and resolving review comments autonomously.
Guides the creation of new, effective Claude Code Skills to extend Claude's capabilities with specialized knowledge and workflows.
Writes, reviews, and refactors Python 3.11 code to meet high standards for clarity, robustness, and maintainability.
Enforces documentation standards, structure, and best practices for agent-focused repositories.
Manages stacked pull requests and dependent branches using the Graphite (gt) command-line tool.
Executes multi-step implementation plans in controlled batches with built-in review checkpoints and mandatory verification.
Generates comprehensive GitHub issues with embedded TDD plans and autonomous agent instructions for full pull request lifecycle management.
Applies Test-Driven Development principles to create robust, verified process documentation and specialized Claude Code skills.
Enforces a rigorous, four-phase debugging methodology to identify root causes and ensure reliable software fixes without guesswork.
Eliminates flaky tests and race conditions by replacing arbitrary timeouts with smart, deterministic condition polling.
Automates a multi-agent design review process immediately following the creation of design documents to ensure technical and product readiness.
Creates reusable, agent-executable slash commands to automate repetitive developer workflows.
Automates the systematic discovery, resolution, and response to pull request feedback from AI bots and human reviewers.
Validates and stress-tests AI skill documentation using a TDD-inspired Red-Green-Refactor cycle to ensure agent compliance under pressure.
Standardizes a rigorous, technical-first approach to processing and implementing code review feedback without performative agreement.
Automates the execution of multi-step implementation plans by dispatching fresh subagents for each task followed by iterative code reviews.
Ensures application reliability by implementing multi-layered validation patterns that make structural bugs and data corruption impossible to reproduce.
Simplifies the creation, validation, and rendering of secure, reusable web forms using the Nette Framework.
Provides non-invasive PHP debugging, profiling, and execution tracing tools powered by Xdebug.
Enforces high-quality testing standards by identifying and preventing common pitfalls like mock-testing and production code pollution.
Enforces mandatory protocols for skill discovery, brainstorming-first workflows, and task tracking to ensure consistent AI output quality.
Automates the code review process by dispatching specialized subagents to verify implementations against requirements before merging.
Analyzes Claude Code interaction history and Git data through SQL queries to reveal developer productivity patterns.
Manages Tilt development environments and Tiltfile authoring to streamline containerized local development workflows.
Empowers Claude with semantic code navigation and IntelliSense-like capabilities using the Language Server Protocol.
Converts Claude Code and Codex CLI session logs into clean, searchable Markdown transcripts with advanced indexing capabilities.
Orchestrates Vite frontend assets within the Litestar framework to ensure seamless integration between Python backends and modern frontend workflows.
Streamlines the synchronization of Litestar Python backends with Vite frontend assets and development workflows.
Streamlines the development of custom Claude Code skills using official Anthropic best practices and standardized templates.
Debugs and resolves issues within Chrome and Firefox extensions by inspecting content scripts, popups, and service workers.
Scroll for more results...