A specification alignment tool that monitors for drift between specifications and implementation during development. It detects scope creep, missing features, and contradictions, then logs decisions to spec README files for traceability and conscious decision-making.

A constitution validation skill that creates project governance rules by exploring your codebase to discover actual patterns and conventions. It supports three rule levels (L1 critical, L2 blocking, L3 advisory) and generates compliance reports to enforce security, architecture, code quality, and testing standards.

A specification validation skill that ensures quality of PRDs, SDDs, and implementation plans using the 3Cs framework (Completeness, Consistency, Correctness). It can validate individual files, compare implementations against specifications, check cross-document alignment, and validate understanding of design decisions.

A specification workflow orchestrator that creates and manages numbered specification directories. It tracks user decisions through product requirements, solution design, and implementation planning phases while maintaining README.md files to log context and progress.

Safe Refactoring provides a structured methodology for improving code quality without changing functionality. It includes a code smells catalog, refactoring patterns reference, and enforces behavior preservation through mandatory test validation before and after each change.

A product requirements specialist skill that helps create and validate Product Requirements Documents (PRDs). It provides structured templates, EARS-formatted acceptance criteria patterns, multi-angle validation workflows, and iterative review cycles to ensure comprehensive requirements documentation.

This skill helps developers document and organize knowledge discovered during development work. It categorizes information into business rules (domain), technical patterns, and external service interfaces, with built-in deduplication to prevent fragmented documentation.

This skill ensures code implementations match documented specifications (PRD, SDD, implementation plans). It checks interface contracts, data structures, business logic, and architecture decisions against requirements, then provides structured compliance reports with deviation classification (critical, notable, acceptable).

This skill helps create detailed implementation plans that break down software features into executable tasks following Test-Driven Development (TDD) principles. It provides templates, examples, and validation checklists to ensure plans are complete, traceable to specifications, and can be followed independently by developers.

A git workflow specialist that provides consistent version control operations across the development lifecycle. It handles branch creation with naming conventions, generates conventional commit messages, creates pull requests with spec-based descriptions, and manages branch lifecycle with safety checks for uncommitted changes.

A systematic analysis workflow that helps you discover patterns, business rules, and technical interfaces in codebases through iterative cycles. It delegates investigation to specialist agents and produces organized documentation in domain, patterns, and interfaces categories.

A debugging methodology skill that applies scientific investigation principles through natural conversation. It guides users through systematic bug diagnosis including hypothesis formation, evidence gathering, root cause analysis, and fix verification while maintaining user control over the investigation direction.

A solution design specialist skill that helps create and validate Solution Design Documents (SDDs). It provides templates, validation checklists, and a structured workflow for documenting technical architecture, interfaces, and design decisions through iterative discovery, documentation, and review phases.

This skill helps manage complex implementation plans by breaking them into phases and executing tasks systematically. It tracks progress with TodoWrite, handles parallel task delegation to agents, validates checkpoints before proceeding, and always pauses for user confirmation between phases.

Vexor CLI is a semantic file discovery skill that helps locate files by intent rather than exact text matching. It wraps the vexor command-line tool to enable natural language queries like 'find authentication logic' across codebases, using embedding providers (OpenAI, Gemini, or local models) for semantic search.

A comprehensive reference guide for thought-based reasoning techniques in LLMs. Covers Chain-of-Thought prompting, Zero-shot CoT, Self-Consistency, Tree of Thoughts, ReAct, PAL, and Reflexion with prompt templates, decision matrices, and best practices for improving complex reasoning tasks.

A comprehensive reference guide for understanding and optimizing context in LLM agent systems. Covers context anatomy, degradation patterns, multi-agent verification workflows, and optimization techniques like compaction and observation masking.

A comprehensive evaluation framework for assessing Claude Code agents, commands, and skills. Provides LLM-as-Judge implementation patterns, multi-dimensional rubrics, bias mitigation techniques, and metrics for measuring agent quality across instruction following, completeness, tool efficiency, reasoning, and coherence.

A comprehensive reference guide for designing multi-agent architectures in Claude Code. It covers three main patterns (supervisor/orchestrator, peer-to-peer/swarm, and hierarchical), along with context isolation strategies, consensus mechanisms, failure mode mitigations, and memory system designs ranging from simple file-based to temporal knowledge graphs.

Use this skill when you writing commands, hooks, skills for Agent, or prompts for sub agents or any other LLM interaction, including optimizing prompts, improving LLM outputs, or designing production prompt templates.

Use when Code implementation and refactoring, architecturing or designing systems, process and workflow improvements, error handling and validation. Provide tehniquest to avoid over-engineering and apply iterative improvements.

Use when executing implementation plans with independent tasks in the current session or facing 3+ independent issues that can be investigated without shared state or dependencies - dispatches fresh subagent for each task with code review between tasks, enabling fast iteration with quality gates

Use when implementing any feature or bugfix, before writing implementation code - write the test first, watch it fail, write minimal code to pass; ensures tests actually verify behavior by requiring failure first

This skill transforms YouTube videos from your favorite channels into polished magazine-style articles. It fetches video transcripts, uses Claude AI to rewrite them as engaging long-form content, and delivers them as EPUB ebooks via email newsletter with optional web dashboard management.

Ultimate Bug Scanner (UBS) is a comprehensive static analysis tool that automatically scans your code for bugs, security issues, and code quality problems. It integrates with Claude Code via hooks to run scans on file saves and blocks dangerous git commands like 'git reset --hard' or 'rm -rf' to prevent accidental data loss.

Mviz is a data visualization skill that generates clean, professional charts and dashboards from compact JSON specifications or markdown files. It supports 17+ chart types (bar, line, scatter, heatmap, sankey, etc.) and 8 UI components, using a 16-column grid layout system with light/dark theme support.

Use when user wants to execute long-running tasks that require multiple sessions to complete. This skill manages task decomposition, progress tracking, and autonomous execution using Codex non-interactive mode with auto-continuation. Trigger phrases include autonomous, long-running task, multi-session, 自主执行, 长时任务, autonomous skill.

This skill helps Claude Code generate valid macOS/iOS Shortcuts (.shortcut files) by providing comprehensive documentation on the plist format, 1,155+ available actions, variable references, and control flow patterns. Generated shortcuts are signed using the built-in macOS 'shortcuts' CLI tool for import into Apple's Shortcuts app.

Wield Google's Gemini CLI as a powerful auxiliary tool for code generation, review, analysis, and web research. Use when tasks benefit from a second AI perspective, current web information via Google Search, codebase architecture analysis, or parallel code generation. Also use when user explicitly requests Gemini operations.

Generate structured agent prompts with FOCUS/EXCLUDE templates for task delegation. Use when breaking down complex tasks, launching parallel specialists, coordinating multiple agents, creating agent instructions, determining execution strategy, or preventing file path collisions. Handles task decomposition, parallel vs sequential logic, scope validation, and retry strategies.