Discover Documentation skills, compare source repositories and read the instructions for each workflow.
Strategic planner that creates detailed implementation plans without writing code. Operates in Interview Mode to gather requirements, then produces self-contained plans in .sisyphus/plans/. Use when user needs...
Orchestrates complex multi-step work by delegating to specialist subagents. NEVER implements directly—only breaks down tasks, manages todos, delegates via Task tool, and verifies completion. Use when coordinati...
Deep module investigation using Amp's Search for discovery, oracle for expert analysis, and mermaid for visualization. Use when you need to understand complex code, prepare for refactoring, or debug issues.
Enables Claude to read, manipulate, and fill out PDF forms
Provides a deep understanding of chemistry through a technical-philosophical approach, for research and education tasks. In research tasks, you will use technical and logical understanding of the subtopics of t...
Comprehensive computational mathematics toolkit for Claude Code agents. Provides tools for five core domains from MIT's Mathematics for Computer Science curriculum - Proofs (propositions, predicates, induction,...
State checkpointing, divergence detection, and confidence tracking for Hopper/Hardin doctrine compliance. Use PROACTIVELY when performing multi-step reasoning, external actions, or any task requiring error reco...
Shell prompt to Claude Code statusLine mirroring. Parses Bash PS1, Zsh PROMPT, Fish fish_prompt, and PowerShell prompt functions to generate compatible statusLine configuration. Use when users want their termin...
Creates detailed implementation plans with atomic steps, model selection per step, dependency labels, and embedded TDD specifications
Executes implementation plans by dispatching agents based on step dependencies, following TDD with tests written before implementation
Conversational brainstorming that refines ideas through targeted questions, triggers codebase exploration, and prepares context for planning
マルチモデルコードレビュー。LLMがコードレビューを行った後、GitHub Copilot CLIに精査させて双方の視点を統合した最終レビューを提供。Use when user wants multi-model code review, second opinion, or wants to cross-ch...
Unity Editor operations via unity-mcp-client CLI. Handles build verification, console logs, tests, scene/object manipulation. Use after script edits or for debugging.
Git commit creation assistant with gitmoji prefixes and Japanese messages. Supports two modes staged-only (commits only staged changes) and smart-commit (analyzes all changes and creates multiple commits with a...
Use when user requests spaced-repetition flashcards from a documentation/article URL or wants to merge/update an existing flashcard vault file - enforces strict card-only output formatting, deep-link footnote c...
Use when making architectural decisions or critically reviewing an existing system/implementation - identifies the right abstractions, surfaces gaps/risks, evaluates tool/technology trade-offs, and produces imp...
Generate Sit Spot Club daily lessons and audio scripts in the Sit Spot Club voice. Use for daily lessons, sit spot practices, sensory awareness curriculum, and guided audio scripts.
明示的に呼び出されたときにのみ読み込みます。エージェントが自律的に呼び出す必要はありません。
明示的に呼び出されたときにのみ読み込みます。エージェントが自律的に呼び出す必要はありません。
Run static analysis, security scans, and dependency checks on .NET code. Use when task involves code quality, security audits, or vulnerability detection.
Build and orchestrate tasks using Nuke build system. Use when task involves running Nuke build targets, orchestrating complex build workflows, or managing build pipelines.
Run .NET tests using dotnet CLI. Use when task involves executing unit tests, generating code coverage reports, or running benchmarks.
Format code using dotnet format, prettier, and other formatting tools. Use when task involves code style fixes, formatting consistency, or preparing code for commit.
Build .NET solution/projects using dotnet CLI. Use when task involves compiling, restoring dependencies, or building artifacts.
The default order uses GitHub repository stars from our indexed data. Stars belong to the source repository and may be shared by multiple skills. They indicate repository interest, not skill installs or an independent quality score.