dotfiles

Use for GitHub operations: creating issues, posting issue comments, creating draft PRs, and adding PR review comments.

Facilitate structured divergent idea generation using the SCAMPER technique (Bob Eberle). An orchestrator elicits a concrete target, applies seven transformation lenses (Substitute, Combine, Adapt, Modify, Put to another use, Eliminate, Reverse) in parallel via focused subagents, then converges into evaluated, prioritized ideas. Use when the user asks for a SCAMPER analysis, systematic ideation, or improvement ideas for an existing product, service, process, or idea.

Facilitate structured multi-perspective analysis using Edward de Bono's Six Thinking Hats. A Blue Hat orchestrator applies one hat at a time in sequence over a single shared record, using five focused hat subagents. Use when the user asks for a Six Hats or 6 hat analysis, a multi-perspective breakdown of a decision, idea, or problem, or systematic structured thinking on a topic.

Author markmap-format Markdown. Use when writing a mindmap (マインドマップ / markmap) in Markdown.

Sample skill for verifying plugin wiring. Trigger when the user asks to run the sample greeting or test the sample plugin.

Use when resolving or addressing PR review comments.

Use for GitHub operations: creating issues, posting issue comments, creating draft PRs, and adding PR review comments.

Use for GitHub operations: creating issues, posting issue comments, creating draft PRs, and adding PR review comments.

Create a git commit from current changes. Trigger on commit requests or after completing a code change task.

Create a git commit from current changes. Trigger on commit requests or after completing a code change task.

Create a git commit from current changes. Trigger on commit requests or after completing a code change task.

Defines where to save work-in-progress artifacts (design, plan, research, temporary files) so output paths stay consistent. Use when saving a design, plan, research note, or temp script, or when running /deep-read, /write-plan, or superpowers (brainstorming/writing-plans).

Process `REVIEW:` inline comments left in code after implementation review. Fix each comment locally and remove it. Use after execute-plan when a human has added `REVIEW:` annotations to the codebase.

Generate AWS architecture diagrams in Mermaid. Invoke when the user asks to draw, design, or document AWS architecture as Mermaid.

Orchestrate work by delegating to sub-agents. Main agent handles only planning, judgment, and user communication. Always active for multi-step work.

Route work through bounded subagents. Use when tasks require codebase investigation, code changes, tests, lint, build, or multi-step validation.

Implement the plan defined in a planning file. Use only after the plan is fully reviewed and approved.

Create or refine a planning file. Use to start the planning phase or to reflect inline annotations back into an existing plan.

Implement the plan defined in a planning file. Use only after the plan is fully reviewed and approved.

Create or refine a planning file. Use to start the planning phase or to reflect inline annotations back into an existing plan.

Process `REVIEW:` inline comments left in code after implementation review. Fix each comment locally and remove it. Use after execute-plan when a human has added `REVIEW:` annotations to the codebase.

Deeply read and understand a specified target, producing a structured research document. Use before the planning phase to prevent uninformed changes.

Deeply read and understand a specified target, producing a structured research document. Use before the planning phase to prevent uninformed changes.

Provides additional review criteria to augment the standard code review workflow. Use when performing code review to check design compliance, security, quality, performance, testing, and best practices.

Search markdown knowledge bases, notes, and documentation using QMD. Use when users ask to search notes, find documents, or look up information.

Route shell, file reads, HTTP, and data analysis through context-mode MCP tools (ctx_ prefix) to protect the context window. Activate when context-mode is connected or on "ctx" commands.

Stress-test a plan or design by grilling the user with tough, methodical questions. Trigger on "grill me" or requests to challenge/critique a plan.

Use when creating or updating ADR files in docs/adr/. Also use when making an architectural decision to evaluate whether an ADR should be written.

Use when writing or reviewing code in Bash, Go, Python, Rust, or TypeScript to enforce coding standards.

Use when writing, updating, or creating any Markdown file. Applies to all documentation including design docs and reports.

Use when implementing new features, fixing bugs, or writing any production code. Enforces red-green-refactor workflow. Does not apply to documentation, configuration, or non-code file edits.

Use when resolving or addressing PR review comments.

Strip all filler, pleasantries, and hedging from responses while keeping full technical substance. Trigger on "caveman", "less tokens", "be brief", or requests for token-efficient output.

Use when writing or reviewing code in Bash, Go, Python, Rust, or TypeScript to enforce coding standards.

Use when writing, updating, or creating any Markdown file. Applies to all documentation including design docs and reports.

Use when implementing new features, fixing bugs, or writing any production code. Enforces red-green-refactor workflow. Does not apply to documentation, configuration, or non-code file edits.

Rules for creating and managing docs/planning.md.

Orchestrate work by delegating to sub-agents. Main agent handles only planning, judgment, and user communication. Always active for multi-step work.

Use when creating or modifying devcontainer configuration files in .devcontainer/ to apply project-specific JSONC format policy.

Use when creating or modifying custom agent files in .config/copilot/agents/ to enforce sub-agent pattern and tool property rules.