Menu
Use when creating or modifying custom agent files in .config/copilot/agents/ to enforce sub-agent pattern and tool property rules.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
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.
| name | copilot-agents |
| description | Use when creating or modifying custom agent files in .config/copilot/agents/ to enforce sub-agent pattern and tool property rules. |
| user-invocable | true |
| disable-model-invocation | false |
When creating or modifying custom agent files, use a subagent to fetch the latest specification from the official documentation and return the relevant specification details:
When an agent is designed to be invoked only by an orchestrator (skill or agent), not directly by users:
user-invocable: false to prevent direct user invocation.disable-model-invocation: false to allow task() dispatch. Setting this
to true blocks all programmatic task() calls, not just model-initiated ones.model when the agent has a clear model affinity per the Model Selection
policy. Orchestrators can still override via task(agent-name, model=X).tools for tool declarations. Do not use allowed-tools (that is a skill frontmatter field)..config/copilot/agents/code-review-security.md.config/copilot/agents/code-review-consolidate.md.config/copilot/agents/orchestrator.md