Menu
Create a custom agent (.agent.md) for a specific job.
Installer avec Codex ou Claude Copiez ce prompt, collez-le dans Codex, Claude ou un autre assistant, puis laissez-le vérifier la page du skill et l'installer pour vous.
Basé sur la classification professionnelle SOC
Agents window architecture — covers the agents-first app, layering, folder structure, chat widget, menus, contributions, entry points, and development guidelines. Use when implementing features or fixing issues in the Agents window.
Use when adding, modifying, or reviewing VS Code configuration policies. Covers the full policy lifecycle from registration to export to platform-specific artifacts. Run on ANY change that adds a `policy:` field to a configuration property.
Act on user feedback attached to the current session. Use when the user submits feedback on the session's changes via the Submit Feedback button.
Use when running VS Code smoke tests or working on smoke-test CI steps. Covers npm run smoketest / smoketest-no-compile, grep filtering tests, and a temporary repeat-loop technique for tracking down flaky smoke tests in CI.
Use when working on the Chat Customizations editor — the management UI for agents, skills, instructions, hooks, prompts, MCP servers, and plugins.
Investigate and fix CI failures on a pull request. Use when CI checks fail on a PR branch — covers finding the PR, identifying failed checks, downloading logs and artifacts, extracting the failure cause, and iterating on a fix. Requires the `gh` CLI.
| name | create-agent |
| description | Create a custom agent (.agent.md) for a specific job. |
| argument-hint | What job should this agent do and how? |
| disable-model-invocation | true |
Related skill: agent-customization. Load and follow agents.md for template and principles.
Guide the user to create an .agent.md.
First, review the conversation history. If the user has been using the agent in a specialized way (e.g., restricting tools, following a specific persona, focusing on certain file types), generalize that into a custom agent. Extract:
If no clear specialization emerges from the conversation, clarify:
Remember to follow the agent-customization guidelines to create highly effective agents.
