Menu
Use `author-command` to get OpenCode Command Authoring when writing or reviewing OpenCode command markdown.
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
| name | author-command |
| description | Use `author-command` to get OpenCode Command Authoring when writing or reviewing OpenCode command markdown. |
Use this guide when writing or reviewing OpenCode command markdown.
.opencode/commands/{name}.md~/.config/opencode/commands/{name}.mdCommand file is raw markdown with YAML frontmatter.
---
description: Short command summary.
agent: agent-name (optional)
model: provider/model (optional)
---
$ARGUMENTS
---------
COMMAND PROMPT
Frontmatter keys:
description: short command summary.agent: agent name. Optional.subtask: false (if need context of session); true (isolated session)tier: Non-creative task -> fast; project changes -> balanced; complex/planning/design task -> smartBody:
$ARGUMENTS where user args belong. Prefer to separate with --------- to avoid confusion with fixed COMMAND PROMPT.Use `author-caveman` to write Caveman English.
Use `author-agent` to get OpenCode Agent Authoring when writing or reviewing OpenCode agent markdown.
Use `author-rules` to write `AGENTS.md` files.
Use `author-skill` to get Skill File Authoring when you need to review/write skill files for agents.
Use `design-prd` to get Product Requirements when planning any feature or to understand project business requirements, user roles, and success criteria.
Use `execute-code` to get "Technical Design" when you must design technical tasks, implement features or refactor code.