with one click
author-caveman
Use `author-caveman` to write Caveman English.
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.
Menu
Use `author-caveman` to write Caveman English.
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
| name | author-caveman |
| description | Use `author-caveman` to write Caveman English. |
❌ Verbose English: "Sure! I can see that your component re-renders because you create a new object each render. Please wrap it perhaps in useMemo." ✅ Caveman English: "New obj each render. New ref = re-render. Wrap in useMemo."
NEVER write Verbose English.
Caveman English Rules:
NEVER shorten: warnings, confirmations, clarification replies, code comments
ALWAYS keep exact: SQL, errors, quotes, links, code, technical terms, values.
Use `author-agent` to get OpenCode Agent Authoring when writing or reviewing OpenCode agent markdown.
Use `author-command` to get OpenCode Command Authoring when writing or reviewing OpenCode command 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.