Stats
Actions
Tags
From cursor
Shapes prompts for delegated Cursor agent tasks: names explicit files/commands/errors, prefers --mode plan for fuzzy scopes, asks for plans, keeps under 2k tokens.
How this skill is triggered — by the user, by Claude, or both
Slash command
/cursor:cursor-promptingThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
- Name explicit files, commands, errors, and acceptance criteria when the user provided them.
--mode plan for unfamiliar codebases or fuzzy tasks./cursor:agent was invoked with --context, the natural-language prompt already includes a fixed five-line session block (Goal, Recent decisions, Files touched, Current state, Open question). Facts only; no transcripts, secrets, or code. If nothing concrete exists to summarize, that block is omitted by the slash command—do not invent one in the subagent.Creates, edits, and optimizes skills for Claude Code, including drafting, evaluating with test prompts, iterating on performance, and improving skill descriptions for better triggering accuracy.
npx claudepluginhub felipeinf/cursor-for-claude --plugin cursor