| name | composer-prompting |
| description | Internal guidance for shaping a well-specified coding task into a tight Cursor/Composer prompt before delegating it via /cursor:delegate |
| user-invocable | false |
Composer Prompting
Use this skill when the cursor-runner subagent (or the main Claude thread) needs to turn a well-specified coding task into a prompt for the Cursor CLI (cursor-agent, Composer by default).
Cursor has no conversation context — whatever the target repo expects, you must bake into the prompt you send. Prompt Composer like a fast executor with a precise contract, not a collaborator you can clarify with mid-run. State the goal, the exact end state, the files it may touch, and how "done" is verified.
Ground the prompt in the target repo first
Before writing the prompt, use Read (only) to check the target repo for:
AGENTS.md, CLAUDE.md, .cursor/rules/**, .github/copilot-instructions.md, CONTRIBUTING.md — convention files.package.json / Taskfile.yml / Makefile / justfile — to learn which commands build and test the project.README.md — for the overall project goal (one sentence is enough).
Language and style follow the target repo, not this plugin. If the repo's commits, comments, or UI strings are in Czech / German / any other language, Composer must match — do not force English. If the repo is mixed (code in English, user copy in Czech), say so explicitly. When in doubt, tell Cursor: "match the existing style of surrounding files."
References — read the one you need
Assembly checklist
- Ground the prompt in the target repo's conventions and verify commands.
- Write the five sections plus the guardrails block, in order (see prompt-anatomy).
- Chunk anything bigger than one reviewable slice (see model-selection).
- Pick the smallest model that fits; default to
composer-2.5-fast.
- Decide resume vs fresh.
- Remove redundant instructions before sending.
