curl -fsSL https://api.cheatcodehq.com/install.sh | sh -s -- claude-code-prompt-improver --to allCopies 1 skill into each app's skills folder (Claude Code: ~/.claude/skills), after checking every file against severity1/claude-code-prompt-improver at commit 306c325. Nothing else on your computer changes. To undo it, run the terminal command with --uninstall at the end; that also removes what the app added.
Then start a new session in your AI app and ask for the work in plain words; it picks the skill from its description. In Claude Code you can also type /claude-code-prompt-improver:prompt-improver.
See it in use
After installing, start a new session and say: Use the prompt-improver skill to improve this request before acting on it: fix the bug.
What else it can do, and its limits
- Normally a hook that reads every prompt and decides whether it is too vague to act on, then asks 1 to 6 grounded multiple-choice questions with AskUserQuestion before proceeding
- The listed package ships the skill half only, not the hook that invokes it automatically; this run invoked the skill directly
- This session had no AskUserQuestion tool, so it wrote down the questions and its chosen answers instead of asking them, then proceeded
- Research normally runs through an Explore subagent; with none available here it searched and read the files directly
- Needs no install beyond the plugin; runs no external script and calls no network service
- Skips straight to work when a prompt is already specific; only a vague one triggers the research-and-clarify flow
Sample input Recorded Oct 28, 2026 in Claude Code 2.1.309 with Sonnet 5.5. The video replays that session; nothing in it was acted or edited.
What's inside 1 skill
prompt-improverThis skill enriches vague prompts with targeted research and clarification before execution. Should be used when a prompt is determined to be vague and requires systematic research, question generation, and execution guidance.
This skill enriches vague prompts with targeted research and clarification before execution. Should be used when a prompt is determined to be vague and requires systematic research, question generation, and execution guidance.
About
Something wrong with this listing, or it did not install? Tell us