Claude Code Prompt Improver — Development skill for Claude Code
Intelligent prompt improver hook for Claude Code.
How to install Claude Code Prompt Improver
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open severity1/claude-code-prompt-improver and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Claude Code Prompt Improver does
A UserPromptSubmit hook that enriches vague prompts before Claude Code executes them. Uses the AskUserQuestion tool (Claude Code 2.0.22+) for targeted clarifying questions.
Alternatives in Development
- Prompt Improver — 652 ★
- Claude Gemini Bridge — Intelligent integration between Claude Code and Google Gemini for large-scale code analysis 386 ★
- Dashclaw Quality — Recurring find-and-fix quality pass over the whole DashClaw app — browser smoke (frontend-verify) + code gates 297 ★
README
Claude Code Prompt Improver
A UserPromptSubmit hook that enriches vague prompts before Claude Code executes them. Uses the AskUserQuestion tool (Claude Code 2.0.22+) for targeted clarifying questions.
What It Does
Intercepts prompts and evaluates clarity. Claude then:
- Checks if the prompt is clear using conversation history
- For clear prompts: proceeds immediately (zero overhead)
- For vague prompts: invokes the
prompt-improverskill to create research plan, gather context, and ask 1-6 grounded questions - Proceeds with original request using the clarification
**Result:** Better outcomes on the first try, without back-and-forth.
**v0.4.0 Update:** Skill-based architecture with hook-level evaluation achieves 31% token reduction. Clear prompts have zero skill overhead, vague prompts get comprehensive research and questioning via the skill.
How It Works
sequenceDiagram
participant User
participant Hook
participant Claude
participant Skill
participant Project
User->>Hook: "fix the bug"
Hook->>Claude: Evaluation prompt (~189 tokens)
Claude->>Claude: Evaluate using conversation history
alt Vague prompt
Claude->>Skill: Invoke prompt-improver skill
Skill-->>Claude: Research and question guidance
Claude->>Claude: Create research plan (TodoWrite)
Claude->>Project: Execute research (codebase, web, docs)
Project-->>Claude: Context
Claude->>User: Ask grounded questions (1-6)
User->>Claude: Answer
Claude->>Claude: Execute original request with answers
else Clear prompt
Claude->>Claude: Proceed immediately (no skill load)
end
Installation
**Requirements:** Claude Code 2.0.22+ (uses AskUserQuestion tool for targeted clarifying questions)
Option 1: Via Marketplace (Recommended)
**1. Add the marketplace:**
claude plugin marketplace add severity1/severity1-marketplace
**2. Install the plugin:**
...
Related Skills
Claude Vibes
Claude Code plugin for people who describe what they want and let Claude build it: brand identity, product pla
No Vibes
Claude Code Stop hook that blocks false-success closeouts. Single bash file, jq-only dep, drop-in. Receipts in
Claude Code Boost
Hook utilities for Claude Code with intelligent auto-approval.
Pharn Dev Ship
Run PHARN's build loop in order so the human need not re-type or memorize it: /pharn-dev-plan → human approve
Ship Off
Disable ship-sop auto-mode. Sets trigger.mode to "manual" so the agent-sop Stop hook (sop-stop-drift.sh, user-
Ship On
Enable ship-sop auto-mode. Sets trigger.mode to "auto" in ship-sop.config.json so the agent-sop Stop hook (sop
Related Agents
Calculator
Handles the Salary Calculator's table calculation step — the arithmetic-heavy step where precision matters mos
AI Integration Specialist
Use this agent for AI model integration, prompt engineering, and intelligent code generation features. This ag
Type Safety Reviewer
TypeScript type safety reviewer. Looks for any, unsafe casts, missing Zod schemas at boundaries, type assertio