prompt-improver

prompt-improver is a skill for Claude Code, Codex from yuchenbigpen1/normies. It costs 35 tokens per session (920 once invoked), scanned A, original, Apache-2.0.

A question-asking skill that turns vague business requests into clear requirements. It focuses on goals, constraints, context, and whether an existing product or custom work is the better fit.

In plain words
What is it for?
Use it when a request does not explain the desired outcome, business context, constraints, or whether to build or buy a solution.
Why use it?
It prevents work from starting with an unclear objective or missing important limits. It asks only for information that cannot reasonably be inferred.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it when a request does not explain the desired outcome, business context, constraints, or whether to build or buy a solution.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/yuchenbigpen1/normies/prompt-improver
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add yuchenbigpen1/normies --skill prompt-improver
Clone the repo
git clone --depth 1 https://github.com/yuchenbigpen1/normies

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for prompt-improver

README.md
[![agentmods](https://agentmods.dev/badge/skills/yuchenbigpen1/normies/prompt-improver/github.svg)](https://agentmods.dev/skills/yuchenbigpen1/normies/prompt-improver)
Your own site
<a href="https://agentmods.dev/skills/yuchenbigpen1/normies/prompt-improver"><img src="https://agentmods.dev/badge/skills/yuchenbigpen1/normies/prompt-improver/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for prompt-improver

Your own site · 80×15
<a href="https://agentmods.dev/skills/yuchenbigpen1/normies/prompt-improver"><img src="https://agentmods.dev/badge/skills/yuchenbigpen1/normies/prompt-improver.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 920 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00035 $0.00920
Opus 5 $0.00017 $0.00460
Sonnet 5 $0.00007 $0.00184
Haiku 4.5 $0.00003 $0.00092

Measured 12d ago against content hash 069932f35270, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

prompt-improver scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

packages/shared/assets/workspace-template/skills/prompt-improver/SKILL.md · 123 lines

How it starts

The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Prompt Improver Skill

Purpose

Help non-technical business operators articulate their needs clearly by asking focused, business-relevant questions. This skill is invoked when a request is too vague to determine the right approach (build vs. buy, custom vs. off-the-shelf, etc.).

When This Skill is Invoked

The Explore agent evaluates each user message for clarity. If the request is too vague to determine the right approach, the agent invokes this skill to ask clarifying questions.

Key principle: Most prompts should pass through without interruption. Only truly ambiguous requests trigger this skill.

Core Workflow

Phase 1: Context Review

Before asking questions, review what you already know:

  1. Check conversation history — Has the user already explained their business, team, or goals?
  2. Review any connected sources — Are there existing tools, APIs, or data sources that provide context?
  3. Identify the ambiguity — What specifically is unclear? The goal? The scale? The constraints?

Rules:

  • Never ask about things already discussed in conversation
  • Focus on business context, not technical details
  • If you can reasonably infer intent, just proceed

Phase 2: Ask 1-3 Focused Questions

Based on what's missing, formulate at most 3 questions. Less is better.

Question categories:

Category Example
Goal "What outcome are you looking for?"
Scale "How many people will use this?"
Existing tools "What tools does your team use today?"
Timeline "Is this urgent, or a longer-term improvement?"
Constraints "Are there budget or tool restrictions?"

Question guidelines:

  • Use plain, non-technical language
  • Provide concrete options (multiple choice preferred)
  • Keep descriptions brief — one sentence max
  • Never reference code, files, APIs, or technical concepts

Phase 3: Get Clarification

Use the ask_user_question tool:

questions: [{
  question: "Clear business question ending with ?"
  options: [
    { label: "Plain language (1-5 words)", description: "What this means for them (one sentence)" },
    ...2-4 options total
  ]
  multiSelect: false
}]

Read the full file on GitHub · 123 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 12d ago First seen · 123 lines · 35 tokens per session scan A 069932f35270

Subscribe to this mod's changes

prompt-improver is a skill published in the GitHub repository yuchenbigpen1/normies (4 stars, last pushed 6mo ago), licensed Apache-2.0. It adds 35 tokens to every session and 920 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.