improve-prompt

improve-prompt is a skill for Claude Code, Codex from AcKeskin/contexture. It costs 113 tokens per session (2,434 once invoked), scanned A, original, MIT.

An interview-based editor for improving prompts used with language, image, video, or audio models.

In plain words
What is it for?
It helps rewrite an existing prompt and briefly explain the changes, across different AI vendors and model types.
Why use it?
It removes ambiguity about the task, context, output format, and success criteria so the model has fewer things to guess.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: names the AskUserQuestion tool.

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.

agentmods
npx agentmods add skills/ackeskin/contexture/improve-prompt
Any agent
npx skills add AcKeskin/contexture --skill improve-prompt
Clone the repo
git clone --depth 1 https://github.com/AcKeskin/contexture

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 improve-prompt

README.md
[![agentmods](https://agentmods.dev/badge/skills/ackeskin/contexture/improve-prompt.svg)](https://agentmods.dev/skills/ackeskin/contexture/improve-prompt)
Your own site
<a href="https://agentmods.dev/skills/ackeskin/contexture/improve-prompt"><img src="https://agentmods.dev/badge/skills/ackeskin/contexture/improve-prompt.svg" alt="Measured on agentmods" height="20"></a>
Per session 113 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,434 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00113 $0.02434
Opus 5 $0.00056 $0.01217
Sonnet 5 $0.00023 $0.00487
Haiku 4.5 $0.00011 $0.00243

Measured 2d ago against content hash 728ed13cc2f6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

improve-prompt 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 2d 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.

skills/improve-prompt/SKILL.md · 180 lines

How it starts

The opening of the file, as written. The whole thing — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Improve Prompt

Overview

Turn a vague or under-specified prompt into one that reliably produces the output the user actually wants — for any target model, not just Claude. The skill is model-agnostic: it uses techniques that hold across vendors (OpenAI, Google, Meta, Mistral, Midjourney, Stable Diffusion, Sora, Veo, ElevenLabs, etc.) and only mentions a vendor when a technique is genuinely vendor-specific, flagged as optional.

Core principle: A good prompt removes the model's need to guess. Most weak prompts fail because they leave the task, the context, the output shape, or the success criteria implicit. The job is to make those explicit without bloating the prompt.

This is a collaborator, not an auto-rewriter. Never auto-fire. Never silently rewrite. When the prompt is underspecified, ask before guessing — see The Iron Rule.

When to Use

  • User types /improve-prompt.
  • User pastes a prompt (or describes one) and asks to improve / sharpen / fix / "make it better" / "why isn't this working".
  • User wants help phrasing a request to any AI model — text, image, video, or audio.

Don't use for: writing a prompt from a blank slate where the user hasn't said what they want at all (interview them first about the goal), or for non-prompt copy-editing.

The Iron Rule

DO NOT GUESS AT MISSING INTENT. ASK, THEN REWRITE.

If the prompt is missing something that materially changes the output — the audience, the format, the constraints, the target model's medium — you ask before rewriting. Inventing those details produces a confident rewrite that solves the wrong problem. The exception: if the gap has an obvious, low-risk default, fill it and state the assumption in the rationale so the user can correct it.

Workflow

1. Classify  → text/LLM prompt or generative (image/video/audio)?
2. Diagnose  → score against the relevant dimensions; list what's missing
3. Decide    → gaps that change the output → interview; trivial gaps → assume + flag
4. Rewrite   → produce the improved prompt
5. Explain   → short rationale: what changed, why, and any assumptions made

Read the full file on GitHub · 180 lines

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. 2d ago First seen · 180 lines · 113 tokens per session scan A 728ed13cc2f6

Subscribe to this mod's changes

improve-prompt is a skill published in the GitHub repository AcKeskin/contexture (2 stars, last pushed 1mo ago), licensed MIT. It adds 113 tokens to every session and 2,434 once invoked, about $0.0006 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 2026-09-03.

Related

Other skills, from other repositories

ax-gen

This skill helps an LLM generate correct AxGen code using @ax-llm/ax. Use when the user asks about ax(), AxGen, generators, forward(), streamingForward(), validation, assertions, streaming assertions, field processors, step hooks, self-tuning, or structured outputs. For MCP clients, transports, prompts, resources…

ax-llm/ax · 86 tokens

ax-signature

This skill helps an LLM generate correct DSPy signature code using @ax-llm/ax. Use when the user asks about signatures, s(), f(), field types, string syntax, fluent builder API, validation constraints, or type-safe inputs/outputs.

ax-llm/ax · 57 tokens

ax-llm

This skill helps with using the @ax-llm/ax TypeScript library for building LLM applications. Use when the user asks about ax(), ai(), f(), s(), agent(), flow(), AxGen, AxAgent, AxFlow, signatures, streaming, or mentions @ax-llm/ax.

ax-llm/ax · 68 tokens

ax-playbook

This skill helps an LLM generate correct playbook code using @ax-llm/ax. Use when the user asks about playbook(), AxPlaybook, context playbooks, evolving context, ACE / Agentic Context Engineering, agent.playbook(), or growing/applying task knowledge offline and online with evolve() and update().

ax-llm/ax · 70 tokens

ax-refine

Use this skill when writing or reviewing Ax bestOfN/refine code, reward functions, thresholds, native sample selection, serial attempts, generated advice, and attempt diagnostics.

ax-llm/ax · 38 tokens

prompt-master

Generates optimized prompts for AI tools. Activates only when the user explicitly asks to write, fix, improve, or adapt a prompt for a specific AI tool (LLM, Cursor, Midjourney, image AI, video AI, coding agents, etc.). Does not activate for general conversation, coding tasks, document writing, or other…

nidhinjs/prompt-master · 78 tokens