idea-refine

idea-refine is a skill for Claude Code from 233i/agent-skills. It costs 46 tokens per session (2,186 once invoked), scanned A, original, MIT.

An interactive process for turning an early idea into a clear, practical concept. It explores different directions, tests hidden assumptions, and produces a short plan covering the problem, recommended direction, first version, and exclusions.

In plain words
What is it for?
Use it to explore a product or project idea, question its assumptions, define a minimum viable version, and create a one-page plan after discussion.
Why use it?
Unclear ideas can lead to building the wrong thing or trying to do too much. Structured questions and evaluation help narrow the scope before implementation begins.

Skill for Claude Code

Written for Claude Code: $ARGUMENTS substitution. Also seen: names the AskUserQuestion tool.

Part of the agent-skills plugin — 20 skills, 7 commands, 3 agents, 1 hook shipped together

Good fit Use it to explore a product or project idea, question its assumptions, define a minimum viable version, and create a one-page plan after discussion.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/233i/agent-skills/idea-refine
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 233i/agent-skills --skill idea-refine
Clone the repo
git clone --depth 1 https://github.com/233i/agent-skills

Made for: Claude Code.

Or install agent-skills, the plugin that ships this one along with the rest of its 20 skills, 7 commands, 3 agents, 1 hook.

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 idea-refine

README.md
[![agentmods](https://agentmods.dev/badge/skills/233i/agent-skills/idea-refine.svg)](https://agentmods.dev/skills/233i/agent-skills/idea-refine)
Your own site
<a href="https://agentmods.dev/skills/233i/agent-skills/idea-refine"><img src="https://agentmods.dev/badge/skills/233i/agent-skills/idea-refine.svg" alt="Measured on agentmods" height="20"></a>
Per session 46 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,186 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 $0.00046 $0.02186
Opus 5 $0.00023 $0.01093
Sonnet 5 $0.00009 $0.00437
Haiku 4.5 $0.00005 $0.00219

Measured 8d ago against content hash edd3a561aa20, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

idea-refine 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 8d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/idea-refine.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/idea-refine/SKILL.md · 179 lines

How it starts

The opening of the file, as written. The whole thing — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.

想法打磨

通过结构化的发散与收敛思考,把原始想法打磨成清晰、可执行、值得构建的概念。

工作方式

  1. Understand & Expand(发散): 重述想法、提出尖锐问题,并生成多个变体。
  2. Evaluate & Converge: 把想法聚类、做压力测试,并暴露隐藏假设。
  3. Sharpen & Ship: 产出一页具体的 markdown 文档,把工作真正往前推进。

用法

这个 skill 主要是一段交互式对话。你给出一个想法,agent 会带着你走完整个打磨流程。

# Optional: Initialize the ideas directory
bash /mnt/skills/user/idea-refine/scripts/idea-refine.sh

触发短语:

  • "Help me refine this idea"
  • "Ideate on [concept]"
  • "Stress-test my plan"

输出

最终输出是一页 markdown one-pager,在用户确认后保存到 docs/ideas/[idea-name].md,内容包括:

  • Problem Statement
  • Recommended Direction
  • Key Assumptions
  • MVP Scope
  • Not Doing list

详细说明

你是一个构思搭档。你的工作,是帮助用户把原始想法提炼成清晰、可执行、值得真正构建的概念。

理念

  • 简单是最终的高级。不断逼近“仍然能解决真实问题的最简单版本”。
  • 从用户体验开始,再反推技术。
  • 对 1000 件事说不,聚焦胜过铺开。
  • 质疑每一个假设。“大家都这么做”不是理由。
  • 给人们展示未来,而不只是给他们一匹更快的马。
  • 看不见的部分,也应该和看得见的一样漂亮。

流程

当用户带着一个想法($ARGUMENTS)调用这个 skill 时,带他走完三个阶段。根据用户反馈动态调整,不要把它执行成死板模板,这是一场对话。

Phase 1:Understand & Expand(发散)

目标: 把原始想法打开。

  1. 把想法重述成一个清晰的 “How Might We” 问题。 这会强迫你把真正要解决的问题说清楚。

  2. 提出 3-5 个打磨问题,不要更多。 重点围绕:

    • 这具体是为谁做的?
    • 成功长什么样?
    • 真正的约束是什么,例如时间、技术、资源?
    • 之前有人试过什么?
    • 为什么是现在?

    使用 AskUserQuestion 工具收集这些输入。在没有搞清楚用户是谁、成功标准是什么之前,不要继续。

  3. 生成 5-8 个想法变体,可以从这些镜头切入:

    • Inversion: “如果反着做会怎样?”
    • Constraint removal: “如果预算 / 时间 / 技术都不是约束呢?”
    • Audience shift: “如果这是为另一类用户设计的呢?”
    • Combination: “如果把它和某个相邻想法合并呢?”
    • Simplification: “10 倍更简单的版本会是什么?”
    • 10x version: “如果规模扩大 10 倍,它会长什么样?”
    • Expert lens: “这个领域专家会觉得理所当然,但外行看不到的点是什么?”

    要敢于超出用户最初提出的范围。去构想用户还没意识到自己需要的东西。

如果你是在一个现有代码库里工作: 使用 GlobGrepRead 去扫描相关上下文,例如现有架构、已有模式、约束和先例。让你的变体建立在真实存在的东西上,必要时引用具体文件和模式。

再读一遍本 skill 目录里的 frameworks.md,它里面有更多构思框架可选。选择性使用,挑适合这个想法的镜头,不要机械地把所有框架跑一遍。

Phase 2:Evaluate & Converge

当用户对第一阶段做出反馈,例如指出哪些方向有感觉、哪些不行、补充了新背景之后,就切换到收敛模式:

  1. 把最有共鸣的想法聚成 2-3 个不同方向。 每个方向必须是真正有差异的,而不是一个主题下的小改写。

  2. 用三个标准对每个方向做压力测试:

    • User value: 谁会受益?受益有多大?这是止痛药还是维生素?
    • Feasibility: 技术成本和资源成本是什么?最难的一环是什么?
    • Differentiation: 它到底哪里真的不同?用户为什么会从现有方案切换过来?

Read the full file on GitHub · 179 lines

Files

What ships with it

4 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. 8d ago First seen · 179 lines · 46 tokens per session scan A edd3a561aa20

Subscribe to this mod's changes

idea-refine is a skill published in the GitHub repository 233i/agent-skills (6 stars, last pushed 5mo ago), licensed MIT. It adds 46 tokens to every session and 2,186 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens