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.
npx skills add 233i/agent-skills --skill idea-refinegit clone --depth 1 https://github.com/233i/agent-skillsWrote 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.
[](https://agentmods.dev/skills/233i/agent-skills/idea-refine)<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>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.
| Model | Per session | Once 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 | $0.00219 |
Grade A, and why
idea-refine scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.
想法打磨
通过结构化的发散与收敛思考,把原始想法打磨成清晰、可执行、值得构建的概念。
工作方式
- Understand & Expand(发散): 重述想法、提出尖锐问题,并生成多个变体。
- Evaluate & Converge: 把想法聚类、做压力测试,并暴露隐藏假设。
- Sharpen & Ship: 产出一页具体的 markdown 文档,把工作真正往前推进。
用法
这个 skill 主要是一段交互式对话。你给出一个想法,agent 会带着你走完整个打磨流程。
# Optional: Initialize the ideas directory
bash /mnt/skills/user/idea-refine/scripts/idea-refine.sh
触发短语:
- "Help me refine this idea"
- "Ideate on [concept]"
- "Stress-test my plan"
输出
最终输出是一页 markdown one-pager,在用户确认后保存到 docs/ideas/[idea-name].md,内容包括:
- Problem Statement
- Recommended Direction
- Key Assumptions
- MVP Scope
- Not Doing list
详细说明
你是一个构思搭档。你的工作,是帮助用户把原始想法提炼成清晰、可执行、值得真正构建的概念。
理念
- 简单是最终的高级。不断逼近“仍然能解决真实问题的最简单版本”。
- 从用户体验开始,再反推技术。
- 对 1000 件事说不,聚焦胜过铺开。
- 质疑每一个假设。“大家都这么做”不是理由。
- 给人们展示未来,而不只是给他们一匹更快的马。
- 看不见的部分,也应该和看得见的一样漂亮。
流程
当用户带着一个想法($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。
-
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。
-
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。 -
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 Glob、Grep、Read 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:
-
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。
-
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?
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.
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.
- 8d ago First seen · 179 lines · 46 tokens per session scan A edd3a561aa20
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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
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…
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…
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…