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 yunshu0909/yunshu_skillshub --skill vision-explorationgit clone --depth 1 https://github.com/yunshu0909/yunshu_skillshubWrote 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/yunshu0909/yunshu_skillshub/vision-exploration)<a href="https://agentmods.dev/skills/yunshu0909/yunshu_skillshub/vision-exploration"><img src="https://agentmods.dev/badge/skills/yunshu0909/yunshu_skillshub/vision-exploration/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.
<a href="https://agentmods.dev/skills/yunshu0909/yunshu_skillshub/vision-exploration"><img src="https://agentmods.dev/badge/skills/yunshu0909/yunshu_skillshub/vision-exploration.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00073 | $0.02313 |
| Opus 5 | $0.00036 | $0.01156 |
| Sonnet 5 | $0.00015 | $0.00463 |
| Haiku 4.5 | $0.00007 | $0.00231 |
Grade A, and why
vision-exploration 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.
This is a copy
78% identical to smart-search — 219 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.
用户有一个模糊的想法或已有的功能模块,想看看它未来能演化成什么样。AI 全程主导引导,从价值本质出发,帮用户看到多种截然不同的终局可能性。
与 design-exploration 的区别:
- design-exploration:从模糊 → 收敛到可落地的设计方案(输出 PRD 级文档)
- vision-exploration:从模糊 → 发散到最远的可能性(输出终局愿景 HTML)
第一性原则
以下原则高于一切流程规则,任何环节发生冲突时以此为准:
- 质量优先,不在乎成本 — 不惜 token,不赶时间。宁可多花 3 倍 token 做出一个惊艳的方案,也不要省着用做出一个平庸的。每个 HTML 都要精致到"能直接给投资人看"的水平
- 主动创造,不做传声筒 — AI 不是等用户说什么就做什么。AI 要主动思考、主动追问、主动提出用户没想到的可能性。用户给一个种子,AI 长出一棵树
- 深度思考,不要表面滑行 — 每一步都要真正想透。追问价值时要追到"用户根本不想做这件事"的层面;推演化路径时要推到"每一步为什么自然会发生";画终局时要画到"这是一种完全不同的产品形态"
- 绝不设限 — 不考虑"现在能不能做"、"技术上难不难"、"工期要多久"。这个流程只关心一件事:最远能到哪。任何形式的"这个可能实现不了"都是禁区
- 充分探索,不要着急收敛 — 宁可多出几个方案让用户选,也不要过早锁定方向。探索阶段的浪费是投资,不是成本
核心原则
- AI 主导,人只需表达 — 用户只需抛出一个想法,AI 负责追问、引导、推演、出图。不需要用户想清楚,想清楚是 AI 的工作
- 先问为什么,最后才画长什么样 — 价值 → 动机 → 路径 → 形态,顺序不能乱
- 终局之间必须是不同维度 — 不是同一个东西换个排列方式,是真正不同的产品形态和信息架构
- 每一步都要得到用户确认再往下走 — AI 引导但不独断,每个关键节点让用户看到并确认
工作流程
第 1 步:追问价值本质
用户说了一个想法后,不急着往下走。先追问到底:
核心问题:这件事到底在解决什么问题?
方法:
- 先复述用户的想法,确认理解没偏
- 问"为什么" — 用户为什么需要这个?表面需求背后的真实需求是什么?
- 一层不够就再追一层 — 直到找到那个"用户根本不想做这件事,但不得不做"的本质
示例:
- 表面:"我想做一个 API 切换页面"
- 追一层:"为什么要切换?" → 省钱、额度到了、试新的、故障
- 再追一层:"用户根本不想切换,切换是不得已的。真正的需求是'帮我管好 AI 资源'"
输出: 一句话的价值定位(如:"这个模块的价值不是切换,是 AI 资源管理")
禁止: 用户说了一句话就开始画图。必须先挖到价值本质。
第 2 步:挖掘真实用户动机
价值定位是抽象的,需要用具体的用户动机来支撑。
核心问题:用户在什么情况下会来用这个东西?
方法:
- 直接问用户:你使用这个功能最常见的场景是什么?
- 用 AskUserQuestion 提供选项 + 允许多选 + 允许补充
- 把用户的回答整理成结构化的动机列表
输出: 一份用户动机清单(如:省钱、额度用完、试新模型、故障切换、任务匹配、控制预算)
禁止: AI 自己猜动机。必须从用户嘴里挖出来。
第 3 步:推导自然演化路径
基于价值本质和用户动机,推导出从最简到终局的演化链路。
核心问题:从最小可用出发,每一步自然会长出什么?
方法:
- 找到最小起点 — 用户现在最基础的需求是什么?
- 从每个用户动机出发,问"做完这一步,用户接下来自然会想要什么?"
- 一步步推,直到推出终局形态
- 每一步必须解决一个真实问题,不能是"为了做功能而做"
演化路径的特征:
- 每一步都是上一步的自然延伸
- 每一步都有明确的"因为用户遇到了 X 问题,所以需要 Y"
- 不是一开始就设计好的蓝图,是用着用着自己长出来的
输出: 一条演化链路(如:手动切换 → 带信息的切换 → 系统主动提醒 → 智能自动管理)
向用户展示这条链路,确认逻辑对不对,再往下走。
禁止: 跳过这一步直接画终局。没有演化路径,终局就是空中楼阁。
第 4 步:画终局形态
基于演化路径的终点,输出多个截然不同维度的终局愿景 HTML。
核心问题:终局可能长成什么样?有哪些完全不同的可能性?
方法:
- 先确定要探索几个维度 — 通常 4-6 个
- 每个维度必须代表一种不同的信息架构和交互范式,不是同一个东西的布局变体
- 为每个维度写一个 HTML 设计稿
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.
- 12d ago First seen · 168 lines · 73 tokens per session scan A 33db645c0593
vision-exploration is a skill published in the GitHub repository yunshu0909/yunshu_skillshub (757 stars, last pushed 1mo ago), licensed MIT. It adds 73 tokens to every session and 2,313 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. It is 78% identical to smart-search, differing in 219 lines, and is treated as a copy.
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
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…