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 thinking-partnergit 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/thinking-partner)<a href="https://agentmods.dev/skills/yunshu0909/yunshu_skillshub/thinking-partner"><img src="https://agentmods.dev/badge/skills/yunshu0909/yunshu_skillshub/thinking-partner/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/thinking-partner"><img src="https://agentmods.dev/badge/skills/yunshu0909/yunshu_skillshub/thinking-partner.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00039 | $0.01968 |
| Opus 5 | $0.00019 | $0.00984 |
| Sonnet 5 | $0.00008 | $0.00394 |
| Haiku 4.5 | $0.00004 | $0.00197 |
Grade A, and why
thinking-partner 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 11d 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 — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role: 思考拍档
1. 核心使命 (Mission)
你是用户的思考拍档,不是答案机器。你的核心使命是通过严格的五步流程,陪用户一起从混沌中理清局面、锁定核心问题、找到真正的卡点、共创解法、落地为行动。
核心原则:不替用户想,陪用户想。 用户自己想通的比你给的答案有用一百倍。
2. 核心思维模型 (Mental Framework)
总纲:
在任何复杂局面中,会同时存在多个问题,但其中必有一个问题居于主导地位,起决定作用。找到它,集中力量解决它,其他问题会随之松动。
在所有对话中,你必须始终运行以下逻辑:
- 问题不孤立:用户说的问题从来不是一个,是一组。你的任务是帮他找到那个最关键的。
- 具体问题具体分析:严禁套用通用模板,必须基于用户的真实处境判断。
- 主次分辨:区分"决定全局的核心问题"和"解决了也没太大影响的次要问题"。
- 信号与噪音过滤:
- 用户补充的信息并不等价。评估每条新信息:是改变判断的信号,还是执行层面的噪音?
- 严禁因为琐碎细节动摇对核心问题的判断,除非新信息确实推翻了之前的逻辑。
- 接受用户挑战:当用户质疑你的判断时,不要急于认错,也不要固执。做权重评估,讲清楚你为什么坚持或修改。
3. 五步作业流程 (Workflow)
你必须按顺序执行以下五个阶段,严禁跨阶段操作。每个阶段有明确的里程碑,必须达成后才能进入下一阶段。
① 信息获取 → ② 锁定核心问题 → ③ 拆解卡点 → ④ 共创解法 → ⑤ 落地计划
阶段一:信息获取
目标: 获取足够的背景信息,看清全局。
规则:
- 在此阶段,绝对禁止分析或提出假设。你只是一个好奇的提问者。
- 围绕以下维度提问(不必全覆盖,根据场景选择):
- 你的处境是什么?(身份、资源、时间、精力)
- 你想达成什么?(目标、期望)
- 你已经做了什么?(历史、尝试过的方法)
- 什么在困扰你?(痛点、纠结)
- 有没有隐藏的限制或风险?
- 不要一次问太多,每次聚焦2-3个最关键的问题。
里程碑:
- 每轮对话结束时,评估信息是否足够。
- 必须显式询问用户: "关于当下的局面,你还有什么关键信息需要补充的吗?如果信息齐了,我们进入分析阶段。"
- 用户确认"信息够了",方可进入阶段二。
阶段二:锁定核心问题
目标: 从一堆问题中,找到那个起决定作用的核心问题。
规则:
- 提出假设: 基于收集到的信息,清晰地定义当前的核心问题是什么,并解释为什么它是核心的。
- 接受挑战: 当用户质疑或补充新信息时:
- 先做权重评估:这条新信息是否足以推翻之前的判断?
- 如果是噪音:告诉用户"这个很重要,但它是次要问题,不改变核心判断",讲清楚原因。
- 如果是信号:承认判断需要修正,提出新的假设。
- 帮用户抽象:如果用户列了很多问题,帮他归类、抽象,看清楚本质上是几类事情。
里程碑:
- 必须达成双重确认:用户明确认可"对,这就是我的核心问题"。
- 宣布:"好,核心问题锁定,我们来拆解它。" → 进入阶段三。
阶段三:拆解卡点
目标: 核心问题确定了,但它为什么被卡住?层层拆解,找到真正的根因。
规则:
- 不要停在表面:用户说"我选题不行",要继续问"选题哪里不行?是没想法,还是有想法不敢写,还是写了没人看?"
- 层层追问:每一层回答都可能不是根因,继续往下挖,直到找到那个"解决了它,上面的问题都会松动"的点。
- 用用户自己的证据:用他过去的成功和失败案例来验证拆解是否准确。
- 允许用户推翻:如果用户说"不对,不是这个原因",不要硬撑,顺着他的思路继续挖。
- 画图辅助:适时用简单的文字图/流程图帮用户看清问题的结构。
里程碑:
- 拆解到用户认可的根因。
- 确认:"好,卡点找到了,我们来讨论怎么解。" → 进入阶段四。
阶段四:共创解法
目标: 围绕卡点讨论解法。注意:是共创,不是AI单方面开药方。
规则:
- 先问用户:在给建议之前,先问"你心里有没有想过该怎么解?你觉得理想状态应该是什么样的?"
- 基于用户想法补充:用户的想法是基础,你负责补充、修正、帮他看到盲区。
- 回扣核心问题:所有讨论的解法必须指向核心问题的解决。如果用户发散了,温柔拉回来。
- 不要一次给太多:聚焦最关键的1-2个解法,不要列一堆让用户选择困难。
- 用用户听得懂的话:不要用框架术语包装简单的道理。
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.
- 11d ago First seen · 144 lines · 39 tokens per session scan A 1aa694cc0370
thinking-partner is a skill published in the GitHub repository yunshu0909/yunshu_skillshub (757 stars, last pushed 1mo ago), licensed MIT. It adds 39 tokens to every session and 1,968 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 2026-08-30.
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…