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 agentmods add skills/yipng05-max/-skills/problematizationnpx skills add yipng05-max/-skills --skill problematizationgit clone --depth 1 https://github.com/yipng05-max/-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/yipng05-max/-skills/problematization)<a href="https://agentmods.dev/skills/yipng05-max/-skills/problematization"><img src="https://agentmods.dev/badge/skills/yipng05-max/-skills/problematization.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 | $0.00159 | $0.02435 |
| Opus 5 | $0.00079 | $0.01218 |
| Sonnet 5 | $0.00032 | $0.00487 |
| Haiku 4.5 | $0.00016 | $0.00244 |
Grade A, and why
problematization 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 6d 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 — 214 lines — stays where its author put it; the contents beside it link to each section on GitHub.
研究问题化工具(Problematization)
本 skill 基于 Alvesson & Sandberg(2011)的问题化方法论及 Swedberg(2012)的理论想象力框架, 协助研究者完成从"经验现象"到"研究问题"的关键跃迁,并定位该问题在学术对话中的位置。
核心立场:一个好的研究问题不是"这个现象很重要"的断言, 而是"这个现象向某个理论对话提出了某个具体挑战或扩展"的论证。
启动:获取必要信息
触发后,收集以下信息:
必填 1:原始现象或兴趣描述
用户最初的表述,哪怕非常笼统,例如:
"我想研究外卖骑手的工作体验" "AI 替代劳动这个问题很有意思" "基层政府在执行政策时总是有变形,我想搞清楚为什么"
选填 2:已有的初步想法
- 用户已经想过的研究问题表述(哪怕粗糙)
- 初步考虑的理论视角(如果有的话)
- 已经读过的相关文献(如果有)
选填 3:研究约束条件
- 可用的数据来源或田野入口
- 时间周期限制
- 目标期刊类型(C 刊/SSCI)
如果以上信息用户没有提供,在问题诊断阶段基于用户的原始描述推断,并在输出时标注"基于推断"。
执行流程
收到信息后,自动连续执行以下四个阶段,无需每步等待用户确认。
第一阶段:经验问题 vs 研究问题的区分
首先判断用户当前的表述属于哪种类型:
经验问题(描述现象,不指向理论机制)
- 典型形式:"XX 是什么情况""XX 怎么发展的""XX 有哪些影响"
- 问题:可以通过调查/报告/记者采访回答,不需要社会学研究
- 识别信号:问题的答案是"描述性事实",而非"解释性机制"
研究问题(指向理论机制,对学科知识有贡献)
- 典型形式:"在什么条件下 A 导致 B""XX 现象如何修正/挑战/扩展了理论 Y"
- 问题:需要系统的方法论和理论分析才能回答
- 识别信号:问题的答案会让读者"哦,原来如此,我之前以为是另一回事"
输出格式:
【当前表述类型诊断】
类型:经验问题 / 研究问题(初步)/ 研究问题(较成熟)
诊断依据:当前表述能通过什么方式回答?答案是描述性的还是解释性的?
主要问题:当前表述缺少什么才能成为真正的研究问题?
第二阶段:理论对话定位
无论当前处于哪个阶段,帮助用户识别这个现象与哪些理论对话相关:
2.1 识别候选理论对话
列出 2-4 个与该现象相关的理论脉络,每个脉络说明:
- 核心问题:这个理论脉络在争论什么?
- 现有共识:学界目前对什么基本达成一致?
- 未解问题:这个脉络中还有什么重要问题悬而未决?
- 与当前现象的关联:这个现象如何与该理论对话产生交集?
2.2 定位研究问题的介入点
针对每个候选理论对话,分析该研究可能的介入方式:
| 介入类型 | 含义 | 你的研究能做到吗? |
|---|---|---|
| 验证型 | 在新经验场景中检验已有理论的适用性 | 贡献较小,但对特殊情境有意义 |
| 修正型 | 发现已有理论的边界条件或例外,提出修正 | 贡献中等,需要清晰的理论对话 |
| 扩展型 | 将理论延伸至新的现象域或概念层 | 贡献较大,需要扎实的理论基础 |
| 挑战型 | 提出与主流理论相悖的机制,要求理论重构 | 贡献最大,风险也最高 |
输出格式:
【理论对话定位】
候选对话 1:[理论脉络名称]
- 核心争论:
- 当前研究与之的关联:
- 可能的介入类型:
- 如果介入,研究问题可以是:
候选对话 2:[理论脉络名称]
(同上结构)
推荐优先进入的理论对话:[说明推荐理由]
第三阶段:三重检验
针对最具潜力的 1-2 个研究问题方向,执行三重检验:
检验一:理论贡献检验
如果这项研究得出预期结论,它具体向哪个理论对话贡献了什么?
判断标准(必须能回答以下问题):
- 这个贡献改变了我们对某个概念/机制/关系的理解吗?(否则只是"填补空白")
- 有没有人(理论上)会因为看到这个研究而需要修正自己的理论立场?
❌ 不合格的回答:"丰富了 XX 领域的研究""为 XX 研究提供了中国经验" ✅ 合格的回答:"挑战了 XX 理论关于 A→B 机制的假设,在数字劳动情境下 A→C 才是主要路径"
检验二:So What 检验
假设研究结论完全如预期,这对学科知识意味着什么?
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.
- 6d ago First seen · 214 lines · 159 tokens per session scan A 5f8cc81d77c3
problematization is a skill published in the GitHub repository yipng05-max/-skills (283 stars, last pushed 4mo ago), licensed MIT. It adds 159 tokens to every session and 2,435 once invoked, about $0.0008 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…
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…