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 yipng05-max/-skills --skill design-coherence-checkgit 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/design-coherence-check)<a href="https://agentmods.dev/skills/yipng05-max/-skills/design-coherence-check"><img src="https://agentmods.dev/badge/skills/yipng05-max/-skills/design-coherence-check/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/yipng05-max/-skills/design-coherence-check"><img src="https://agentmods.dev/badge/skills/yipng05-max/-skills/design-coherence-check.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 | $0.00189 | $0.03054 |
| Opus 5 | $0.00095 | $0.01527 |
| Sonnet 5 | $0.00038 | $0.00611 |
| Haiku 4.5 | $0.00019 | $0.00305 |
Grade A, and why
design-coherence-check 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 10d 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 — 263 lines — stays where its author put it; the contents beside it link to each section on GitHub.
研究设计内部一致性检查工具(Design Coherence Check)
本 skill 基于 Crotty(1998)的研究设计四层架构、Lincoln & Guba(1985)的可信度框架, 以及 Guba & Lincoln(1994)的范式论,对研究设计进行自上而下的一致性检查。
核心立场:一个研究设计的内在一致性不是技术问题,而是知识论问题。 研究者的认识论立场规定了她能做出什么类型的知识宣称; 方法论是实现这些宣称的策略;具体方法是策略的操作化。 三个层次必须指向同一个认识论方向,否则研究的根基是不稳的。
启动:获取必要信息
触发后,收集以下信息:
必填 1:研究问题
研究要回答的核心问题。
必填 2:研究设计描述
可以是以下任意形式:
- 已写好的方法章节(粘贴文本)
- 研究设计框架描述(简要说明各个组成部分)
- 逐项告知(认识论立场/研究方法/数据收集/分析策略)
选填 3:理论框架
研究采用的理论视角(有助于检查理论预设与方法论的一致性)。
选填 4:已有疑虑
研究者自己对设计一致性的疑惑(优先处理)。
执行流程
收到信息后,连续执行以下三个阶段,无需等待用户确认。
第一阶段:研究设计四层架构还原
首先提取并明确研究设计的四个层次,建立后续检查的基准:
层次 1:本体论(Ontology)
研究者对"社会实在"的基本假设是什么?
从研究设计或理论选择中推断:
- 实在论(Realism):存在独立于观察者的客观社会实在
- 建构主义(Constructivism):社会实在是被主体建构的,不独立于认识者
- 批判实在论(Critical Realism):存在实在的结构/机制,但只能通过观察其效果来认识
- 关系主义(Relationalism):实在由关系构成,而非由实体构成
层次 2:认识论(Epistemology)
关于"知识如何产生"的基本立场是什么?
- 客观主义(Objectivism):知识是对独立存在的实在的发现,研究者与研究对象分离
- 建构主义(Constructivism):知识是研究者与被研究对象共同建构的
- 主观主义(Subjectivism):知识来自主体的内部意义世界
- 批判实在论认识论:知识是对实在机制的溯因推理
层次 3:方法论(Methodology)
研究策略和设计类型是什么?
- 扎根理论 / 现象学 / 民族志 / 叙事研究 / 案例研究 / 话语分析
- 调查研究 / 实验设计 / 准实验设计
- 混合方法(需进一步说明整合类型)
层次 4:具体方法(Methods)
数据收集和分析的具体工具是什么?
- 数据收集:深度访谈 / 参与观察 / 问卷 / 文献/档案 / 实验
- 数据分析:主题分析 / 扎根编码 / 内容分析 / 话语分析 / 统计分析
输出格式:
【研究设计四层架构】
本体论立场(推断):[立场名称]
依据:[从研究设计哪些地方推断出来的]
确定程度:明确声明 / 可推断 / 不清晰
认识论立场(推断):[立场名称]
依据:
确定程度:
方法论(研究设计类型):[类型名称]
说明:
具体方法:
数据收集:
数据分析:
第二阶段:逐级一致性检查
检查四个层次之间的一致性,重点检查三个"接缝":
接缝 1:本体论 → 认识论
检查原则:本体论立场规定了认识论的可能范围。
常见不一致:
| 本体论 | 不兼容的认识论 | 矛盾来源 |
|---|---|---|
| 建构主义(无客观实在) | 客观主义认识论 | 矛盾:如果没有独立实在,怎么能"客观地"认识? |
| 实在论 | 激进建构主义 | 矛盾:既然有客观实在,知识怎么可能完全是建构的? |
| 关系主义 | 个体主义认识论 | 矛盾:关系主义本体论要求从关系而非实体出发 |
检查问题:本体论和认识论的立场是否相互支持?还是存在内在张力?
评估:✅ 一致 / ⚠️ 有张力(需要说明处理方式) / ❌ 根本性矛盾
接缝 2:认识论 → 方法论
检查原则:方法论必须能够实现认识论声称的知识生产方式。
常见不一致:
| 认识论立场 | 不兼容的方法论 | 矛盾来源 |
|---|---|---|
| 建构主义认识论 | 扎根理论(格雷泽版)的"客观发现" | 建构主义不能声称客观发现理论,只能声称建构理论 |
| 客观主义认识论 | 现象学(现象学关注主观体验,预设主观知识的合法性) | 认识论与方法论的知识观冲突 |
| 诠释主义 | 要求"可重复性"和"推广性" | 诠释主义的目标是深度理解,不是统计推广 |
| 批判实在论 | 仅做描述性分析(不寻找机制) | 批判实在论要求揭示深层机制,不满足于现象描述 |
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.
- 10d ago First seen · 263 lines · 189 tokens per session scan A df9673f3b163
design-coherence-check is a skill published in the GitHub repository yipng05-max/-skills (285 stars, last pushed 4mo ago), licensed MIT. It adds 189 tokens to every session and 3,054 once invoked, about $0.0009 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…