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 argument-auditorgit 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/argument-auditor)<a href="https://agentmods.dev/skills/yipng05-max/-skills/argument-auditor"><img src="https://agentmods.dev/badge/skills/yipng05-max/-skills/argument-auditor/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/argument-auditor"><img src="https://agentmods.dev/badge/skills/yipng05-max/-skills/argument-auditor.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 | $0.00173 | $0.02460 |
| Opus 5 | $0.00086 | $0.01230 |
| Sonnet 5 | $0.00035 | $0.00492 |
| Haiku 4.5 | $0.00017 | $0.00246 |
Grade A, and why
argument-auditor 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 9d 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 — 248 lines — stays where its author put it; the contents beside it link to each section on GitHub.
论证结构审查工具（Argument Auditor）
本 skill 基于 Toulmin（1958）的论证模型及学术写作逻辑规范， 对学术文本的论证结构进行系统性审查，识别论证缺陷并给出针对性的修改建议。
核心立场：学术论文的说服力来自论证结构，而非修辞技巧。 一段文字如果主张-证据-推理链条不完整，无论语言多么流畅，都无法在学术共同体中站稳脚跟。
启动：获取必要信息
触发后，收集以下信息：
必填 1：待审查的文本
粘贴需要审查的段落、小节或章节。长度不限，但建议一次审查一个论证单元（通常是一个段落到一个小节）。
选填 2：审查范围
- 单段落：审查该段落内部的论证逻辑
- 小节（多段落）：审查段落间的逻辑推进关系 + 每个段落内部逻辑
- 章节：审查整体论证架构 + 各小节的衔接
选填 3：已知的疑虑
用户自己感觉哪里有问题（有助于优先处理）。
选填 4：写作背景
- 这段文字在论文中的位置（引言/文献综述/理论框架/方法/分析/讨论/结论）
- 目标读者和期刊类型（C 刊/SSCI）
执行流程
根据审查范围，自动选择对应深度，连续执行以下阶段，无需等待用户确认。
第一阶段：论证结构提取
首先提取文本的论证骨架，将其还原为 Toulmin 模型的基本要素：
| 要素 | 含义 | 从文本中提取 |
|---|---|---|
| 主张（Claim） | 这段文字最终想让读者接受什么观点？ | |
| 证据（Data/Ground） | 用什么材料支撑主张？ | |
| 推理（Warrant） | 从证据到主张的逻辑跨越是什么？ | |
| 支撑（Backing） | 推理本身有没有根据？ | |
| 限定（Qualifier） | 主张的适用范围是否有明确限定？ | |
| 反驳条件（Rebuttal） | 文本是否预先处理了可能的反驳？ |
输出格式：
【论证骨架提取】
主张：[一句话概括]
证据：[列出主要证据，逐条编号]
推理：[从证据到主张的逻辑链条是什么？]
支撑：[推理本身是否有依据？]
限定：[主张的适用边界是否明确？]
反驳处理：[有 / 无 / 部分有]
第二阶段：逐项问题诊断
针对以下七类常见论证问题，逐一检查：
问题类型 1：主张不清晰（Unclear Claim）
表现：
- 段落没有明确的论点句（topic sentence）
- 主张太宽泛，无法被特定证据支撑或反驳
- 主张被掩盖在叙述性表达中
检查问题：这段文字想让读者相信什么？能用一句清晰的陈述句表达吗？
严重程度：🔴 高（论证的一切都依赖主张是否清晰）
问题类型 2：证据不足（Insufficient Evidence）
表现：
- 只有一条证据支撑重要主张
- 证据是举例性的，但被当作系统性支撑使用
- 只援引了支撑性证据，忽视了相反证据
检查问题：这些证据的数量和类型足以支撑如此强度的主张吗？
严重程度：🔴 高
问题类型 3：推理跳跃（Logical Gap）
表现：
- 证据和主张之间存在未言明的隐性推理步骤
- 从"A 发生"直接跳到"因此 C 成立"，中间的 B 没有交代
- 使用"因此""由此可见""这说明"等连接词，但逻辑关系并不成立
检查问题：从证据到主张，中间有哪些步骤被省略了？这些省略的步骤成立吗？
严重程度：🔴 高
问题类型 4：循环论证（Circular Reasoning）
表现：
- 用主张本身作为支撑主张的理由
- 证据是主张的另一种表述，而非独立的支持
- 定义与论证混淆（用定义"证明"现象）
检查问题：证据是否独立于主张？还是只是主张的换句话说？
严重程度：🔴 高
问题类型 5：过度概括（Overgeneralization）
表现：
- 从有限案例推出无边界的普遍结论
- 主张的适用范围远超证据的覆盖范围
- 用"总是""必然""所有"等强限定词，但证据不支持如此强的表述
检查问题：主张的强度与证据的范围是否匹配？
严重程度：🟡 中
问题类型 6：稻草人论证（Straw Man）
表现：
- 在文献批评部分，将已有研究的立场简化或曲解后再批评
- 批评的对象不是原著的实际主张，而是简化版本
- 对比框架不公平（用自己的最强版本对比别人的最弱版本）
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.
- 9d ago First seen · 248 lines · 173 tokens per session scan A 46a5faefa768
argument-auditor is a skill published in the GitHub repository yipng05-max/-skills (285 stars, last pushed 4mo ago), licensed MIT. It adds 173 tokens to every session and 2,460 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…
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…