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 rongarede/claude-skills-research --skill paragraph-progression-analyzergit clone --depth 1 https://github.com/rongarede/claude-skills-researchWrote 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/rongarede/claude-skills-research/paragraph-progression-analyzer)<a href="https://agentmods.dev/skills/rongarede/claude-skills-research/paragraph-progression-analyzer"><img src="https://agentmods.dev/badge/skills/rongarede/claude-skills-research/paragraph-progression-analyzer/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/rongarede/claude-skills-research/paragraph-progression-analyzer"><img src="https://agentmods.dev/badge/skills/rongarede/claude-skills-research/paragraph-progression-analyzer.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 | $0.00074 | $0.02715 |
| Opus 5.5 | $0.00030 | $0.01086 |
| Sonnet 5.5 | $0.00015 | $0.00543 |
| Haiku 4.5 | $0.00007 | $0.00271 |
Grade A, and why
paragraph-progression-analyzer 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 2mo 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 — 223 lines — stays where its author put it; the contents beside it link to each section on GitHub.
段落主位推进形态分析工具
基于 Daneš (1974) 主位推进理论（Thematic Progression Theory），对中文学术论文段落逐句拆解主位（Theme）与述位（Rheme），判定推进模式，检测断裂点，输出连贯性诊断与修复建议。
触发方式
/progression <段落文本或章节位置>- 「分析这个段落的推进形态」
- 「检查段落连贯性」
- 「主位推进诊断」
- 「thematic progression analysis」
适用范围
本 Skill 适用于中文学术论文的任何段落，不预设章节类型：
- 绪论 / Introduction
- 文献综述 / Related Work
- 方法 / Methods
- 实验与结果 / Results
- 讨论与总结 / Discussion / Conclusion
输入要求
{段落文本}— 由用户明确指定的一个或多个中文学术论文段落- 每个段落独立分析，不跨段合并
核心理论框架
主位与述位
| 概念 | 定义 | 识别方法（中文） |
|---|---|---|
| 主位（Theme, T） | 句子起点，已知/给定信息 | 话题位置：谓语动词前的话题性成分 |
| 述位（Rheme, R） | 新信息，交际核心 | 话题之后的全部陈述内容 |
5 种推进模式
| 编号 | 模式名称 | 符号表示 | 适用场景 |
|---|---|---|---|
| P1 | 简单线性推进 | T1→R1, T2(=R1)→R2, T3(=R2)→R3 | 流程描述、因果链、方法步骤 |
| P2 | 恒定主位推进 | T1→R1, T1→R2, T1→R3 | 特征罗列、属性描述 |
| P3 | 派生主位推进 | T(hyper)→{T1→R1, T2→R2, T3→R3} | 分类论述、先总后分 |
| P4 | 述位分裂推进 | T1→R1(=a+b+c), T2(=a)→R2, T3(=b)→R3 | 展开多个子话题 |
| P5 | 主位跳跃 | T(n+1) 与 T(n)/R(n) 无关 | 逻辑断裂信号，需检查隐含连接 |
中文特殊规则
- 零主位（Zero Theme）：中文常承前省略主语，分析时须恢复省略的主位，标记为
T(n)=[零，承T(n-1)] - 话题链（Topic Chain）：中文多个小句共享同一话题时，后续句的主位为零形式，本质是恒定主位推进（P2）
- 双主位：中文偶见"时间/条件状语 + 话题"双层主位结构，以话题性成分为准
执行规范
Step 1: 逐句切分与 T/R 识别
对输入段落按句号、分号切分为独立句子（编号 S1, S2, ...），对每句识别：
| 字段 | 说明 |
|---|---|
| 句号 | S1, S2, ... |
| 原文 | 原句全文 |
| 主位 T | 该句话题性成分（句首已知信息） |
| 述位 R | 该句新信息部分 |
| 零主位 | 是否省略主位？若是，恢复为何 |
Step 2: 标注句间推进关系
对每对相邻句（Sn → Sn+1），判定 T(n+1) 的来源：
| 来源类型 | 判定条件 | 对应模式 |
|---|---|---|
| T(n+1) = R(n) | 下句主位来自上句述位 | P1 简单线性 |
| T(n+1) = T(n) | 下句主位与上句主位相同 | P2 恒定主位 |
| T(n+1) 派生自超主位 | 下句主位来自段首总领概念 | P3 派生主位 |
| T(n+1) = R(n) 的子成分 | 上句述位含多个子项，下句取其一 | P4 述位分裂 |
| 无法追溯 | T(n+1) 与 T(n)、R(n) 均无关 | P5 主位跳跃（断裂） |
Step 3: 判定整段推进模式
基于 Step 2 的逐对关系，判定整段的主导推进模式：
- 若 ≥60% 的句对属于同一模式 → 单一模式
- 若无主导模式 → 混合模式，列出组合（如 P1+P3）
Step 4: 检测推进断裂点
断裂 = P5 主位跳跃。对每个断裂点输出：
| 字段 | 说明 |
|---|---|
| 位置 | S(n) → S(n+1) 之间 |
| 断裂描述 | T(n+1) 是什么，为何无法追溯到 T(n) 或 R(n) |
| 严重程度 | 轻微（有隐含逻辑连接）/ 严重（读者会困惑） |
| 可能原因 | 话题切换过快 / 缺少过渡句 / 逻辑跳步 |
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.
- 2mo ago First seen · 223 lines · 74 tokens per session scan A c9ee56949489
paragraph-progression-analyzer is a skill published in the GitHub repository rongarede/claude-skills-research (4 stars, last pushed 7mo ago), licensed MIT. It adds 74 tokens to every session and 2,715 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-08-31.
paragraph-progression-analyzer compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| paragraph-progression-analyzerrongarede/claude-skills-research | Skill | 4 | 7mo ago | MIT | A | 74 | Claude Code, Codex |
| paper-skillcLin-c/paper-skill | Skill | 146 | 6d ago | MIT | A | 122 | Codex |
| latex-fmtCalix-L/awesome-latex-skills | Skill | 187 | 1mo ago | MIT | A | 43 | Codex |
| latex-rescueCalix-L/awesome-latex-skills | Skill | 187 | 1mo ago | MIT | A | 41 | Codex |
| pdf2texCalix-L/awesome-latex-skills | Skill | 187 | 1mo ago | MIT | A | 46 | Codex |
| research-expertpersonamanagmentlayer/pcl | Skill | 45 | 20d ago | Apache-2.0 | A | 50 | Claude Code |
| latex-polishCalix-L/awesome-latex-skills | Skill | 187 | 1mo ago | MIT | A | 45 | Codex |