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 | $0.00037 | $0.01358 |
| Sonnet 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 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 — 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.
- 11d 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 (2 stars, last pushed 5mo ago), licensed MIT. It adds 74 tokens to every session and 2,715 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
package-author
A packaging guide for turning scripts, skills, or an MCP service into a standard plugin package. MCP is a way for an AI assistant to connect to external tools.
notes
Skill "notes" from Pinvou/pinvou-agent, covering ima notes, operations, write rules, examples and response handling.
taiyi-integration
A project workflow skill for closing a TaiyiForge change and recording it in a CHANGELOG.md file. It checks review results, tests, and the state of the working tree before archiving the change.
taiyi-ui-design
A design-planning guide for describing how an application's user interface should look and behave. It produces a UI-DESIGN.md document covering layouts, components, interactions, accessibility, and error states.
taiyi-evolve
A workflow skill that compares the implemented code with the frozen design after development and testing. It records architecture changes and proposes updates to DESIGN.md, the document describing the intended system structure.
taiyi-diagram-c4
A code-scanning tool that builds C4 architecture documents from a repository. It separates facts observed in the code from conclusions inferred about the design and uses Mermaid diagrams as the source format.