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 ta-findings-writergit 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/ta-findings-writer)<a href="https://agentmods.dev/skills/yipng05-max/-skills/ta-findings-writer"><img src="https://agentmods.dev/badge/skills/yipng05-max/-skills/ta-findings-writer/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/ta-findings-writer"><img src="https://agentmods.dev/badge/skills/yipng05-max/-skills/ta-findings-writer.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 | $0.00107 | $0.01526 |
| Opus 5 | $0.00053 | $0.00763 |
| Sonnet 5 | $0.00021 | $0.00305 |
| Haiku 4.5 | $0.00011 | $0.00153 |
Grade A, and why
ta-findings-writer 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 12d 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 — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TA 研究发现章节写作
将主题分析的主题汇总表转化为论文发现章节。核心原则： 每条引语都必须有研究者声音的解释，引语是证据，不是结论本身。
启动：收集必要信息
启动时收集（在 ta-research-workflow 中已有的信息自动复用）：
- 主题汇总表：主题名称、核心含义、代表性引语（来自
thematic-analysis输出，或研究者提供） - 研究问题
- 理论定位（A/B/C）——若在工作流中已确认，自动沿用
- 主题关系（可选）：主题间是并列/递进/因果/对立关系？
- 可选：理论框架摘要（A 或 C 定位时需要）
第一步：确认理论定位对发现章节的影响
根据理论定位，明确告知研究者发现章节的写作取向：
A（理论驱动）
- 每个主题的阐释段落需明确呼应理论概念
- 主题命名本身可以使用理论术语
- 发现章节承担一部分理论诠释工作
B（经验驱动）
- 发现章节保持资料近端语言，尽量用被访者的语言世界
- 理论对话全部留给讨论章节
- 此处的任务是"让资料说话"，而非"让理论说话"
C（敏感性概念）
- 主题命名可借用理论术语，但阐释以现象描述为主
- 适度渗透理论语言，但不过度解释
- 理论在发现章节隐而不显，在讨论章节深化
第二步：确认叙事结构
skill 根据主题关系自动判断推荐结构，并提供选项让研究者确认：
主题并列型（推荐条件：各主题相互独立，没有明显的逻辑先后）
- 每个主题独立成一个小节
- 小节结构相同：主题阐释 → 引语证据 → 分析解释
- 小节间用简短过渡句衔接
主题串联型（推荐条件：主题间有因果链、递进逻辑、或对立张力）
- 沿逻辑线展开：条件 → 过程 → 结果，或张力 → 应对 → 后果
- 每个主题是叙事链条的一个节点
- 节点之间有明确的承接关系（"在X的背景下，行动者进一步……"）
第三步：逐主题写作
对每个主题，按以下单元依次写作：
单元 1：主题阐释（1段，必须有）
说明这个主题捕捉了什么现象或机制，为什么值得单独成为一个主题。
写作要求：
- 不是对主题名称的翻译（"'适应性策略'这个主题是指……"）
- 而是对现象的诠释（"在数据中，受访者反复呈现出一种……的模式，这一模式的核心在于……"）
- A 定位：在阐释中点明与哪个理论概念的关联
- B 定位：以现象描述为主，不过度理论化
- C 定位：可以用理论透镜"照亮"现象，但以现象描述为基础
单元 2：引语证据（2–3条，必须有）
选取最能说明主题含义的代表性引语，每条引语配一段分析性解释。
引语呈现格式：
"受访者原话" （受访者编号/匿名代码，如：访谈A，2023年）
引语后的分析解释（必须有，不可跳过）：
- 这段话说明了什么？它如何支持主题的核心含义？
- 注意这段话中哪个词、哪个表述最有分析价值？为什么？
- A 定位：这段话如何与理论概念对话？
- B/C 定位：这段话揭示了什么行动逻辑或意义系统？
禁止行为：
- 连续放置多条引语，没有分析解释（"引语堆砌"）
- 引语之后只写一句泛泛的总结（"以上说明了……"）
- 用引语作为主题阐释的替代（引语只能是证据，不能是论点本身）
单元 3：主题内部张力或变体（可选，有则写）
如果数据中存在同一主题内的分歧、例外或类型差异：
- 呈现差异，说明它属于同一主题的不同表现（而非反例）
- 简短处理，1–2段，不展开为独立主题
单元 4：承接句（串联型叙事时使用）
末尾写一句将本主题与下一主题连接的过渡句，说明两者的逻辑关系。
第四步：发现章节整体检查
所有主题写完后，进行整体检查：
- 引语/分析比例：每条引语后是否都有实质性分析？（禁止1:0，即只有引语没有分析）
- 主题命名一致性：主题名称在全文是否使用同一术语，没有随意替换？
- 理论定位一致性：各主题的阐释深度和语言风格是否符合选定的 A/B/C 定位？
- 结构清晰性：读者能否从小节标题和主题阐释段落清楚理解每个主题的含义？
输出与保存
写作完成后，调用 Write 工具保存：
文件命名：findings.md
保存路径：当前项目目录
告知研究者：
"研究发现章节已保存至
findings.md（[字数]字，共[N]个主题）。 如在 ta-research-workflow 中，请继续下一检查点（讨论写作）。"
语言
- 默认中文
- 引语原文保持原样，不翻译、不改写
- 学术写作风格：书面化、精确、避免口语化
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.
- 12d ago First seen · 136 lines · 107 tokens per session scan A 999ba27668a6
ta-findings-writer is a skill published in the GitHub repository yipng05-max/-skills (286 stars, last pushed 4mo ago), licensed MIT. It adds 107 tokens to every session and 1,526 once invoked, about $0.0005 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…