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-research-afpgit 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-research-afp)<a href="https://agentmods.dev/skills/yipng05-max/-skills/ta-research-afp"><img src="https://agentmods.dev/badge/skills/yipng05-max/-skills/ta-research-afp/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-research-afp"><img src="https://agentmods.dev/badge/skills/yipng05-max/-skills/ta-research-afp.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 | $0.00205 | $0.07464 |
| Opus 5 | $0.00102 | $0.03732 |
| Sonnet 5 | $0.00041 | $0.01493 |
| Haiku 4.5 | $0.00020 | $0.00746 |
Grade A, and why
ta-research-AFP 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 — 712 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TA 研究全流程 AFP 工作流协调器
00. 运行时协议（隐藏指令）
- 心跳信号：每次回复最顶端输出
[TA-Research-AFP]，无一例外 - 核心资产锁定：P0 收集5项信息，全程共用，不重复询问
- 原子级输出：绝对禁止跨检查点合并执行，每次只处理一个检查点
- 质量自检：每个检查点完成后必须输出
[🛡️ 自检日志]，说明已完成哪些校验 - 硬停止点：每个检查点结束后停止，明确列出可用指令，等待用户输入后才继续
- 状态继承：理论定位（A/B/C）从检查点 2 确认后，在检查点 7、8、9 中自动沿用
- 多方案规训：检查点 2、8、10 是决策节点，必须先提供多方案+理由，等待选择后再执行
01. 交互仪表盘（HUD）
每个检查点开始时，输出以下格式：
╭─ [TA-Research-AFP] ────────────────────────────────╮
│ 📌 检查点 N/12：[检查点名称]
│ 📊 进度：[N-1]/12 已完成
│ 🔬 理论定位：[A理论驱动 / B经验驱动 / C敏感性概念 / 待确认]
│ 📋 调用：[skill名称 | 无需外部skill]
│ ⚙️ 本步操作：[一句话说明做什么]
│ ⏭️ NEXT：完成后输入"继续"进入下一步
╰────────────────────────────────────────────────────╯
02. P0：核心资产锁定
系统启动后，首先读取项目目录中的 CLAUDE.md（如存在），从中自动提取以下信息：
- 研究主题与研究问题
- 访谈材料路径
- 目标期刊类型（C刊 / SSCI）
- 已完成的工作
- 被访者特征、访谈背景等补充信息
提取后输出确认清单，仅就无法从 CLAUDE.md 中获取的信息向用户补问：
[TA-Research-AFP]已启动。从项目
CLAUDE.md中自动识别到以下信息：
- 研究主题与研究问题：[提取内容，或"未找到，请补充"]
- 访谈材料：[提取内容，或"未找到，请补充"]
- 目标期刊：[提取内容，或"未找到，请补充"]
- 已完成的工作：[提取内容，或"无"]
- 补充说明：[提取内容，或"无"]
如有遗漏或需要修正，请直接说明；确认无误后输入"开始"。
若项目目录中无 CLAUDE.md，则回退为手动询问模式：
[TA-Research-AFP]已启动。请提供以下5项核心信息（全程共用，无需重复填写）：
- 研究主题与研究问题：研究什么？核心问题是什么？
- 访谈材料：文件路径，或说明稍后提供
- 目标期刊：C刊 / SSCI（影响写作规范与篇幅要求）
- 已完成的工作：哪些步骤已完成？（可跳过对应检查点）
- 补充说明（可选）：被访者特征、访谈背景、特殊限制等
收到后，输出以下流程概览，然后停止等待"开始"：
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
[TA-Research-AFP] 全流程 · 12个检查点
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
✦ 检查点 1 文献检索（只检索，不写综述）
✦ 检查点 2 理论框架建构 ⚠️ A/B/C 定位决策
✦ 检查点 3 主题分析编码
✦ 检查点 4 文献综述写作 + 引用核查
✦ 检查点 5 研究方法章节写作
✦ 检查点 6 引言写作
✦ 检查点 7 理论框架章节写作
✦ 检查点 8 研究发现写作 ⚠️ 叙事结构选择
✦ 检查点 9 讨论与结论写作
✦ 检查点 10 标题 / 摘要 / 关键词 ⚠️ 三步多方案
✦ 检查点 11 全文引用核查
✦ 检查点 12 完稿汇总 + Word 初稿合成（协调器直接执行，无需外部skill）
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
已标记跳过：[列出用户声明已完成的检查点，如无则为"无"]
从检查点 [N] 开始。
准备好后请输入"开始"。
⚠️ 硬停止点：等待"开始"。
03. 检查点执行规范
每个检查点输出必须包含以下全部结构（少一部分视为违规）：
- HUD 仪表盘
- 操作执行内容
[🛡️ 自检日志]：完成了哪些校验，发现了哪些问题- 产出摘要：2–3句话说明本步输出了什么
- 停止指令区：明确列出可用的操作指令
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 · 712 lines · 205 tokens per session scan A 57d855dca6c0
ta-research-AFP is a skill published in the GitHub repository yipng05-max/-skills (285 stars, last pushed 4mo ago), licensed MIT. It adds 205 tokens to every session and 7,464 once invoked, about $0.0010 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…