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-afp-autogit 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-auto)<a href="https://agentmods.dev/skills/yipng05-max/-skills/ta-research-afp-auto"><img src="https://agentmods.dev/badge/skills/yipng05-max/-skills/ta-research-afp-auto/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-auto"><img src="https://agentmods.dev/badge/skills/yipng05-max/-skills/ta-research-afp-auto.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 | $0.00209 | $0.04038 |
| Opus 5 | $0.00105 | $0.02019 |
| Sonnet 5 | $0.00042 | $0.00808 |
| Haiku 4.5 | $0.00021 | $0.00404 |
Grade A, and why
ta-research-AFP-auto 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 — 438 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TA 研究全流程全自动 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-Auto-AFP]，无一例外 - 全自动模式：所有检查点连续执行，不等待用户确认，不设硬停止点
- 决策日志：维护全局
auto_decisions[]列表，每次自动决策立即追加记录 - 卡点处理：遇到任何阻断（文件缺失/工具不可用/信息不足），执行降级策略后继续，不中断流程
- 状态继承：理论定位（A/B/C）在 CP2 自动确定后，全程锁定
- 原子级执行：每个检查点独立完成、记录、存档后，自动触发下一个
- 唯一停顿点：仅在 CP12 完稿汇总时停止，输出完整报告等待研究者审阅
01. 交互仪表盘（HUD）
每个检查点开始时输出：
╭─ [TA-Auto-AFP] ────────────────────────────────────╮
│ 📌 检查点 N/12：[检查点名称]
│ 📊 进度：[N-1]/12 已完成
│ 🔬 理论定位：[A/B/C | 待确定]
│ 📋 调用：[skill名称 | 无需外部skill]
│ ⚙️ 本步操作：[一句话说明做什么]
│ 🤖 模式：全自动（无需确认，自动进入下一步）
╰────────────────────────────────────────────────────╯
02. P0：核心资产自动锁定
启动后立即执行，无需用户输入：
-
读取项目目录中的
CLAUDE.md（如存在），提取：- 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
-
输出自动识别结果后，直接进入检查点 1，不等待确认：
[TA-Auto-AFP] 已启动 · 全自动模式
从 CLAUDE.md 自动识别：
研究主题：[内容]
研究问题：[内容]
访谈材料：[路径 或 未找到→将在CP3询问]
目标期刊：[C刊/SSCI 或 未找到→默认C刊]
已完成工作：[内容 或 无]
自动进入检查点 1...
若无 CLAUDE.md，输出提示后仍直接启动，将缺失信息标记为"待补充"，在对应检查点执行时再处理。
03. 卡点降级策略（全局）
遇到以下情况时，执行对应降级策略，不中断流程：
| 卡点类型 | 降级策略 |
|---|---|
| 文件缺失（如无访谈材料） | 跳过该检查点，日志记录"跳过原因：材料缺失" |
| 工具不可用（如 Chrome MCP 离线） | 降级为手动描述模式：输出操作步骤供研究者参考，标注"需手动执行" |
| 引用核查存疑 | 统一标注 ⚠️ 待核实，不删除，不阻断 |
| Skill 调用失败 | 记录错误，跳过该 skill，协调器直接生成简版产出 |
| 信息不足以执行 | 使用合理默认值（见各检查点说明），日志记录默认值选择理由 |
04. 检查点执行规范
每个检查点完成后自动输出：
- HUD 仪表盘
- 执行内容摘要
[🛡️ 自检日志]- 本步决策记录（如有自动决策）
- 自动触发下一检查点（无停止指令）
检查点 1：文献检索
调用：cnki-advanced-search + foreign-literature-search（双轨并行）
自动执行：
- 基于研究主题自动构建检索词（含同义词扩展）
- 执行中文检索（CSSCI）+ 外文检索（SSCI）
- 生成 WoS/Scopus 布尔检索式
卡点处理：
- Chrome MCP 不可用 → 输出知网检索步骤说明（标注"需手动执行"），外文检索照常执行
- 关键词无法确定 → 使用研究问题中的核心名词作为检索词
产出：
知网检索结果_{关键词}_{日期}.xlsx外文文献检索_{关键词}_{日期}.xlsx
[🛡️ 自检日志]
□ 中文检索已完成（或标注"需手动执行"）
□ 外文检索已完成，WoS检索式已生成
□ 文献池已建立，自动进入检查点 2
检查点 2：理论框架建构【自动决策节点】
调用：ta-framework-builder
自动决策——理论定位（A/B/C）：
系统根据以下规则自动判断，无需用户选择：
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 438 lines · 209 tokens per session scan A 6ca1fcd2db70
ta-research-AFP-auto is a skill published in the GitHub repository yipng05-max/-skills (285 stars, last pushed 4mo ago), licensed MIT. It adds 209 tokens to every session and 4,038 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…