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 yinqd3/workbuddy-skills --skill deep-researchgit clone --depth 1 https://github.com/yinqd3/workbuddy-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/yinqd3/workbuddy-skills/deep-research)<a href="https://agentmods.dev/skills/yinqd3/workbuddy-skills/deep-research"><img src="https://agentmods.dev/badge/skills/yinqd3/workbuddy-skills/deep-research/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/yinqd3/workbuddy-skills/deep-research"><img src="https://agentmods.dev/badge/skills/yinqd3/workbuddy-skills/deep-research.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 | $0.00150 | $0.01530 |
| Opus 5 | $0.00075 | $0.00765 |
| Sonnet 5 | $0.00030 | $0.00306 |
| Haiku 4.5 | $0.00015 | $0.00153 |
Grade A, and why
deep-research 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 10d 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 — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deep Research — 通用学术研究 Agent 团队
领域无关的 13-Agent 团队，适用于任何主题的严格学术研究。
快速开始
研究气候变化对城市供水系统的影响
帮我梳理厌氧消化产甲烷菌基因组学的研究现状
7 种运行模式
| 模式 | 适用场景 | 时长估计 |
|---|---|---|
socratic |
有模糊想法，需要引导 | 对话式 |
full |
有明确研究问题，需要全面研究 | 完整流程 |
quick |
需要快速摘要 | ~30 分钟 |
review |
有论文需要评估 | 中 |
lit-review |
只需要文献综述 | 中 |
fact-check |
验证特定声明 | 短 |
systematic-review |
PRISMA 系统综述或元分析 | 长 |
不确定选哪个？从 socratic 开始。
Agent 团队（13 个）
| # | Agent | 角色 | 阶段 |
|---|---|---|---|
| 1 | 研究问题 Agent | 将模糊主题转化为精确的 FINER 评分研究问题 | 阶段 1 |
| 2 | 研究架构 Agent | 设计方法论蓝本：范式、方法、数据策略、分析框架 | 阶段 1 |
| 3 | 文献检索 Agent | 系统文献检索、筛选、APA 7.0 注释文献目录 | 阶段 2 |
| 4 | 来源验证 Agent | 事实核查、来源分级（证据等级）、掠夺性期刊检测 | 阶段 2 |
| 5 | 综合分析 Agent | 跨来源整合、矛盾解析、主题综合、缺口分析 | 阶段 3 |
| 6 | 报告编撰 Agent | 起草完整 APA 7.0 报告 | 阶段 4, 6 |
| 7 | 主编 Agent | Q1 期刊编辑审查：原创性、严谨性、证据充分性 | 阶段 5 |
| 8 | 魔鬼代言 Agent | 挑战假设、逻辑谬误检测、替代解释、确认偏误检查 | 阶段 1,3,5 |
| 9 | 伦理审查 Agent | AI 辅助研究伦理、署名完整性、双重用途筛查 | 阶段 5 |
| 10 | 苏格拉底导师 Agent | Q1 期刊编辑角色，苏格拉底式五层引导 | 苏格拉底模式 |
| 11 | 偏倚风险 Agent | RoB 2 / ROBINS-I 偏倚风险评估 | 系统综述 |
| 12 | 元分析 Agent | 效应量、异质性、GRADE 分级 | 系统综述 |
| 13 | 文献监测 Agent | 研究后文献监测：摘要、撤稿警报、矛盾发现 | 可选 |
6 阶段工作流
用户: "研究 [主题]"
|
阶段 1: 确定范围（交互式）
|-> [研究问题 Agent] → 研究问题简报
|-> [研究架构 Agent] → 方法论蓝本
+-> [魔鬼代言 Agent] — 检查点 1
** 用户确认后进入阶段 2 **
|
阶段 2: 调研
|-> [文献检索 Agent] → 文献库 + 注释目录
+-> [来源验证 Agent] → 验证并分级的来源
|
阶段 3: 分析
|-> [综合分析 Agent] → 综合叙述 + 缺口分析
+-> [魔鬼代言 Agent] — 检查点 2
** 用户审查发现后进入阶段 4 **
|
阶段 4: 撰写
+-> [报告编撰 Agent] → 完整 APA 7.0 报告
|
阶段 5: 审查
|-> [主编 Agent] → 编辑决策
|-> [伦理审查 Agent] → 伦理报告
+-> [魔鬼代言 Agent] → 脆弱性扫描
|
阶段 6: 修改
+-> [报告编撰 Agent] → 最终打磨报告
苏格拉底模式（五层引导）
- 层 1: 探索兴趣 — "是什么让你对这个话题感兴趣？"
- 层 2: 界定范围 — "你关注的是哪个具体方面？"
- 层 3: 形成问题 — "你真正想问的研究问题是什么？"
- 层 4: 方法论 — "回答这个问题需要什么证据？"
- 层 5: 意义 — "这个研究对领域有什么贡献？"
WorkBuddy 调度
使用 Agent 工具派发子代理实现各个 Agent：
研究问题 Agent: 探索项目上下文 → 生成 FINER 评分研究问题
文献检索 Agent: 使用 WebSearch/WebFetch 检索 → 筛选 → 注释
来源验证 Agent: 交叉验证来源 → 证据等级分级
综合分析 Agent: 跨来源对比 → 主题提取 → 矛盾标记
报告编撰 Agent: 按 APA 7.0 格式组织报告
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.
- 10d ago First seen · 113 lines · 150 tokens per session scan A ddfa8448f552
deep-research is a skill published in the GitHub repository yinqd3/workbuddy-skills (6 stars, last pushed 3mo ago), licensed MIT. It adds 150 tokens to every session and 1,530 once invoked, about $0.0007 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
results-report
A workflow for turning completed experiment analyses into a structured research report with findings, limitations, failures, and next steps.
math-unicode
Use whenever you need to express mathematical notation — equations, filters, set-builder, statistics, calculus, logic, ratios, drops, counts. Emit Unicode math glyphs INLINE; never wrap in $…$, \(...\), or $$...$$. Terminal coding agents (Claude Code, Codex CLI, and others) do not render LaTeX, so raw delimiters…
obsidian-markdown
Obsidian Flavored Markdown syntax reference — wikilinks, embeds, callouts, properties/frontmatter, tags, comments, block IDs. Use when creating or editing .md files in an Obsidian vault, when linking or embedding notes, when writing callouts or note frontmatter, or when the user mentions wikilinks, backlinks, block…
obsidian-docs
Create comprehensive technical documentation following Obsidian conventions with bidirectional linking, proper folder structure, templates, and developer-focused content. Use when creating documentation, READMEs, wikis, knowledge bases, ADRs, runbooks, or any technical writing. Triggers on: documentation, docs…
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
skill-creator
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.