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 phd-literature-reviewgit 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/phd-literature-review)<a href="https://agentmods.dev/skills/yipng05-max/-skills/phd-literature-review"><img src="https://agentmods.dev/badge/skills/yipng05-max/-skills/phd-literature-review/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/phd-literature-review"><img src="https://agentmods.dev/badge/skills/yipng05-max/-skills/phd-literature-review.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 | $0.00281 | $0.04791 |
| Opus 5 | $0.00140 | $0.02396 |
| Sonnet 5 | $0.00056 | $0.00958 |
| Haiku 4.5 | $0.00028 | $0.00479 |
Grade A, and why
phd-literature-review 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 — 252 lines — stays where its author put it; the contents beside it link to each section on GitHub.
博士论文文献综述工程化写作系统 (PhD-LitReview-Auto-Flow)
00. 运行时协议
- 心跳信号: 每次回复最顶端输出
[PhD-LitReview-Auto-Flow]。 - 状态继承: 系统启动时强制提取或要求用户投喂核心资产（必须包含：专业领域、研究方向、选题名称、研究主问题、研究子问题、核心概念/关键词、文献综述的分类标准）。
- 2万字饱和与差异化字数规训:
- 本章总字数目标约 2 万字。
- P4（各主题模块写作）：每个主题模块 2,500 - 4,000 字，视主题权重而定。核心概念界定模块可适当压缩至 1,500 - 2,500 字。
- P5（研究述评与空白识别）：2,000 - 3,000 字。
- P6（本章小结）：800 - 1,200 字。
- 熔断与绝对单步机制: 绝对禁止一次性输出所有内容。在分主题撰写阶段（P4），每次只能输出一个主题模块，写完必须停止，等待用户指令后再写下一个。
- 行文参差感规训: 核心论证段落使用长段落（600-800字）进行深度综合与评述，概念界定与过渡使用短段落（150-300字），形成学术节律感。避免全篇均匀分段。
- 引注格式绝对规训: 强制使用
(作者, 出版年)格式。中文双作者用顿号（如(张三、李四, 2020)），英文双作者用&（如(Smith & Jones, 2020)）。三人及以上首次全列，后续用"等/et al."。去主语化引用为主（括号引用），嵌入式引用（如"Smith(2020)指出…"）仅在突出特定学者贡献时使用。 - 文献真实性铁律: 所有引用文献必须经过检索核实。每个主题模块写作完成后，立即调用
literature-verifierskill 核查该模块所引文献。未核实通过的文献立即移除并补充替代文献。严禁编造或猜测任何文献信息。 - 博士论文文献综述与顶刊文献综述的核心差异:
| 维度 | 博士论文文献综述（本skill） | 顶刊文献综述 |
|---|---|---|
| 长度 | 2万字（30-50页） | 2-5页 |
| 目的 | 展示全面深入的文献掌握能力 | 论证研究空白，支撑研究设计 |
| 覆盖 | 力求系统、全面、穷尽 | 战略性选取，服务论证 |
| 组织 | 主题式为主，兼顾时间演进 | 纯主题式、论证式 |
| 概念 | 需独立设节进行概念界定与辨析 | 概念界定嵌入论证 |
| 批判 | 全面评价各研究优缺点 | 精准指出与本文相关的局限 |
| 理论 | 需梳理理论流派的完整发展脉络 | 仅选取直接相关理论 |
| 述评 | 需独立设节进行系统性研究述评 | 以研究空白收束即可 |
01. 执行工作流
P0: 核心资产锁定与分类标准探针
- 动作 1: 系统打招呼，索要 7 项核心资产：
- 专业领域（如管理学、教育学、社会学、传播学等）
- 研究方向（如组织行为学、教育技术、社会治理等）
- 选题名称（完整的博士论文题目）
- 研究主问题（一句话概括）
- 研究子问题（列表，通常 3-5 个）
- 核心概念/关键词（3-6 个，如"数字化转型""组织韧性""动态能力"）
- 文献综述的分类标准偏好（A.按核心概念分类 B.按理论流派分类 C.按研究方法分类 D.按时间演进分类 E.混合分类 F.由系统推荐）
- 动作 2: 询问用户是否已有文献库（如 EndNote/Zotero 导出清单、已读论文清单、开题报告文献列表），若有则要求投喂。
- 动作 3: 询问写作语言（中文/英文）及引注格式偏好（A.APA第7版 B.GB/T 7714-2015 C.其他自定义格式）。
- 强制停止点: 等待用户提供全部核心资产后方可继续。
P1: 文献版图规划与主题模块设计
-
动作 1: 根据核心资产，将文献综述拆解为 4-7 个主题模块。模块设计需阅读
references/structure-patterns.md选择合适的结构模式。 -
动作 2: 为每个主题模块明确以下要素并以表格形式呈现：
序号 模块标题 核心任务 预估字数 检索关键词 1 核心概念界定与辨析 界定X/Y/Z概念内涵、外延与关系 2000字 ... 2 [主题A] ... 3500字 ... ... ... ... ... ... N-1 研究述评与空白识别 系统评价+识别Gaps 2500字 — N 本章小结 凝练总结 1000字 —
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.
- 12d ago First seen · 252 lines · 281 tokens per session scan A b4f9879af8f3
phd-literature-review is a skill published in the GitHub repository yipng05-max/-skills (286 stars, last pushed 4mo ago), licensed MIT. It adds 281 tokens to every session and 4,791 once invoked, about $0.0014 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…