literature-search SKILL.md skillA
literature-search from qiaomiaojoe/ai-academic-workflow is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add qiaomiaojoe/ai-academic-workflow/literature-search@git:20261031.310c480Pins git:20261031.310c480 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- qiaomiaojoe/ai-academic-workflow
- Path
skills/literature-search/SKILL.md- Versions recorded
- 5
- Latest version
- git:20261031.310c480, committed Oct 31, 2026
- First version recorded
- Jul 3, 2026
- Size
- 4,198 bytes
- Repository stars
- 10
- License
- a license file GitHub does not identify
文献搜索完整任务入口（乔淼PhD · AI学术训练营 · AI学术工作流）。编排四个步骤 skill 跑完一次完整的文献搜索：pxyv-search 四维检索 → lit-verify 验真 → lit-pyramid 金字塔分层 → lit-pdf-zotero 获取 PDF + 入库 Zotero + 可视化，每阶段停下等确认。用户只要单独某一步（只检索/只验真/只分层/只入库）时直接用对应步骤 skill，不走本入口。Trigger on："帮我搜文献"、"完整跑一遍文献搜索"、"搜 30 篇文献入 Zotero"、"文献搜索工作流"、"search literature and import to Zotero"。.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Literature Search · 文献搜索任务编排 一次完整的文献搜索 = 四个步骤 skill 按序执行，**每阶段完成后输出结果表、停下等用户确认**（用户说"继续"就直接进下一阶段）： | 阶段 | 调用 skill | 产出 | |------|-----------|------| | 1 检索 | `pxyv-search` | 四维候选清单（验真前） | | 2 验真 | `lit-verify` | 验真报告 + 干净清单（含被引数） | | 3 分层 | `lit-pyramid` | Classic / Key / Supporting 分层表 + 维度缺口表 | | 4 落地 | `lit-pdf-zotero` | PDF 落盘 + 文献清单.md + Zotero 入库 + 可视化 HTML | ## 编排规则 - 开工前收齐参数一次问全：选题（PXYV 或一句话，一句话则先经 `topic-pxyv-parse`）、目标总篇数（默认 30）、Key 篇数（默认 5）、年限（默认近 5 年）、语言、Zotero Collection 名、额外检索要求。参数在各阶段透传给对应 skill。 - 各阶段严格按对应 skill 的 SKILL.md 协议执行，不要在本入口里即兴替代（对应 skill 不可用时，读其 SKILL.md 内容内联执行）。 - 阶段 3 出现维度缺口时，问用户是否回阶段 1 补搜（给关键词建议），补搜的增量走 2→3 再并入。 - 全程硬约束：**不编造文献，宁缺毋滥**；某维度验真后不足配额，明确说"仅找到 N 条可信文献，建议补搜"，不凑数。 - **语言构成也是要求，不能拿另一种语言补**：用户选了「中英混合」（或纯中 / 纯英），验真后某种语言不够（比如知网用不了、中文大量剔除），**不准用另一种语言补满总数**。停下来告诉用户：这种语言只核实了 N 条、卡在哪（知网连不上 / 要登录 / 验证码……），给选项——补搜这种语言 / 用户登录知网后重新验真 / 接受这种语言少于预期。总数因此不到目标篇数，就照实交少的。 - **每阶段结果表和最终报告都写语言分布**（中文 N / 英文 M），和用户要的对照；对不上时最终报告开头就写明，不能笼统说「完成」。 - **调用方覆盖约定**：调用方（工作台 prompt / 用户）显式给出的参数、输入路径、落盘路径与工具选择，一律覆盖本 skill 的默认；但本 skill 的方法步骤、硬约束与停点不可被省略或稀释——调用方若要求跳过某硬约束，以本 skill 为准并提示冲突。 ## 快速模式 …
Read the whole file at its exact version.
How to install
mdr add qiaomiaojoe/ai-academic-workflow/literature-search@sha256:22ca468415a2bdc1The line at the top of this page pins the label git:20261031.310c480, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_3an4egzw5iyy77ne)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 5 versions of this file, between Jul 3, 2026 and Oct 31, 2026, about one every 30 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261031.310c480 latest | 2026-10-31 | 310c480 | 4,198 B | A | view · diff |
| git:20261014.1ae645b | 2026-10-14 | 1ae645b | 3,175 B | A | view · diff |
| git:20260717.efc442f | 2026-07-17 | efc442f | 2,366 B | A | view · diff |
| git:20260704.8f9ae45 | 2026-07-04 | 8f9ae45 | 2,037 B | A | view · diff |
| git:20260703.eabb41d | 2026-07-03 | eabb41d | 12,038 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (4198 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
qiaomiaojoe/ai-academic-workflow · 10 stars · license a license file GitHub does not identify · pushed 2026-11-03 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_3an4egzw5iyy77ne GET https://markdownregistry.com/api/v1/resolve?ref=qiaomiaojoe/ai-academic-workflow/literature-search GET https://markdownregistry.com/api/v1/blob/22ca468415a2bdc166bb9ce06d3eb7e37212f61417f0448f9f898155748154ed
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.
More from qiaomiaojoe/ai-academic-workflow
Every file in qiaomiaojoe/ai-academic-workflow