lit-pyramid SKILL.md skillA
lit-pyramid 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/lit-pyramid@git:20261103.34046b9Pins git:20261103.34046b9 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/lit-pyramid/SKILL.md- Versions recorded
- 4
- Latest version
- git:20261103.34046b9, committed Nov 3, 2026
- First version recorded
- Jul 4, 2026
- Size
- 3,968 bytes
- Repository stars
- 10
- License
- a license file GitHub does not identify
文献金字塔分层（乔淼PhD · AI学术训练营 · AI学术工作流）。把一份已验真的文献清单按硬指标分到 Classic / Key Texts / Supporting 三层：Classic 四条硬指标（概念奠基 + 被引门槛 + 持续被引）、Key 三条（顶刊 + 对话关系 + 年均引用）、Supporting 按 PXYV 节点配额；含对话关系判定与覆盖配额检查。Trigger on："把这些文献做金字塔分层"、"文献金字塔"、"帮我把文献库分 Classic/Key/Supporting"、"tier my literature into a pyramid"。.
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
# Lit Pyramid · 金字塔分层（Classic / Key / Supporting） 对**已验真**的清单做三件事：金字塔分层、对话关系判定、覆盖配额检查。真伪 / 相关性初筛不在本 skill（先跑 `lit-verify`）。 ## 调用约定（独立运行） - 输入：已验真的文献清单（含被引数；来自 `lit-verify`，或用户给的 Zotero 集合 / 表格）+ 本研究 RQ（用户给一句话，或读 `选题.md`）。清单没有被引数 → 先补采（OpenAlex / Scholar / CNKI）。 - 参数（默认可覆盖）：Key 篇数默认 5；Supporting 每节点配额默认 = 余量/4。 - 输出：会话内分层表；可落盘 `文献金字塔.md`（分层版，默认当前工作目录；名字有意区别于 lit-pdf-zotero 的最终 `文献清单.md`，避免顺跑撞名）。 - **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。 ## 金字塔三层硬指标 - **Classic（1 篇）** 四条全满足：① P 维度核心概念的命名者/奠基者（同领域 ≥3 篇综述把它列为概念出处）② 总被引 ≥500（社科）或 ≥1000（自然科学/CS）③ 发表 ≥10 年仍在被引（近 2 年仍有 ≥10 次新引用）④ 不受发表年限限制。 - **Key Texts（N 篇）** 三条全满足：① 发表在 P 所在领域 top-tier 期刊（表格注明期刊名 + 位次依据：SSCI Q1 / 北大核心 / 影响因子 / CNKI 高被引；英文期刊的收录、影响因子、JCR 分区用 `journal-rank` 查，不凭印象写）② 与本研究 RQ 存在**直接对话关系** ③ 近 5 年年均引用 ≥10。整组 Key 必须覆盖 P / X / V 三维，每维 ≥1 篇（Y 通常无 Key）。 - **Supporting（~余量）**：① 提供具体证据（数据 / 案例 / 方法对照 / 政策文本 / 行业报告均可）② 按 P/X/Y/V 四节点分配：P/X ≥5，Y/V ≥3 ③ 同行评审优先；权威机构报告可作 Y 节点补充。 ## 三机制检查 1. **分层归位**：每篇明确判到 Classic / Key / Supporting / 拒（四选一），注明分层证据（Classic 给引用数 + 概念出处证据；Key 给期刊名 + 年均引用 + 对话关系；Supporting 给证据类型）；不满足任一层硬指标 → 拒并注明具体指标。 …
Read the whole file at its exact version.
How to install
mdr add qiaomiaojoe/ai-academic-workflow/lit-pyramid@sha256:15eb71d61cdb8a9aThe line at the top of this page pins the label git:20261103.34046b9, 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_2oldn24ocvixnw4x)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 4 versions of this file, between Jul 4, 2026 and Nov 3, 2026, about one every 41 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261103.34046b9 latest | 2026-11-03 | 34046b9 | 3,968 B | A | view · diff |
| git:20260717.efc442f | 2026-07-17 | efc442f | 3,876 B | A | view · diff |
| git:20260717.59c14bf | 2026-07-17 | 59c14bf | 3,456 B | A | view · diff |
| git:20260704.8f9ae45 | 2026-07-04 | 8f9ae45 | 3,464 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 (3968 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_2oldn24ocvixnw4x GET https://markdownregistry.com/api/v1/resolve?ref=qiaomiaojoe/ai-academic-workflow/lit-pyramid GET https://markdownregistry.com/api/v1/blob/15eb71d61cdb8a9a8683d91f49ce4472ef81bc7e442ca3f42bb11ad51b2df0e0
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.