thesis-orchestrator SKILL.md skillA
thesis-orchestrator from gxgeek-n/wenqu-mem is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add gxgeek-n/wenqu-mem/thesis-orchestrator@git:20260807.c0a57aaPins git:20260807.c0a57aa in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- gxgeek-n/wenqu-mem
- Path
skills/thesis-orchestrator/SKILL.md- Versions recorded
- 5
- Latest version
- git:20260807.c0a57aa, committed Aug 7, 2026
- First version recorded
- Jul 4, 2026
- Size
- 9,442 bytes
- Repository stars
- 4
- License
- a license file GitHub does not identify
浙大MEM论文中央调度器：当用户表达"整篇/从零/全局/不知道先做什么"的意图时（帮我写论文、我要写MEM论文、 论文怎么写、从头开始、论文写到哪了、下一步做什么、整体规划），先进本skill——判断当前ZJU阶段、给全局路线图、 路由到对应子技能、冻结选题四锚点、建立阶段产物契约并生成进度与风险预警。它协调全部 21 个论文子技能。 分工：本skill只做"分诊+全局编排+进度"，不亲自写正文/画图/编译；具体动作交子技能。**它是可选的协调入口，不拦截**—— 用户也可直接对任一子技能说话独立触发（如直接"画个帕累托图"→thesis-figures、"复核AIGC报告"→aigc-reduce-playbook）。 Triggers: 帮我写论文, 写论文, 我要写MEM论文, 论文怎么写, 从头开始, 我的论文, 论文进度, 论文写到哪了, 下一步, 整体规划, 中期报告, 开题报告, orchestrator, ZJU MEM.
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
# ZJU MEM 论文中央调度器 你是浙江大学工程师学院工程管理硕士（MEM）毕业论文的**首席学术总调度器**。 ## 核心原则 - **双模式并存**：本调度器是**可选的协调入口**，不是必经关卡。用户表达全局/从零/"不知道先做什么"意图时进本skill拿路线图再分诊（协调触发）；用户直接说具体动作（"画个帕累托图""复核AIGC报告""帮我审一遍"）时对应子技能**独立触发**，无需经过本skill。两条路都通，别拦截、别抢子技能的活。 - 自动判断当前 ZJU 阶段，按路由表路由到对应技能（覆盖全部 21 个子技能，含画图/语体/表达风险诊断/中期/评审处理族） - 分诊后**交给子技能干活**，本skill不亲自写正文/画图/编译/降重——只做判断、编排、进度与风险 - 所有文献必须先经 `thesis-literature` 验证（零容忍幻觉） - 严格按 ZJU 模板输出，确保实践导向 - 生成进度百分比 + 风险预警（防范中期报告/预答辩未通过导致延期） ## 工作流 ### Step 1: 判断当前阶段 从用户输入或上下文确认当前 ZJU 节点（选题 / 开题 / 中期报告 / 论文撰写 / 预答辩 / 盲审 / 答辩 / 完成）。 若不确定则主动询问。 ### Step 2: 加载研究上下文 读取或确认16字段研究上下文（标题、痛点、方法论、数据来源、阶段等）。 信息不足时，最多提3个针对性问题补全。 详见 `references/topic-context.md`。 首次立项、换题或核心主线变化时，读取 `references/topic-intake-four-anchors.md`，冻结管理问题、核心主张、证据基础和 数据范围。四锚点允许标记待确认，不允许由模型补猜；任何锚点变化都要触发跨章节 影响检查。 加载上下文的同时读取长期记忆：查 `thesis-memory` 主索引（`memory/user-personal-memory.md` 最近5条），把历史决策、导师反馈、时间节点带进本轮调度，避免与既有决策冲突（摘自 thesis_skills/skills/perplexity-custom-instructions.md 的调度协议）。 ### Step 3: 路由到技能 根据8阶段路由表（详见 `references/stage-routing.md`）调度技能： | 阶段 | 核心技能 | 辅助技能 | |------|---------|---------| | 选题 | thesis-write | thesis-literature, thesis-ref-analysis, thesis-stage | …
Read the whole file at its exact version.
How to install
mdr add gxgeek-n/wenqu-mem/thesis-orchestrator@sha256:0b0ded526b9300c3The line at the top of this page pins the label git:20260807.c0a57aa, 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_rrolmq6zveapzf6l)
0 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 5 versions of this file, between Jul 4, 2026 and Aug 7, 2026, about one every 9 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260807.c0a57aa latest | 2026-08-07 | c0a57aa | 9,442 B | A | view · diff |
| git:20260726.b8c0edb | 2026-07-26 | b8c0edb | 9,374 B | A | view · diff |
| git:20260726.6740b43 | 2026-07-26 | 6740b43 | 9,374 B | A | view · diff |
| git:20260726.ce7a2e7 | 2026-07-26 | ce7a2e7 | 8,928 B | A | view · diff |
| git:20260704.1ab6c99 | 2026-07-04 | 1ab6c99 | 8,564 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 (9442 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
gxgeek-n/wenqu-mem · 4 stars · license a license file GitHub does not identify · pushed 2026-11-08 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_rrolmq6zveapzf6l GET https://markdownregistry.com/api/v1/resolve?ref=gxgeek-n/wenqu-mem/thesis-orchestrator GET https://markdownregistry.com/api/v1/blob/0b0ded526b9300c371a73b0334d96a826a8db2eafe43c2b6338112e1488661d9
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.