AGENTS.md@academic-toolkitA

AGENTS.md@academic-toolkit from fourteen1416/academic-agent-toolkit is an AGENTS.md file: the standing instructions coding agents read in that repo.

Install it, pinned
mdr add fourteen1416/academic-agent-toolkit/academic-toolkit/AGENTS.md@git:20261023.0a9dfaa

Pins git:20261023.0a9dfaa in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 14 of 14 checks passed
Kind
AGENTS.md file
Repository
fourteen1416/academic-agent-toolkit
Path
academic-toolkit/AGENTS.md
Versions recorded
5
Latest version
git:20261023.0a9dfaa, committed Oct 23, 2026
First version recorded
Sep 23, 2026
Size
11,107 bytes
Repository stars
12
License
a license file GitHub does not identify

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

# academic-toolkit — 全学术 Agent 系统(宿主无关)

**主控 = 当前驱动本项目的 Agent**。同一时刻只有一个主控;不存在「调用另一个 agent runtime」的逻辑。
本仓库服务六大领域:数模竞赛、学术论文、文献与研究、课程与研究材料、知识产权材料、图表与文档生产。绘图不是系统边界。

## 一、架构与所有权

| 层 | 唯一职责 | 位置 |
|---|---|---|
| 当前Agent | 理解任务、领域推理、方法选择、内容与结果解释 | 当前宿主 |
| 技能 | 当前单步的专业作业方法,不重复排整条流程 | `skills/` |
| 执行侧 | 资源读取、文件编辑、真实工具运行、依赖复用、评审收发 | `execution/` |
| 引擎 | 合同解析、状态、唯一验收、检查点与审计 | `engine/` |
| 工具 | 检索、求解、编译、格式化等具体操作 | `tools/` |
| 目录与资产 | 能力、技能索引、数据和参考材料 | `data/`;`../capabilities/`、`../assets-local/`(仓库根,本表其余路径相对 `academic-toolkit/`) |

引擎只编排不执行Agent。执行侧不决定研究结论,也不自行批准。工作流SQLite是状态真源,操作表记录真实执行;没有证据不能写成成功。

执行步骤动作走宿主无关的 `StepAction.workspace`(与 `skills/`、宿主无关协议、`workflow_cli` 同口径):步骤产出与编辑以工作区相对路径登记,不绑定任何宿主私有路径或宿主专属 API。

## 二、启动与执行

在 `academic-toolkit/` 中:

```bash
python -m engine.workflow_cli boot
python -m engine.workflow_cli probe
python -m engine.workflow_cli start --template <模板> --workspace <工作区> --params <业务参数JSON>
python -m engine.workflow_cli next --wf <工作流ID> --db <数据库>
```

已存在工作流则恢复,不重建。`next` 返回当前任务、合同和执行会话;真实主技能与必用技能正文直接提供。入口技能负责选模板,不能嵌套成单个业务步骤。

## 三、任务路由

| 用户任务 | 模板或单步能力 |
|---|---|
| 国赛完整解题 | `comp_cumcm` |
| 华为杯完整解题 | `comp_huawei` |
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add fourteen1416/academic-agent-toolkit/academic-toolkit/AGENTS.md@sha256:b4056b32982d19e8

The line at the top of this page pins the label git:20261023.0a9dfaa, 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.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_ggmg23xyexwcxede.svg)](https://markdownregistry.com/a/art_ggmg23xyexwcxede)

2 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 5 versions of this file, between Sep 23, 2026 and Oct 23, 2026, about one every 7 days.

versioncommittedcommitsizeaudit
git:20261023.0a9dfaa latest2026-10-23 0a9dfaa 11,107 BA view · diff
git:20260927.965986c2026-09-27 965986c 9,370 BA view · diff
git:20260923.f7df9722026-09-23 f7df972 18,103 BA view · diff
git:20260923.a3587452026-09-23 a358745 16,771 BA view · diff
git:20260923.40d44082026-09-23 40d4408 16,948 BA view

Audit of the latest version

A  14 of 14 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Size between 200 bytes and 200 KB (11107 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

GitHub

fourteen1416/academic-agent-toolkit · 12 stars · license a license file GitHub does not identify · pushed 2026-10-27 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_ggmg23xyexwcxede
GET https://markdownregistry.com/api/v1/resolve?ref=fourteen1416/academic-agent-toolkit/academic-toolkit/AGENTS.md
GET https://markdownregistry.com/api/v1/blob/b4056b32982d19e85ed945615925176665a4624b3b5db0d35ef74115f2088340

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: how to write a good AGENTS.md · AGENTS.md vs CLAUDE.md · which agent file does what.

More from fourteen1416/academic-agent-toolkit

AGENTS.md AGENTS.md file
fourteen1416/academic-agent-toolkit · AGENTS.md
git:20261024.6925a98 · audit A · 12 stars
ablation-planner SKILL.md skill
fourteen1416/academic-agent-toolkit · academic-toolkit/skills/ablation-planner/SKILL.md · Use when main results pass result-to-claim (claim_supported=yes or partial) and ablation studies are needed to answer…
git:20260927.a059f3a · audit A · 12 stars
agent-bootstrap SKILL.md skill
fourteen1416/academic-agent-toolkit · academic-toolkit/skills/agent-bootstrap/SKILL.md · 任意智能体自举驱动本academic-toolkit:读协议、探测能力、选择路由或启动工作流。触发词:启动项目、如何驱动、bootstrap、自举、宿主无关接入、agent 开始工作。
git:20260927.efd5131 · audit A · 12 stars
agent-figure-gallery SKILL.md skill
fourteen1416/academic-agent-toolkit · academic-toolkit/skills/agent-figure-gallery/SKILL.md · Query the AgentFigureGallery visual reference KB, show candidates for human preference selection, and export selected…
git:20260927.a059f3a · audit A · 12 stars
analyze-results SKILL.md skill
fourteen1416/academic-agent-toolkit · academic-toolkit/skills/analyze-results/SKILL.md · Analyze ML experiment results, compute statistics, generate comparison tables and insights. Use when user says "analyze…
git:20260923.2013b81 · audit A · 12 stars
anti-ai-detection SKILL.md skill
fourteen1416/academic-agent-toolkit · academic-toolkit/skills/anti-ai-detection/SKILL.md · 中文学术文本 AI 特征检测:八维度加八项统计特征分析、AI 味改写建议、改写质量检查,并生成国赛 AI 使用声明。触发词:反AI检测、AI味、去AI化、AI 生成特征、AI 使用声明。
git:20260923.f7822e6 · audit A · 12 stars
anti-defensive-writing SKILL.md skill
fourteen1416/academic-agent-toolkit · academic-toolkit/skills/anti-defensive-writing/SKILL.md · 删减防御性写作:去掉不必要的免责声明、模糊限定、道歉式表述、自我贬低与过度解释,同时保留必要的范围/准确性/安全/法律/伦理/方法学限定。触发词:更简洁、更有力、更直接、更自信、少限定、少免责、别啰嗦、不要过度解释、改掉…
git:20260927.efd5131 · audit A · 12 stars
arxiv-metadata SKILL.md skill
fourteen1416/academic-agent-toolkit · academic-toolkit/skills/arxiv-metadata/SKILL.md · Fetch structured metadata for an arXiv paper. Use when you have an arXiv ID or URL and need title, authors, date, or…
git:20260927.a059f3a · audit A · 12 stars
arxiv-submission-package SKILL.md skill
fourteen1416/academic-agent-toolkit · academic-toolkit/skills/arxiv-submission-package/SKILL.md · Prepare an arXiv submission package from a LaTeX paper. Cleans the source, builds a tarball, and extracts metadata for…
git:20260927.a059f3a · audit A · 12 stars
arxiv SKILL.md skill
fourteen1416/academic-agent-toolkit · academic-toolkit/skills/arxiv/SKILL.md · Search, download, and summarize academic papers from arXiv. Use when user says ”search arxiv”, ”download paper”, or…
git:20260927.a059f3a · audit A · 12 stars
assets-inventory SKILL.md skill
fourteen1416/academic-agent-toolkit · academic-toolkit/skills/assets-inventory/SKILL.md · 扫描用户上传的资产(题目/代码/数据/图/结果),输出资产清单 ASSETS_INVENTORY.md 与一致性冲突报告 ASSETS_CONFLICTS.md,供后续步骤决定哪些资产已有、哪些需要补全。
git:20260923.2013b81 · audit A · 12 stars
auto-paper-improvement-loop SKILL.md skill
fourteen1416/academic-agent-toolkit · academic-toolkit/skills/auto-paper-improvement-loop/SKILL.md · 论文自动改进循环(2 轮):先由外部审稿模型评审,再按要求改稿,最后重编译验证。触发词:改论文、improve paper、论文润色循环、auto improve、迭代打磨论文。
git:20260927.efd5131 · audit A · 12 stars

Every file in fourteen1416/academic-agent-toolkit

Browse by kind, by grade A, or by owner.