award-paper-mining SKILL.md skillA
award-paper-mining from fourteen1416/academic-agent-toolkit is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add fourteen1416/academic-agent-toolkit/award-paper-mining@git:20260927.a059f3aPins git:20260927.a059f3a in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- fourteen1416/academic-agent-toolkit
- Path
academic-toolkit/skills/award-paper-mining/SKILL.md- Versions recorded
- 4
- Latest version
- git:20260927.a059f3a, committed Sep 27, 2026
- First version recorded
- Sep 23, 2026
- Size
- 5,643 bytes
- Repository stars
- 12
- License
- a license file GitHub does not identify
挖掘获奖论文语料，沉淀为可复用统计与版面资产（采集归档、统计报告、版面蒸馏）。触发词：优秀论文挖掘、获奖论文语料、范文库、award paper mining、历年论文归档、论文统计报告、版面蒸馏、论文套壳、章节骨架、句式模板。.
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
# award-paper-mining — 获奖论文语料挖掘与统计沉淀
## 定位
把"国赛/美赛优秀论文"从公开展示页沉淀为**可复用的结构化语料、统计资产与版面资产**，持续喂养
论文写作与文献步的范文参照。本技能固化的是本仓已跑通一届样本（2021-2025 共 62 篇）的
流水线：**抓取 → 归档 → 合并 → 关键页语义标注 → 结构化 JSON → 统计报告 → 版面蒸馏**。
版面蒸馏的目标：在作者已有自己的建模、数据与计算结果的前提下，把成果**套上国奖水准的
论文外壳**——章节骨架、摘要页结构、段落功能句式、图表规范、排版规格全部对齐获奖范文；
模型推导、代码实现、方案决策不在版面蒸馏范围内。
**产物落私有资料区**（`assets-local/award-papers/`，gitignored，无再分发权）；
**清单与统计摘要**（本文档同目录的 `references/` 与 `data/award_paper_exemplars.json`）入 git。
## 输入契约
- 目标年份/赛事/题型（如"2026 国赛 A-E"）
- 公开展示源（历年：中国大学生在线 dxs.moe.gov.cn；美赛：COMAP）——**只采集公开往届展示页**
- 复用策略：已有年份只增量补差；整届重跑须先声明
## 执行步骤
1. **抓取与归档**（`年/论文号/页号.jpg` 结构）
- 逐届抓取公开展示页，按 `年/论文号/` 归档页面件；记录来源 URL 与抓取日期
- 断链/缺页如实登记，不伪造补全
2. **逐篇合并 PDF**
- 按篇合并页面为 `年_论文号.pdf`；合并件仅作整篇快读，**页面件是唯一真源**
- 体积膨胀预警：合并件常达页面件 15 倍，归档前评估冷存储去向
3. **关键页语义标注**（每篇 7 页：封面/摘要/重述/建模/求解/结果/结论）
- 标注页角色写入结构化条目；这是让语料"可检索/可对照"的关键元数据
4. **结构化 JSON 底座**
- 每篇一条：`year / paper_id / 题型 / 页数 / 关键页映射 / problem / model / methods / key_takeaways`
- **字段填充率如实登记**（空字段标 unavailable，不占位编造）
5. **统计报告**（可编码规则优先）
- 摘要统计（字数区间/四要素完整度）、图表配色统计（口径显式声明：页面级≠图表级）、
文风量化（样本覆盖数如实标注）
- 每条统计给**样本量与口径**；口径缺陷在文首更正说明
…Read the whole file at its exact version.
How to install
mdr add fourteen1416/academic-agent-toolkit/award-paper-mining@sha256:9684b05b9e7e6377The line at the top of this page pins the label git:20260927.a059f3a, 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_oaanppcpbcutsayx)
1 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 4 versions of this file, between Sep 23, 2026 and Sep 27, 2026, about one every 2 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260927.a059f3a latest | 2026-09-27 | a059f3a | 5,643 B | A | view · diff |
| git:20260923.38362cb | 2026-09-23 | 38362cb | 5,764 B | A | view · diff |
| git:20260923.c5ddd43 | 2026-09-23 | c5ddd43 | 3,923 B | A | view · diff |
| git:20260923.980ae39 | 2026-09-23 | 980ae39 | 3,926 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 (5643 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
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_oaanppcpbcutsayx GET https://markdownregistry.com/api/v1/resolve?ref=fourteen1416/academic-agent-toolkit/award-paper-mining GET https://markdownregistry.com/api/v1/blob/9684b05b9e7e637704fda39295d557a743409321504fe55995fa8063a0dba7b0
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.