comp-code SKILL.md skillA
comp-code 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/comp-code@git:20261023.cb0b591Pins git:20261023.cb0b591 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/comp-code/SKILL.md- Versions recorded
- 5
- Latest version
- git:20261023.cb0b591, committed Oct 23, 2026
- First version recorded
- Sep 23, 2026
- Size
- 68,593 bytes
- Repository stars
- 12
- License
- a license file GitHub does not identify
数学建模竞赛编程实现。根据建模报告编写代码、执行计算、收集结果。Use when user says "编程", "写代码", "code implementation".
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
# 竞赛编程实现 根据建模报告编写代码并执行计算：**$ARGUMENTS** ## ⛔⛔⛔ 任务规模警示（先读这段, 再读后面所有内容） **这不是简单任务。** 数学建模竞赛的 comp-code 步骤要把建模报告里**每个**子问题落地成可跑的代码 + 真实结果。 子问题数量由 MODELING_REPORT.md 决定（一问也可能, 多问也可能）, 不是固定的。 ⛔ **判断你是否真的做完了**, 在 `end_turn` 之前自问： 1. MODELING_REPORT.md 里有几问？你是不是真的为每问都写了独立的 .py？ 2. `figures/` 下是不是每问都有对应的 `problem_*_results.json` 且文件非空？ 3. RESULTS.md 是不是已经存在, 包含每问的方法和数值结果？ 4. 跑过完成铁律最后那段 bash 验证脚本了吗？ **任何一项答 "否" → 不要 `end_turn`, 继续干活。** 引擎会反复检测这些产物, 没产出会自动重新拉你回来重做, 与其被动重做不如一次做完。 ⛔ **不要用 "我已经做了主要工作, 剩下的晚点再说" 的心态退出**。 "晚点" 在 LLM 单轮预算里不存在 — 一旦 `end_turn`, 你就被切断了, 下一次进来要重新读上下文 + 重新理解任务, 比当前继续干活贵得多。 ### ⛔⛔⛔ 长求解必须【前台同步等】—— 禁止"后台跑 + 等唤醒"的反模式（会烧光额度） **你现在是非交互模式（无下一轮对话），没有"下一轮"。一旦你 `end_turn`，整个进程立即被切断——你用 `run_in_background` 起的后台任务、你挂的 Monitor 监视，全部随之作废，那条"稍后会有通知把我唤醒"的假设【永远不成立】。** 之前真实翻车过：把求解丢后台 → 挂 Monitor → 说"我等通知"就 `end_turn` → 后台求解跟着被杀、RESULTS.md 从没产出 → 引擎判产出不完整 → 自动重试 → 下一次又重复同样的错 → 白白烧掉多轮额度。 - **❌ 禁止**：`求解脚本 &`（后台）/ `run_in_background` 跑长求解 + Monitor 监视 + `end_turn` 等唤醒。**只要你打算 `end_turn`，后台任务就等于没跑。** - **✅ 必须**：长求解【前台同步等它真正返回】——`timeout 3600 "$PYTHON" problemN.py ...`（超时值按下文"求解器超时设置"，最长 1 小时），**站在原地等到它打印出结果、写出 json 文件为止**，再继续下一步。求解慢没关系，前台等就是了；额度花在"真的在算"上不亏，花在"反复重试白跑"上才亏。 …
Read the whole file at its exact version.
How to install
mdr add fourteen1416/academic-agent-toolkit/comp-code@sha256:d8859b2a3622257dThe line at the top of this page pins the label git:20261023.cb0b591, 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_a7ov7jhwk6klfzen)
1 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 8 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261023.cb0b591 latest | 2026-10-23 | cb0b591 | 68,593 B | A | view · diff |
| git:20260927.a059f3a | 2026-09-27 | a059f3a | 66,038 B | A | view · diff |
| git:20260927.efd5131 | 2026-09-27 | efd5131 | 66,022 B | A | view · diff |
| git:20260923.a358745 | 2026-09-23 | a358745 | 67,531 B | A | view · diff |
| git:20260923.ee897a0 | 2026-09-23 | ee897a0 | 67,540 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 (68593 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_a7ov7jhwk6klfzen GET https://markdownregistry.com/api/v1/resolve?ref=fourteen1416/academic-agent-toolkit/comp-code GET https://markdownregistry.com/api/v1/blob/d8859b2a3622257d97f53d0779f105937f3b57af953664d1594aa114ac414ee0
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.