comp-problem-analysis SKILL.md skillA
comp-problem-analysis 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-problem-analysis@git:20260927.efd5131Pins git:20260927.efd5131 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-problem-analysis/SKILL.md- Versions recorded
- 4
- Latest version
- git:20260927.efd5131, committed Sep 27, 2026
- First version recorded
- Sep 23, 2026
- Size
- 65,788 bytes
- Repository stars
- 12
- License
- a license file GitHub does not identify
数学建模竞赛赛题分析。拆解子问题、定义变量、拟定建模思路。Use when user says "赛题分析", "problem analysis", "分析题目".
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
# 竞赛赛题分析 对以下赛题进行深度分析：**$ARGUMENTS** ## ⚡ 快速模式检测（开头先跑） ```bash FAST_MODE=0 grep -q 'MH_FAST_MODE=1' AGENTS.md 2>/dev/null && FAST_MODE=1 echo "FAST_MODE=$FAST_MODE" ``` **若 `FAST_MODE=1`（速度优先）：** 仍必须产出完整的 PROBLEM_ANALYSIS.md（子问题拆解完整、变量定义、建模思路、图表清单 FIGURE_MANIFEST；题面参数密集时 PROBLEM_FACTS.json 仍要建），但**跳过**：反复推敲措辞的打磨、过度深挖的扩展分析。一次成型、结构齐全即可。**若 `FAST_MODE=0`（默认）：** 后文照常。 ## 常量 - **COMPETITION** / **PROBLEM_ID** / **LANGUAGE** — 从 Additional Parameters 读取 - **TOOLS** — 默认 `python` - **CUSTOM_REQUIREMENTS** — 用户自定义要求 ## 输入 1. 赛题文本（$ARGUMENTS 或 `user_data/` 中的 PDF/Word 文件） 2. 附件数据（`user_data/*.csv` 等） ## ⛔⛔⛔ 完成铁律（最高优先级，违反则本步骤失败） **本步骤必须产出 `PROBLEM_ANALYSIS.md`（≥ 1.5KB，完整的赛题分析）+ FIGURE_MANIFEST 区块 + `CAPABILITY_CHECKLIST.json`（能力清单）**。 ⛔ **能力清单结构校验（结束前必跑，零额度两模式都跑）**： ```bash python _utils/capability_check.py --checklist CAPABILITY_CHECKLIST.json --analysis PROBLEM_ANALYSIS.md CAP=$? # 0=结构合格 1=结构非法/漏拆子问题(必修) 2=无清单 ``` > `CAP=1`（漏拆子问题、machine 项没挂闸、字段非法）必须先修再结束本步骤——能力清单是下游"题型无关验收"的契约，结构不合格 comp-code 的语义校验器就没法逐项验收，题目要的能力会被悄悄降维。`CAP=2`（无清单）：除非纯建模题确实无可拆能力项，否则必须补出清单。 产出结构、存在性和最低完整性由 `finish` 按模板中的 `output_contract` 自动核验；修复返回的具体问题，不复制执行验证脚本。 …
Read the whole file at its exact version.
How to install
mdr add fourteen1416/academic-agent-toolkit/comp-problem-analysis@sha256:3cff80d432566a30The line at the top of this page pins the label git:20260927.efd5131, 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_3uhck3hv2nj22k2e)
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 day.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260927.efd5131 latest | 2026-09-27 | efd5131 | 65,788 B | A | view · diff |
| git:20260923.a358745 | 2026-09-23 | a358745 | 73,236 B | A | view · diff |
| git:20260923.d8950a4 | 2026-09-23 | d8950a4 | 73,824 B | A | view · diff |
| git:20260923.ee897a0 | 2026-09-23 | ee897a0 | 73,554 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 (65788 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_3uhck3hv2nj22k2e GET https://markdownregistry.com/api/v1/resolve?ref=fourteen1416/academic-agent-toolkit/comp-problem-analysis GET https://markdownregistry.com/api/v1/blob/3cff80d432566a30fba1d5f1efe4f56703068f328df0cca5ca1e181dcccaaf04
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.