comp-review SKILL.md skillA
comp-review 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-review@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-review/SKILL.md- Versions recorded
- 5
- Latest version
- git:20261023.cb0b591, committed Oct 23, 2026
- First version recorded
- Sep 23, 2026
- Size
- 10,673 bytes
- Repository stars
- 12
- License
- a license file GitHub does not identify
数学建模竞赛逻辑对抗复核：编程实现后、论文撰写前，用独立视角挑方向反/重复计量/外推过硬/漏变量/跨问矛盾等硬错。触发词：逻辑复核、对抗审查、模型审查。Use between comp-code and comp-paper。.
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·逻辑对抗复核（独立视角，专挑自查盲区） **为什么需要这一步**：建模/编程用的是同一个"心智模型"，如果它在建模阶段就把某个方向想反了（如把上界当下界）、或把某项算了两次，**自查时用的还是那个反的脑子，永远看不见**。这一步换一个独立视角，只干一件事——挑七类"数值合法但逻辑错、或得分点缺证据"的硬伤。 ## 范围与独立性 本步由引擎分派，不能因为快速模式写占位报告或宣称通过。确定性检查不能替代独立语义审查。没有独立上下文时如实阻塞或报告降级，不能伪造会话。 按当前步骤的 `review_scope` 选择业务输入：竞赛审模型与代码；deep_research审来源、综合论证与边界；grant_proposal审科学问题、方法、可行性、预算依据与申请书；paper_submission审稿件、逐条回复和投稿合同；scientific_plotting审图表的数据语义。非竞赛范围不要求不存在的竞赛题面/建模文件。 ## 输入（只读摘要，禁整读大 JSON） - `PROBLEM_ANALYSIS.md`（题面/逐句表/硬约束）、`DATA_FACTS.json`（数据事实台账） - `MODELING_REPORT.md`（假设/`LOGIC_CONTRACT_MACHINE`/`CROSS_PROBLEM_LEDGER`） - `RESULTS.md` + `AUDIT_REPORT.md`（前面各闸的结论） - `figures/*_results.json` 用 `_utils` 下的 summarize 或 `Grep`/`Read` 局部看，**⛔ 禁 `cat` 整包大 JSON**（吃光 context） ## Step 1: 先看确定性闸的既有结论（不重复劳动） ```bash # logic_audit / cross_problem_check 已在 comp-code 阶段跑过，先复用它们的裁定作锚点 [ -f AUDIT_REPORT.md ] && grep -nE "外推|特征完整性|重复计量|跨问|矛盾|❌|⚠" AUDIT_REPORT.md | head -30 ``` ## Step 2: 逐条对撞七类缺口（核心，用证据说话） 对每一类，找**具体代码行/具体数值**当证据，不泛泛而谈： 1. **方向/界反没反**：核对 `LOGIC_CONTRACT_MACHINE.bounds` 声明的上/下界与代码实现是否一致。凡有删失/封顶/反解，代入观测值验证不等号方向。（这是确定性闸抓不到、最需要独立视角的一类） 2. **重复计量**：任何"总量=A+B"，查 A 的拟合/标定是否已吸收 B（如截距用含某分项的总量拟合、又显式加该分项）。 …
Read the whole file at its exact version.
How to install
mdr add fourteen1416/academic-agent-toolkit/comp-review@sha256:13e8fa3d4f893185The 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_u3ayyywxhhbkczmx)
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 7 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261023.cb0b591 latest | 2026-10-23 | cb0b591 | 10,673 B | A | view · diff |
| git:20260927.a059f3a | 2026-09-27 | a059f3a | 7,978 B | A | view · diff |
| git:20260927.efd5131 | 2026-09-27 | efd5131 | 8,045 B | A | view · diff |
| git:20260923.a358745 | 2026-09-23 | a358745 | 9,081 B | A | view · diff |
| git:20260923.d8950a4 | 2026-09-23 | d8950a4 | 9,113 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 (10673 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_u3ayyywxhhbkczmx GET https://markdownregistry.com/api/v1/resolve?ref=fourteen1416/academic-agent-toolkit/comp-review GET https://markdownregistry.com/api/v1/blob/13e8fa3d4f893185707abcbf39944f8f23bd63370c1802366227b001999fa52d
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.