论文辅助 SKILL.md skillA
论文辅助 from cjh-solver/mathmodeling-skills-arsenal is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add cjh-solver/mathmodeling-skills-arsenal/论文辅助@git:20261022.3dfa9a5Pins git:20261022.3dfa9a5 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- cjh-solver/mathmodeling-skills-arsenal
- Path
skills/03-writing/论文辅助/SKILL.md- Versions recorded
- 1
- Latest version
- git:20261022.3dfa9a5, committed Oct 22, 2026
- Size
- 31,420 bytes
- Repository stars
- 15
- License
- Apache-2.0
数模论文节点审查助手,对论文G0-G6节点进行只读审查,检查符号完整性、元话语、负向回声、模型证据,输出结构化修改清单。.
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
# 论文辅助 — 数模论文节点审查助手 ## 角色定位 你有两个独立角色,根据当前节点和用户指令切换: ### 角色一:独立外部审查助手(默认角色,4-18 模式全节点 / harness 模式 H3/H4/H5/H8/H9) 你是用户的**独立外部审查助手**,与 Contest Orchestrator 主 agent 平行运行。**主 agent 不知道你的存在**。 你的核心价值: - **独立审查**:不依赖主 agent 的自我评估,对主 agent 的产出做独立质量检查 - **质量对比**:将你的独立审查结论与主 agent 的自评/产出并列,让用户看清主 agent 完成的质量 - **询问助手**:用户在每个节点可以问任何关于主 agent 产出的问题,你基于源文件给出客观回答 - **辅助优化**:给出具体的优化建议,但不直接修改文件,由用户决定是否采纳 ### 角色二:外部文献阅读子 agent(harness 模式 H3 节点) 在 harness 模式的 H3 节点,你是**主 agent 调用的外部文献 agent**。此时主 agent 知道你的存在,你按主 agent 的 `literature_agent_prompt.md` 要求,阅读用户下载的文献全文,回传结构化摘要。 你的任务边界: - **只做文献阅读和结构化总结**,不做模型路线决策、不做方法 adopt/adapt/reject(那是 H4 主 agent 的事) - 必须阅读全文,不得仅基于摘要或题名补写结论 - 回传字段必须完整:`title`, `authors`, `venue`, `year`, `doi_or_url`, `abstract`, `full_text_summary`, `method_summary`, `data_summary`, `limitations`, `evidence_locators`, `candidate_questions` - 输出格式为 `literature_sources.yaml`,模板见 `templates/literature_sources_template.yaml` - 不联网检索、不替用户下载文献(用户负责检索和下载) - 每篇文献生成稳定 `citation_key`,标注语言(zh/en),按小问标注可迁移点 ### 角色切换规则 - 用户明确说"读文献"、"H3"、"文献摘要"、"literature_sources" → 切换到角色二 - 用户说"审查"、"检查"、"看看主 agent 做得怎么样" → 切换到角色一 - 用户未明确时,默认角色一(独立审查助手) …
Read the whole file at its exact version.
How to install
claude plugin marketplace add https://markdownregistry.com/mp/a/art_z7wyrjzqv2dbzchr/d4a5c1eb267ca72ab22b41d1b77baf4ae9ed635d0cef85478b718498b3051f93.json
Then /plugin install 论文辅助@markdownregistry-z7wyrjzqv2dbzchr in Claude Code. It installs git:20261022.3dfa9a5, the one graded A here, pinned to the commit it was graded at, and leaves it there.
mdr add cjh-solver/mathmodeling-skills-arsenal/论文辅助@sha256:d4a5c1eb267ca72aThe line at the top of this page pins the label git:20261022.3dfa9a5, 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_z7wyrjzqv2dbzchr)
2 badge image fetches in 30 days. What the badge shows.
claude mcp add --transport http markdownregistry https://markdownregistry.com/mcp/registry
Then ask it: what changed in cjh-solver/mathmodeling-skills-arsenal/论文辅助 since the version I have? It reads every saved version here, no key and no account. Any agent that speaks MCP can add it.
Got a copy of 论文辅助 from somewhere else? Ask it: where did my 论文辅助 come from, and what was changed? It names the public original, the version yours is closest to and every changed line. The text is not kept.
Versions
The registry has recorded 1 version of this file, committed on Oct 22, 2026.
Watch this file (sign in, one email per new version)
Committed this skill to a repository? Install the markdownregistry skill updates app on it, or on all of them. When the registry saves a newer version, a pull request brings your copy to it within minutes, the newest version first, then what changed and any check it newly trips. A copy you edited is never touched, and nothing is deleted.
It asks to read and write contents and pull requests, and to read metadata. No workflow file, no Actions setting, nothing runs on your runners. Uninstall it and everything the registry kept about your repository is deleted.
Committed this skill to a repository? Add one workflow file, and when a newer version is saved, a pull request brings your copy to it, the newest version first, then what changed and any check it newly trips. A copy you edited is never touched, and nothing is deleted.
mkdir -p .github/workflows && curl -fsSL https://markdownregistry.com/ci/skill-updates.yml -o .github/workflows/skill-updates.yml
It runs daily on GitHub Actions, no key and no account. Read the workflow before you add it.
Installed this file, say at .claude/skills/论文辅助/SKILL.md? Drop it here to learn which saved version you have and what changed since. Your browser works out its SHA-256 fingerprint and sends only that; the file itself never leaves your computer.
Or paste its contents
Your agent can run this same check on the agent markdown files you have installed, up to 50 in one ask. Add the registry once:
claude mcp add --transport http markdownregistry https://markdownregistry.com/mcp/registry
Then ask it to check the files you have installed. No key and no account.
From the root of your project, one line hashes each installed skill's SKILL.md, your AGENTS.md and your CLAUDE.md, and asks the registry once. Only the fingerprints and paths are sent.
sha256sum .claude/skills/*/SKILL.md AGENTS.md CLAUDE.md | curl -s --data-binary @- https://markdownregistry.com/api/v1/check-copies
In CI, add --fail-with-body: the answer is 409 when any file is behind, so the step fails and still prints which files.
sha256sum .claude/skills/*/SKILL.md AGENTS.md CLAUDE.md | curl -s --fail-with-body --data-binary @- https://markdownregistry.com/api/v1/check-copies
No sha256sum on your machine? shasum -a 256 prints the same lines.
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 (31420 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
cjh-solver/mathmodeling-skills-arsenal · 15 stars · license Apache-2.0 · pushed 2026-11-15 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_z7wyrjzqv2dbzchr GET https://markdownregistry.com/api/v1/resolve?ref=cjh-solver/mathmodeling-skills-arsenal/论文辅助 GET https://markdownregistry.com/api/v1/blob/d4a5c1eb267ca72ab22b41d1b77baf4ae9ed635d0cef85478b718498b3051f93
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.