Academic Paper Writing Pipeline
Imbad0202/academic-research-skills
Runs a 12-agent pipeline that plans, drafts, cites, reviews and formats academic papers, with modes for revision, rebuttals, abstracts and citation checks.
Runs several independent review rounds on a finished math-modeling competition paper and rewrites it until it clears a fixed score and defect bar.
SKILL.md written in Chinese; this summary is our English description.
Install Championship Mode Paper Review
$ npx skills add WuXinbo-bo/Math-model-skills --skill championship-review -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install WuXinbo-bo/Math-model-skills championship-review --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/WuXinbo-bo/Math-model-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/references/stage_protocols/championship-review .claude/skills/championship-review && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "championship-review" agent skill from https://github.com/WuXinbo-bo/Math-model-skills/tree/main/references/stage_protocols/championship-review into .claude/skills/championship-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "championship-review", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/WuXinbo-bo/Math-model-skills/tree/main/references/stage_protocols/championship-reviewType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add WuXinbo-bo/Math-model-skills --skill championship-review -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install WuXinbo-bo/Math-model-skills championship-review --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/WuXinbo-bo/Math-model-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/references/stage_protocols/championship-review .agents/skills/championship-review && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "championship-review" agent skill from https://github.com/WuXinbo-bo/Math-model-skills/tree/main/references/stage_protocols/championship-review into .agents/skills/championship-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "championship-review", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add WuXinbo-bo/Math-model-skills --skill championship-review -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install WuXinbo-bo/Math-model-skills championship-review --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/WuXinbo-bo/Math-model-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/references/stage_protocols/championship-review .cursor/skills/championship-review && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "championship-review" agent skill from https://github.com/WuXinbo-bo/Math-model-skills/tree/main/references/stage_protocols/championship-review into .cursor/skills/championship-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "championship-review", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/WuXinbo-bo/Math-model-skills.git --path references/stage_protocols/championship-review--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add WuXinbo-bo/Math-model-skills --skill championship-review -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install WuXinbo-bo/Math-model-skills championship-review --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/WuXinbo-bo/Math-model-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/references/stage_protocols/championship-review .gemini/skills/championship-review && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "championship-review" agent skill from https://github.com/WuXinbo-bo/Math-model-skills/tree/main/references/stage_protocols/championship-review into .gemini/skills/championship-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "championship-review", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install WuXinbo-bo/Math-model-skills championship-reviewInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add WuXinbo-bo/Math-model-skills --skill championship-review -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/WuXinbo-bo/Math-model-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/references/stage_protocols/championship-review .github/skills/championship-review && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "championship-review" agent skill from https://github.com/WuXinbo-bo/Math-model-skills/tree/main/references/stage_protocols/championship-review into .github/skills/championship-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "championship-review", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add WuXinbo-bo/Math-model-skills --skill championship-review -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install WuXinbo-bo/Math-model-skills championship-review --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/WuXinbo-bo/Math-model-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/references/stage_protocols/championship-review .opencode/skills/championship-review && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "championship-review" agent skill from https://github.com/WuXinbo-bo/Math-model-skills/tree/main/references/stage_protocols/championship-review into .opencode/skills/championship-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "championship-review", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
championship-review- GitHub stars
- 111
- Token cost
- ~437 tokens
- SKILL.md length
- 57 words
- Files
- 1
- Skills in repo
- 9
- Repo updated
- First seen
- Licence
- MIT
At a glance
Runs several independent review rounds on a finished math-modeling competition paper and rewrites it until it clears a fixed score and defect bar.
- Works in 7 steps: 建立全新的独立审稿角色，不向其给出上一轮结论或预设答案。 → 审稿角色查阅 论文/论文正文.tex、模型报告、结果文件、图形与表格引用和本轮… → 写入 审稿报告.md，报告务必涵盖综合分、分维度得分及 P0/P1/P2 列表。 → …
- Running a final quality-control pass on a math-modeling competition paper
- SKILL.md covers 稳定执行契约, 启动, 每轮实施 and 根本缺陷处理, plus 1 more section
- Calls python
What it does
Active only once quality_mode is set to championship and the competition manuscript has already been assembled, this protocol starts each round with a fresh, independent reviewer role that is given no memory of a prior round's conclusions. That role reads the manuscript, model report, result files, figures and the current round's review task file before writing anything.
Each round follows the same chain: a review report scoring the paper overall and by dimension with P0, P1 and P2 issues, a revision plan translating those issues into concrete fixes with evidence and an acceptance check, a full rewrite of the manuscript from that plan, and a fresh-perspective recheck of every change, with the round then logged with its score and remaining issue counts. The first three rounds cycle through mathematical, evidence and judge perspectives, and finding a fundamental error in the model, code or results stops the polishing and triggers a rollback instead of softer wording.
When your agent uses it
- Running a final quality-control pass on a math-modeling competition paper
- Driving multiple independent review rounds before a submission deadline
- Deciding whether a competition paper has cleared the bar to close review
Example prompts
- “Start round one of the championship review with the mathematical perspective.”
- “Record this round's score and move on to the evidence perspective.”
- “Finalize the championship revision now that three rounds have passed.”
Requirements
- A workspace with the manuscript file and upstream evidence already assembled
- Python to run the review and stage-executor scripts
Workflow steps
7 steps, taken from the first numbered list in SKILL.md.
- 建立全新的独立审稿角色，不向其给出上一轮结论或预设答案。
- 审稿角色查阅 论文/论文正文.tex、模型报告、结果文件、图形与表格引用和本轮 审稿任务.md。
- 写入 审稿报告.md，报告务必涵盖综合分、分维度得分及 P0/P1/P2 列表。
- 主控角色将问题转换为 修订计划.md，清晰标明调整位置、证据来源和验收方式。
- 写作角色基于计划直接产出完整 修订论文.tex。
- 采用新的复核视角逐项核验调整，并写入 修订复核.md。
- 登记轮次
What it can do on your machine
Read from SKILL.md and the folder at commit ee8a616. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
python
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Championship Mode Paper Review loads about 437 tokens when it runs. Until then it costs about 31 tokens; SKILL.md has 57 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from WuXinbo-bo/Math-model-skills at commit ee8a616, republished under its MIT licence (© WuXinbo-bo). 57 words, ~437 tokens.
Download SKILL.mdSave it as
.claude/skills/championship-review/SKILL.md (or your agent's skills folder).- name
- championship-review
- description
- Meta-model-agent 冠军模式模拟质量审稿协议。仅在 quality_mode=championship 且竞赛文稿集成完成后使用，通过多轮独立审稿、修订计划、全文改写和逐项复核产出冠军版论文。
冠军模式多轮质量审稿
稳定执行契约
- 执行目标：在冠军模式下，以彼此独立的多轮视角审查并修订完整论文。
- 调用参数：当前工作流输入。
- 权威输入：论文/论文正文.tex、全部上游证据、审稿方法与本轮审稿任务。
- 允许交付：审查/冠军模式/第NN轮/下的审稿、计划、修订与复核文件，以及最终冠军修订稿。
- 禁止写入：不得越权修改已冻结的上游事实、用户原始文件或本协议未授权的目录。
- 可用工具边界：按宿主工具权限执行。
- 最小交付：独立审稿报告、可执行修订计划、完整修订论文、逐项复核和最终总报告。
- 恢复入口：优先读取当前工作、状态记录和已有产物，从最近一次通过门禁的位置继续。
- 失败回退：发现模型、程序或结果根本缺陷时立即回退对应工作流，禁止用措辞淡化上游错误。
- 收口顺序：先核对输入，再完成产物，再运行本环节门禁，最后登记状态；门禁未通过不得宣告完成。
查阅 references/championship-review-method.md，严禁改变问题、模型、计算、证据和论文之间的依赖关系，仅在 MANUSCRIPT 与 ASSURANCE 之间实施本协议。
启动
python scripts/championship_review.py init --workspace .
python scripts/championship_review.py start-round --workspace . --round 1 --perspective mathematical每轮实施
- 建立全新的独立审稿角色，不向其给出上一轮结论或预设答案。
- 审稿角色查阅
论文/论文正文.tex、模型报告、结果文件、图形与表格引用和本轮审稿任务.md。 - 写入
审稿报告.md，报告务必涵盖综合分、分维度得分及 P0/P1/P2 列表。 - 主控角色将问题转换为
修订计划.md，清晰标明调整位置、证据来源和验收方式。 - 写作角色基于计划直接产出完整
修订论文.tex。 - 采用新的复核视角逐项核验调整，并写入
修订复核.md。 - 登记轮次：
python scripts/championship_review.py record-round --workspace . --round 1 --score 86 --p0 0 --p1 2 --paper 审查/冠军模式/第01轮/修订论文.tex --review 审查/冠军模式/第01轮/审稿报告.md --plan 审查/冠军模式/第01轮/修订计划.md --verification 审查/冠军模式/第01轮/修订复核.md后续轮次务必以上一轮 修订论文.tex 为审稿对象，但审稿角色保持独立。前三轮视角依次为 mathematical、evidence、judge。
根本缺陷处理
审稿若发现模型、程序或关键结果错误，停止文字润色，按知识库的回退准则调用 stage_executor.py rework。严禁通过弱化措辞掩盖上游错误。
终版闭合
完成不少于三轮且最后一轮满足 score>=85、P0=0、P1<=2 后运行：
python scripts/championship_review.py finalize --workspace .该命令产出冠军修订稿和总审稿报告，备份并更新 论文/论文正文.tex。随后才准许启动 ASSURANCE。
© WuXinbo-bo, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in references/stage_protocols/championship-review of WuXinbo-bo/Math-model-skills.
Open the folder on GitHubat commit ee8a616
Compare with similar skills
Championship Mode Paper Review next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Championship Mode Paper Review this skillWuXinbo-bo/Math-model-skills | 111 | — | ~437 | Automated safety check: Pass | MIT | |
| Academic Paper Writing PipelineImbad0202/academic-research-skills | 51k | — | ~16k | Automated safety check: Pass | Custom licence | |
| Academic Paper ReviewerImbad0202/academic-research-skills | 51k | — | ~11k | Automated safety check: Pass | Custom licence | |
| Academic Research PipelineImbad0202/academic-research-skills | 51k | — | ~15k | Automated safety check: Pass | Custom licence | |
| Benchmark Paper TemplateHKUSTDial/Supervisor-Skills | 8.8k | — | ~2.8k | Automated safety check: Pass | CC-BY-4.0 | |
| Academic Research Suite for CodexImbad0202/academic-research-skills-codex | 12k | — | ~12k | Automated safety check: Pass | Custom licence |
Similar skills
Academic Paper Reviewer
Imbad0202/academic-research-skills
Simulates a journal peer review of a manuscript with a five-seat reviewer panel, an editorial synthesizer and several review modes.
Academic Research Pipeline
Imbad0202/academic-research-skills
Orchestrates a ten-stage academic workflow from research to finished manuscript, including integrity checks, two rounds of peer review and revision.
Benchmark Paper Template
HKUSTDial/Supervisor-Skills
Structures benchmark and evaluation papers around five pillars, with a completeness audit, an Introduction logic chain, a section skeleton and a pre-submission checklist.
Academic Research Suite for Codex
Imbad0202/academic-research-skills-codex
A router skill that sends academic work such as literature reviews, drafting, citation checks, peer review and revision to the right workflow in the ARS suite.
Academic Writing Assistant
donghuixin/AI-Vibe-Writing-Skills
Drafts and revises academic prose in the author's voice, repairs sentence flow, traces systems-paper claims to evidence and prepares reviewer responses.
More from WuXinbo-bo/Math-model-skills
All 9 skills in this repoMeta-model-agent Math Modeling Pipeline
WuXinbo-bo/Math-model-skills
Runs a staged pipeline for mathematical modeling research and contest papers, from problem analysis and computation to paper writing, review rounds and submission checks.
Modeling Competition Computation Stage
WuXinbo-bo/Math-model-skills
Pipeline stage that turns a mathematical modeling report into runnable programs per sub-question, frozen numerical results and reviewable evidence files.
Math Model Formulation Stage
WuXinbo-bo/Math-model-skills
Stage protocol for a math-modeling pipeline that turns a problem analysis into a unified mathematical mechanism, formulas, a solution route and a validation plan.
Math Modeling Problem Analysis
WuXinbo-bo/Math-model-skills
Breaks a math modeling competition problem statement into sub-problems, variables, constraints and evidence needs, and writes the result to a problem analysis file.
Delivery Assurance
WuXinbo-bo/Math-model-skills
Meta-model-agent 完成编译、版式、匿名、页数、引用与提交前合规验收。适用于提交质量验收. An agent skill from WuXinbo-bo/Math-model-skills.
Evidence Visualization
WuXinbo-bo/Math-model-skills
Meta-model-agent 将计算成果转换为可发表的数据图形、表格和排版引用。适用于证据图谱构建. An agent skill from WuXinbo-bo/Math-model-skills.
Related
Categories
Questions about Championship Mode Paper Review
What does Championship Mode Paper Review do?
Runs several independent review rounds on a finished math-modeling competition paper and rewrites it until it clears a fixed score and defect bar. Active only once quality_mode is set to championship and the competition manuscript has already been assembled, this protocol starts each round with a fresh, independent reviewer role that is given no memory of a prior round's conclusions. That role reads the manuscript, model report, result files, figures and the current round's review task file before writing anything.
When should I use Championship Mode Paper Review?
Championship Mode Paper Review fits situations like: running a final quality-control pass on a math-modeling competition paper; driving multiple independent review rounds before a submission deadline; deciding whether a competition paper has cleared the bar to close review.
How do I install Championship Mode Paper Review in Claude Code?
Run `npx skills add WuXinbo-bo/Math-model-skills --skill championship-review -a claude-code`. Or copy the skill folder (references/stage_protocols/championship-review in WuXinbo-bo/Math-model-skills) into .claude/skills/championship-review in your project. Claude Code loads it when a task matches its description.
How do I install Championship Mode Paper Review in Codex?
Run `npx skills add WuXinbo-bo/Math-model-skills --skill championship-review -a codex`. Or copy the skill folder (references/stage_protocols/championship-review in WuXinbo-bo/Math-model-skills) into .agents/skills/championship-review in your project. Codex loads it when a task matches its description.
Can I use Championship Mode Paper Review in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add WuXinbo-bo/Math-model-skills --skill championship-review -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/championship-review, .gemini/skills/championship-review, .github/skills/championship-review and .opencode/skills/championship-review in your project.
What does Championship Mode Paper Review need to run?
Going by SKILL.md and its folder, Championship Mode Paper Review needs the command-line tools its instructions call (python). Our summary lists: A workspace with the manuscript file and upstream evidence already assembled; Python to run the review and stage-executor scripts.
Does Championship Mode Paper Review access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Championship Mode Paper Review safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Championship Mode Paper Review use?
Championship Mode Paper Review is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Championship Mode Paper Review use?
About 437 tokens (SKILL.md is roughly 1.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Championship Mode Paper Review?
Skills that share tags, products or a category with Championship Mode Paper Review: Academic Paper Writing Pipeline (Imbad0202/academic-research-skills, 51k stars), Academic Paper Reviewer (Imbad0202/academic-research-skills, 51k stars), Academic Research Pipeline (Imbad0202/academic-research-skills, 51k stars) and Benchmark Paper Template (HKUSTDial/Supervisor-Skills, 8.8k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Championship Mode Paper Review?
WuXinbo-bo (a GitHub user) maintains it in WuXinbo-bo/Math-model-skills, which has 111 GitHub stars. The repository holds 9 skills in this directory. The repository was last updated on September 21, 2026.
Source: WuXinbo-bo/Math-model-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.