Pptgen Drawio
xstongxue/best-skills
根据论文或汇报内容生成多页 Draw.io 格式 PPT,支持论文答辩与通用汇报两种模式,自动导出为 .pptx。当用户提到论文答辩 PPT、答辩幻灯片、通用 PPT、汇报 PPT、根据模板生成 PPT、drawio2pptx 时使用。
数学建模国赛(CUMCM/全国大学生数学建模竞赛)分步审核工作流。当用户要求做数学建模国赛题目、完整建模、建模分析、代码求解、结果可视化、生成数学建模论文、写 AI 工具使用声明/AI 使用报告时使用,且需要分步推进、先审核思路与算法再写代码、每个部分写入论文草稿供审核。按'问题重述→数据预处理→逐问建模与求解→模型分析与检验→模型评价与推广→参考文献→附录→问题分析→模型假设→符号说明→摘要'…
$ npx skills add yuanchen-home/cumcm-step-review --skill cumcm-step-review -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install yuanchen-home/cumcm-step-review cumcm-step-review --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
Claude Code skills documentation · loads skills from .claude/skills/
Install the "cumcm-step-review" agent skill from https://github.com/yuanchen-home/cumcm-step-review/tree/main into .claude/skills/cumcm-step-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cumcm-step-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.
$ npx skills add yuanchen-home/cumcm-step-review --skill cumcm-step-review -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install yuanchen-home/cumcm-step-review cumcm-step-review --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "cumcm-step-review" agent skill from https://github.com/yuanchen-home/cumcm-step-review/tree/main into .agents/skills/cumcm-step-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cumcm-step-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 yuanchen-home/cumcm-step-review --skill cumcm-step-review -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install yuanchen-home/cumcm-step-review cumcm-step-review --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "cumcm-step-review" agent skill from https://github.com/yuanchen-home/cumcm-step-review/tree/main into .cursor/skills/cumcm-step-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cumcm-step-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.
$ npx skills add yuanchen-home/cumcm-step-review --skill cumcm-step-review -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install yuanchen-home/cumcm-step-review cumcm-step-review --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "cumcm-step-review" agent skill from https://github.com/yuanchen-home/cumcm-step-review/tree/main into .gemini/skills/cumcm-step-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cumcm-step-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 yuanchen-home/cumcm-step-review cumcm-step-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 yuanchen-home/cumcm-step-review --skill cumcm-step-review -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "cumcm-step-review" agent skill from https://github.com/yuanchen-home/cumcm-step-review/tree/main into .github/skills/cumcm-step-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cumcm-step-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 yuanchen-home/cumcm-step-review --skill cumcm-step-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 yuanchen-home/cumcm-step-review cumcm-step-review --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "cumcm-step-review" agent skill from https://github.com/yuanchen-home/cumcm-step-review/tree/main into .opencode/skills/cumcm-step-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cumcm-step-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.
cumcm-step-review数学建模国赛(CUMCM/全国大学生数学建模竞赛)分步审核工作流。当用户要求做数学建模国赛题目、完整建模、建模分析、代码求解、结果可视化、生成数学建模论文、写 AI 工具使用声明/AI 使用报告时使用,且需要分步推进、先审核思路与算法再写代码、每个部分写入论文草稿供审核。按'问题重述→数据预处理→逐问建模与求解→模型分析与检验→模型评价与推广→参考文献→附录→问题分析→模型假设→符号说明→摘要'…
Cumcm Step Review is an agent skill from yuanchen-home/cumcm-step-review. 数学建模国赛(CUMCM/全国大学生数学建模竞赛)分步审核工作流。当用户要求做数学建模国赛题目、完整建模、建模分析、代码求解、结果可视化、生成数学建模论文、写 AI 工具使用声明/AI 使用报告时使用,且需要分步推进、先审核思路与算法再写代码、每个部分写入论文草稿供审核。按'问题重述→数据预处理→逐问建模与求解→模型分析与检验→模型评价与推广→参考文献→附录→问题分析→模型假设→符号说明→摘要'逐步完成:每部分先给出分析与候选方案,用户审核通过后编写代码,并把该部分写入 Word 论文草稿再次供用户审核;全部定稿后按国赛 AI 使用规范生成 AI 工具使用声明与 AI工具使用详情.pdf;保留建模约束、工具链、算法库与最终验收。
Its SKILL.md is about 2.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 141 other files, including scripts, reference files and assets (for example `CREDITS.md`, `README.md` and `agents/openai.yaml`).
It sits in Documents & Office. It works with draw.io. The licence is MIT.
10 steps, taken from the first numbered list in SKILL.md.
Read from SKILL.md and the folder at commit 07cdd0f. It shows what the files ask for, not the result of running them.
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.
Ships 1 file in scripts/, which the agent can run.
From the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Cumcm Step Review loads about 2.3k tokens when it runs, and up to ~289k if it reads all its reference files. Until then it costs about 85 tokens; SKILL.md has 483 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.
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); the scripts in this folder are not scanned.
The full file from yuanchen-home/cumcm-step-review at commit 07cdd0f, republished under its MIT licence (© yuanchen-home). 483 words, ~2,344 tokens.
.claude/skills/cumcm-step-review/SKILL.md (or your agent's skills folder). This skill also uses 137 other files; get the full folder from GitHub.本 Skill 面向全国大学生数学建模竞赛(CUMCM)的完整建模论文分步审核工作流。它不一次性产出全文,而是按论文章节推进:每部分先给出分析与候选方案,用户审核通过后再写代码,并把该部分写入 Word 论文草稿再次供用户审核,全部冻结后生成最终论文。生成的论文供用户参考,论文结构与格式必须以目标赛题当届官方规则和官方模板为准,不能用往届经验替代官方要求。
SKILL_ROOT:本文件所在目录,只读。脚本、参考、算法资料和模板都从这里读取。PROJECT_ROOT:用户题目和项目所在目录,所有新产物只能写入这里。SKILL_ROOT 内任何文件。PROJECT_ROOT 再处理。SKILL_ROOT、PROJECT_ROOT、当前论文部分、目标赛题与届次、计划读取的入口。未确认的官方规则明确标为待核验。references/阶段流程.md 中对应部分;把该部分写入论文草稿前,必须实际读取 references/优秀论文写法指南.md 的对应章节,需要实证句模/章节频率时再读取 references/优秀论文语料分析报告.md 对应小节,按国赛优秀论文的篇幅、结构、句式与证据组织方式写正文;写、改或评摘要时,必须先实际读取 references/摘要写作/摘要写作方法论.md(93 篇国赛优秀摘要语料提炼的方法论),并按其"起草 → 二次验证 → 定稿"两阶段闭环执行;绘制技术路线图/求解流程图等非数据图时,先读取 references/绘图参考/drawio_flowchart.md 与 tools/drawio/SKILL.md(流程图工具已内置),命中论文级模板(roadmap-5band/framework-3col/stageflow-3col/taskflow-land)时再读取 references/绘图参考/scibox_templates.md 与 tools/drawio/scibox-diagram/SKILL.md(sci-box 流程图模板已内置);使用 PDF、Excel、论文搜索、DOCX 或 LaTeX 时,再实际读取 tools/*/SKILL.md(工具已内置,见 tools/README.md 与渐进式加载表);生成或核对 AI 工具使用声明/AI 使用报告时,必须先实际读取 references/AI使用报告/README.md,并按 references/AI使用报告/规范与红线.md 与 references/AI使用报告/报告结构模板.md 执行,最终运行 references/AI使用报告/scripts/ai_report_audit.py。 知道文件路径不等于已经执行。论文草稿.docx 后,先提交用户审核;用户确认通过后才冻结该部分并进入下一部分。用户要求修改时,修改后重新提交审核。任何含公式的部分,提交审核前必须完成公式格式检查与修复(公式居中、编号右对齐且连续、正文 (n) 引用、无占位符残留),并按 references/阶段流程.md"公式检查(所有部分通用)"与 references/质检清单.md 四·一执行门禁;用户审核时一并核对公式格式,未通过不得冻结。references/质检清单.md 完成作者自检;独立 Subagent 质检门禁默认关闭,用户明确启用时按该文件中"独立质检"章节执行。PROJECT_ROOT/ai_usage_log.md(格式见 references/AI使用报告/报告结构模板.md 第 1 节);最终论文生成后、正式提交前按第 12 部分生成 AI 工具使用声明与 AI使用报告.docx/AI工具使用详情.pdf,核心建模与问题分析表述为参赛队主导并逐项人工审查核验;不得虚构使用记录,也不得用"未使用 AI"掩盖实际使用。PROJECT_ROOT 维护 论文草稿.docx:必须是 Word 文档,直接可读、可批注,供用户审核;不生成 Markdown 版本作为审核载体。论文草稿.docx,再提交用户审核。完整论文.docx 和 完整论文.pdf(LaTeX 编译;用户明确只要一种格式时按用户要求)。按以下顺序推进。每部分统一执行"分析 →(如需要)方案审核 → 代码实现 → 写入论文草稿.docx → 用户审核 → 冻结",详细要求见 references/阶段流程.md:
references/摘要写作/摘要写作方法论.md)references/AI使用报告/README.md;仅当届官方未作要求,或本队全程未用 AI 并按官方"未使用"文案声明时,可跳过)references/降重模块/README.md)8、9、10 在写作与审核顺序上放最后(问题确定后写),摘要(11)在全部部分冻结后撰写;最终成稿排版时,摘要独立成首页,问题分析紧跟问题重述,模型假设与符号说明放在建模正文之前;12(AI 使用报告)在最终论文与摘要定稿后、正式提交前执行。
| 用户意图 | 执行方式 |
|---|---|
| 完整建模 | 按上述 1–11 顺序分步推进,全部审核定稿后生成最终论文;使用过 AI 工具时继续执行 12(AI 使用报告)后再提交 |
| 只做单一或部分章节 | 只执行对应部分及其门禁,不强制全流程 |
| 只写代码、跑结果 | 需要题目和可执行的模型说明;缺失时先补齐必要分析 |
| 只生成或修改论文 | 需要已审核的草稿与真实运行结果;缺失时回退到对应部分 |
| 生成 AI 工具使用声明 / AI 使用报告 | 需要已冻结的完整论文与 ai_usage_log.md;按 references/AI使用报告/README.md 执行,产出 AI使用报告.docx 与 AI工具使用详情.pdf |
| 终稿去 AI 味 / AIGC 降重(可选) | 需要已审核定稿的完整论文;按 references/降重模块/README.md 执行,产出独立的“去 AI 味版”并保留冻结原稿 |
PROJECT_ROOT/论文草稿.docx:分步追加、供用户审核的 Word 文档。PROJECT_ROOT/完整论文.docx:全部部分审核定稿后生成。PROJECT_ROOT/完整论文.pdf 与 完整论文-LaTeX/:由同一冻结正文生成并真实编译。.py / .m)、结果表格、三分类候选图(raw_qN_*、process_qN_*、result_qN_* 每类至少 3 张且覆盖全部子问题)、results/复现清单.json。PROJECT_ROOT/ai_usage_log.md:贯穿执行过程的 AI 使用留痕(提交前必须存在,供 AI 使用报告引用)。PROJECT_ROOT/AI使用报告.docx 与 PROJECT_ROOT/AI工具使用详情.pdf:使用过 AI 工具时生成;PDF 供支撑材料打包,论文附录支撑材料文件列表须列出。references/质检清单.md 完成自检。scripts/paper_check.py,并按 references/质检清单.md 完成编译与 PDF 视觉检查;硬错误未修不得交付。JOURNAL_PALETTES = {nature, science, cell, ieee, general, okabe-ito, wong},各套含主色板与变体,apply_publication_style(journal=..., variant=...) 自动切换;默认 nature(用户定制主色板),需严格色盲友好时用 journal="okabe-ito"(冗余编码 + 灰度预览)。export_figure() 默认只保存一个 300 DPI PNG;svg=True、grayscale_preview=True、extra_formats 按需追加;figure_audit.py 不强制 SVG/PNG 配对,SVG 存在时文本检查降级为提示;MATLAB 导出默认 PNG。(1)(2)… 右对齐且连续;正文用 (n) 引用,公式出现后解释符号。每问审核必检"公式格式 + 模型求解过程"(四步骨架:算法依据→总述→Step 步骤→工具参数与结果衔接),未通过不得进入下一问(见 references/阶段流程.md 第 3 部分与 references/质检清单.md 四·一)。tools/drawio/ 按 references/绘图参考/drawio_flowchart.md 生成;技术路线图、研究内容全景图、分阶段流程图、任务流水线图优先用内置 tools/drawio/scibox-diagram/ 四套论文级模板(见 references/绘图参考/scibox_templates.md),不命中模板才手写 XML。规则同上(图内无标题、图题在图下、图后跟分析、同类型 ≤3、配色/字号/布局一致),导出 PDF 或 300 DPI PNG;.drawio 源文件与 content JSON 保留在 PROJECT_ROOT/figures/。先读本文件,再按当前部分读取 references/阶段流程.md 对应章节;使用工具前读取对应工具的 SKILL.md;禁止一次性加载全部资料。
| 当前任务 | 额外读取 |
|---|---|
| 开始或推进任一部分 | references/README.md → references/阶段流程.md |
| 把某部分写入论文草稿(每个部分) | references/优秀论文写法指南.md 对应章节 →(需要实证句模时)references/优秀论文语料分析报告.md 对应小节 → references/写作与图表规范.md → references/roles/论文手/章节模板.md |
| 写、改或评摘要(摘要部分/评审既有摘要) | references/摘要写作/摘要写作方法论.md →(按需)references/摘要写作/analysis.md(评审视角)→ references/摘要写作/templates.md(句式)→ references/摘要写作/mistakes.md(误区)→ references/摘要写作/checklist.md(自检)→ references/摘要写作/example.md(改写案例)→ references/摘要写作/摘要汇总.md(93 篇语料对照) |
| 选择模型或查算法 | references/模型选型树.md / references/算法索引.md,再读取一个或少数几个 assets/*.md |
| 绘图与配色 | references/绘图参考/chart_knowledge_base.md(100+ 图表速查/图级/避坑)→ references/绘图参考/chart_selection.md(论证意图)→ scripts/plot_style.py、assets/期刊配色方案.md、references/写作与图表规范.md |
| 绘制技术路线图/流程图等非数据图 | references/绘图参考/drawio_flowchart.md(国赛规则与落位)→ 命中模板时 references/绘图参考/scibox_templates.md(四套模板选择)→ tools/drawio/scibox-diagram/SKILL.md + 对应 references/<template>.md(模板渲染)→ tools/drawio/SKILL.md(完整工作流)→ 按图类型 tools/drawio/references/diagram-types.md → 手写 XML 前 tools/drawio/references/xml-authoring.md |
| 热力图进阶 / 相关分析进阶图(用户提到"热力图进阶"时优先) | references/绘图参考/heatmap_advanced.md(Mantel 连线图 + 皮尔逊整合矩阵,优先)→ references/绘图参考/chart_knowledge_base.md(热力图/矩阵散点图)→ references/绘图参考/plot_recipes.md §8 |
| 图表自检 | scripts/figure_audit.py、references/绘图参考/visual_review.md |
| 科研绘图模板 | assets/figure-templates/README.md |
| 搜索论文 | tools/paper_search/SKILL.md |
| 读取题目 PDF | tools/pdf/SKILL.md |
| 处理 Excel | tools/xlsx/SKILL.md |
| 写入或生成 Word 草稿/论文 | tools/docx/SKILL.md |
| 生成 LaTeX 论文 | tools/latex/SKILL.md |
| 迁移到其他工具/机器(复制包后效果变差时) | scripts/check_env.py(环境诊断)→ 迁移与依赖说明.md(外部依赖与工具差异)→ requirements.txt(安装清单) |
| 写 AI 使用声明 / 生成 AI 使用报告(提交前) | references/AI使用报告/README.md(触发与流程)→ references/AI使用报告/规范与红线.md(口径与红线)→ references/AI使用报告/报告结构模板.md(结构与留痕)→ references/AI使用报告/一致性自检清单.md → tools/docx/SKILL.md;门禁 references/AI使用报告/scripts/ai_report_audit.py |
| 终稿去 AI 味 / AIGC 降重(可选) | references/降重模块/README.md(触发与协议)→ references/降重模块/红线与自检.md →(已安装时)aigc-reduce 方法论;完成后复跑全文门禁 |
| 最终验收 | scripts/paper_check.py、references/质检清单.md |
论文草稿.docx 并经用户审核确认;最终论文由同一冻结正文生成。references/摘要写作/摘要写作方法论.md 两阶段闭环撰写并经用户审核:逐题段与子问题一一对应、每问有量化结果、无公式与表格、关键词 4–6 个且与正文一致、摘要内每个数值与正文结果一致。ai_usage_log.md 完整覆盖各冻结环节;AI使用报告.docx 与 AI工具使用详情.pdf 已生成并经用户审核;ai_report_audit.py 退出码为 0;报告、声明、附录与支撑材料四者一致,核心建模与问题分析表述为参赛队主导并逐项人工审查核验。PROJECT_ROOT;SKILL_ROOT 未被改写。© yuanchen-home, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 137 other files (scripts, references, assets) in the repository root of yuanchen-home/cumcm-step-review.
Open the folder on GitHubat commit 07cdd0f
Cumcm Step 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 |
|---|---|---|---|---|---|---|
| Cumcm Step Review this skillyuanchen-home/cumcm-step-review | 319 | — | ~2.3k | Automated safety check: Pass | MIT | |
| Pptgen Drawioxstongxue/best-skills | 3k | — | ~2.1k | Automated safety check: Pass | Apache-2.0 | |
| Thesis Figure Skill0xE1337/thesis-figure-skill | 144 | — | ~9.1k | Automated safety check: Pass | MIT | |
| Systems DiagrammingWuXinbo-bo/Math-model-skills | 111 | — | ~6.3k | Automated safety check: Pass | MIT | |
| Obsidian Skills Integratedanbeime/skill | 7.8k | — | ~1.4k | Automated safety check: Pass | MIT | |
| Legal Visualizationcat-xierluo/legal-skills | 720 | — | ~2k | Automated safety check: Warn | CC-BY-NC-4.0 |
xstongxue/best-skills
根据论文或汇报内容生成多页 Draw.io 格式 PPT,支持论文答辩与通用汇报两种模式,自动导出为 .pptx。当用户提到论文答辩 PPT、答辩幻灯片、通用 PPT、汇报 PPT、根据模板生成 PPT、drawio2pptx 时使用。
0xE1337/thesis-figure-skill
生成学术论文配图:LaTeX/TikZ 代码(结构化图表,直接嵌入论文)或 draw.io XML (技术路线图、汇报配图)。自动按论文领域风格设计,编译验证后交付。
WuXinbo-bo/Math-model-skills
Meta-model-agent 构建技术路线、方法关系、系统架构与流程示意资产。适用于系统逻辑制图. An agent skill from WuXinbo-bo/Math-model-skills.
anbeime/skill
内容创作者与技术写作员在让AI撰写Obsidian笔记时,使用此官方技能可精准处理双链、Callout及Bases数据库语法,一键生成格式零破坏的Canvas画布与专业笔记,彻底解决AI破坏专属格式的痛点。
cat-xierluo/legal-skills
Legal Visualization。面向法律业务场景的法律图解与图表生成技能;当用户要求把案件材料、合同材料、合规事项、交易安排、证据链、诉讼流程、时间轴、法律关系、客户汇报、法律服务方案或律师团队工作整理成关系图、流程图、时间轴、证据链、风险图、路线图、PNG/SVG/PDF/.drawio…
ZyhSechub/chinese-thesis-workbench-skill
Standardizes, drafts, revises, checks and packages Chinese undergraduate theses from school templates, source code and literature, with evidence traceability and DOCX output.
yuanchen-home/cumcm-step-review
A skill your agent uses when the user requests diagrams, flowcharts, architecture diagrams, ER diagrams, UML / sequence / class diagrams, SysML / MBSE diagrams (block definition, internal block…
Works with
Categories
数学建模国赛(CUMCM/全国大学生数学建模竞赛)分步审核工作流。当用户要求做数学建模国赛题目、完整建模、建模分析、代码求解、结果可视化、生成数学建模论文、写 AI 工具使用声明/AI 使用报告时使用,且需要分步推进、先审核思路与算法再写代码、每个部分写入论文草稿供审核。按'问题重述→数据预处理→逐问建模与求解→模型分析与检验→模型评价与推广→参考文献→附录→问题分析→模型假设→符号说明→摘要'…. Cumcm Step Review is an agent skill from yuanchen-home/cumcm-step-review.
Cumcm Step Review fits situations like: documents & Office work in your project.
Run `npx skills add yuanchen-home/cumcm-step-review --skill cumcm-step-review -a claude-code`. Or copy the skill folder (the yuanchen-home/cumcm-step-review repository) into .claude/skills/cumcm-step-review in your project. Claude Code loads it when a task matches its description.
Run `npx skills add yuanchen-home/cumcm-step-review --skill cumcm-step-review -a codex`. Or copy the skill folder (the yuanchen-home/cumcm-step-review repository) into .agents/skills/cumcm-step-review in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add yuanchen-home/cumcm-step-review --skill cumcm-step-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/cumcm-step-review, .gemini/skills/cumcm-step-review, .github/skills/cumcm-step-review and .opencode/skills/cumcm-step-review in your project.
SKILL.md names no scripts, command-line tools or credentials: Cumcm Step Review is instructions for the agent only.
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.
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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
Cumcm Step Review is published under the MIT licence (from the LICENSE file in the skill folder). It allows redistribution, so the full SKILL.md is shown on this page.
About 2.3k tokens (SKILL.md is roughly 9.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 287k tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Cumcm Step Review: Pptgen Drawio (xstongxue/best-skills, 3k stars), Thesis Figure Skill (0xE1337/thesis-figure-skill, 144 stars), Systems Diagramming (WuXinbo-bo/Math-model-skills, 111 stars) and Obsidian Skills Integrated (anbeime/skill, 7.8k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
yuanchen-home (a GitHub user) maintains it in yuanchen-home/cumcm-step-review, which has 319 GitHub stars. The repository holds 2 skills in this directory. The repository was last updated on September 4, 2026.
Source: yuanchen-home/cumcm-step-review on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.