Skip to content

Lucasuiii/modeling-workbench / .agents/skills/cumcm-workflow

cumcm-workflow

Verified

Build or resume mathematical-modeling competition work, including CUMCM, MCM/ICM, graduate and regional contests, data challenges, and open-topic statistical modeling. Guide problem framing, modeling, computation, validation, Chinese or English LaTeX writing, and reviewed PDF/source delivery using current official requirements. Not for ordinary paper polishing.

FileKindSize
SKILL.mdskill md9.0 KB
agents/openai.yamlconfig427 B
assets/latex-template/generic-ctex/macros.texother859 B
assets/latex-template/generic-ctex/main.tex.tmplother2.5 KB
assets/latex-template/generic-ctex/metadata.tex.tmplother272 B
assets/latex-template/generic-ctex/planned-section.tex.tmplother1.0 KB
assets/latex-template/generic-ctex/references.bibother155 B
assets/latex-template/generic-ctex/sections/00_abstract.texother935 B
assets/latex-template/generic-ctex/sections/98_references.texother221 B
assets/latex-template/generic-ctex/sections/99_appendix.texother264 B
assets/latex-template/generic-ctex/template.jsonconfig304 B
assets/latex-template/generic-en/macros.texother868 B
assets/latex-template/generic-en/main.tex.tmplother2.2 KB
assets/latex-template/generic-en/metadata.tex.tmplother278 B
assets/latex-template/generic-en/planned-section.tex.tmplother1013 B
assets/latex-template/generic-en/references.bibother155 B
assets/latex-template/generic-en/sections/00_abstract.texother454 B
assets/latex-template/generic-en/sections/98_references.texother201 B
assets/latex-template/generic-en/sections/99_appendix.texother240 B
assets/latex-template/generic-en/template.jsonconfig249 B
assets/latex-template/huawei-ctex/main.tex.tmplother3.3 KB
assets/latex-template/huawei-ctex/template.jsonconfig276 B
assets/plot-style/cumcm.mplstyleother953 B
references/01-intake.mdmarkdown3.9 KB
references/02-problem-analysis.mdmarkdown2.8 KB
references/03-model-design.mdmarkdown7.6 KB
references/04-computation.mdmarkdown13.4 KB
references/05-validation.mdmarkdown5.9 KB
references/06-paper-writing.mdmarkdown14.3 KB
references/07-compile-delivery.mdmarkdown6.1 KB
references/artifact-contracts.mdmarkdown3.1 KB
references/competition-adaptation.mdmarkdown6.8 KB
references/competition-writing.mdmarkdown5.6 KB
references/diagnostics.mdmarkdown4.5 KB
references/evidence-rules.mdmarkdown1.6 KB
references/handoffs.mdmarkdown3.5 KB
references/huawei-delivery.mdmarkdown10.1 KB
references/latex-template.mdmarkdown6.2 KB
references/mechanism-validation.mdmarkdown11.6 KB
references/open-topic-research.mdmarkdown4.9 KB
references/task-driven-modeling.mdmarkdown7.2 KB
schemas/claim-ledger.schema.jsonconfig5.5 KB
schemas/common.schema.jsonconfig2.5 KB
schemas/compile-receipt.schema.jsonconfig3.7 KB
schemas/cross-question-ledger.schema.jsonconfig1.3 KB
schemas/delivery-manifest.schema.jsonconfig7.9 KB
schemas/figure-manifest.schema.jsonconfig1.9 KB
schemas/handoff.schema.jsonconfig2.1 KB
schemas/independent-review-package.schema.jsonconfig3.4 KB
schemas/independent-review-result.schema.jsonconfig4.0 KB
schemas/latex-template-manifest.schema.jsonconfig2.4 KB
schemas/model-contract.schema.jsonconfig5.0 KB
schemas/paper-plan.schema.jsonconfig3.3 KB
schemas/paper-quality-report.schema.jsonconfig5.7 KB
schemas/paper-revision-log.schema.jsonconfig2.2 KB
schemas/paper-visible-text-report.schema.jsonconfig1.6 KB
schemas/problem-facts.schema.jsonconfig1.7 KB
schemas/results-index.schema.jsonconfig1.4 KB
schemas/run-manifest.schema.jsonconfig7.1 KB
schemas/source-manifest.schema.jsonconfig1.9 KB
schemas/task-capabilities.schema.jsonconfig3.9 KB
schemas/workflow-state.schema.jsonconfig2.4 KB
scripts/backend_selection.pyscript6.3 KB
scripts/build_handoff.pyscript20.4 KB
scripts/build_independent_review_package.pyscript14.9 KB
scripts/canonical_evidence.pyscript8.4 KB
scripts/compile_sources.pyscript2.4 KB
scripts/cumcm_check.pyscript2.9 KB
scripts/delivery_archives.pyscript7.0 KB
scripts/doctor.pyscript7.5 KB
scripts/index_result.pyscript10.9 KB
scripts/init_latex_paper.pyscript17.2 KB
scripts/init_project.pyscript11.1 KB
scripts/inventory_artifacts.pyscript4.1 KB
scripts/json_pointer.pyscript1.0 KB
scripts/official_materials.pyscript3.0 KB
scripts/paper_visible_text_check.pyscript5.4 KB
scripts/plan_redo.pyscript18.8 KB
scripts/project_status.pyscript5.8 KB
scripts/provenance.pyscript2.2 KB
scripts/record_compile.pyscript13.2 KB
scripts/record_decision.pyscript12.0 KB
scripts/record_run.pyscript28.1 KB
scripts/refresh_evidence.pyscript4.7 KB
scripts/set_mode.pyscript2.0 KB
scripts/submission_check.pyscript10.6 KB
scripts/workflow_checks.pyscript146.0 KB

references/latex-template.md

View on GitHub
# Reader-facing LaTeX scaffold

For Huawei Cup / 中国研究生数学建模竞赛, also read [Huawei delivery adaptation](huawei-delivery.md): current official cover, abstract/anonymity checks, submission filenames, attachments and measured MD5 binding.

Initialize after a claim-led `PAPER_PLAN.json` exists:

```bash
python3 "$S/init_latex_paper.py" --project <project> --competition <actual-name> --language <zh-or-en> \
  --competition-year <year> \
  --title <title> --keywords '<actual object; model; method>'
```

`--competition` records the actual competition. Default `--template auto` selects `huawei-ctex` for recognized Huawei Cup/graduate modeling names in Chinese (see [Huawei adaptation](huawei-delivery.md)); other competitions retain the generic scaffold. Explicit `--template generic` overrides automatic selection, while `--template huawei-ctex` selects the Chinese preset directly. This selects typography only, never current official rules. `--language zh` uses the Chinese CTeX scaffold; `--language en` uses an English article scaffold with the same modular body and evidence binding. Omitted options retain CUMCM/Chinese defaults. The template mode `contest_article` identifies the English asset; it is not a new workflow mode. The existing Chinese asset ID `cumcm-contest-ctex` is retained for compatibility and does not override the manifest's actual competition name.

Supply `--title` and `--keywords` from the actual problem, model, data, or method. The initializer has no reader-facing generic fallback and rejects generic title placeholders or workflow-oriented keyword filler.

The initializer checks exact subproblem coverage through `paper_structure`, stages all generated files, and publishes them transactionally with rollback if a commit fails. It refuses to overwrite existing source. If source metadata declares an adaptable official paper template, generic initialization stops so that template can be adopted or adapted. Format/submission/competition instructions do not block generic initialization; they remain bound official materials and `official_compliance` stays `unverified` until paper/delivery checks them. Filename keywords alone do not decide the role.

The scaffold keeps setup in `main.tex`, metadata in `metadata.tex`, shared notation/macros in `macros.tex`, and substantive writing in `sections/`. Abstract, references, and appendix are generic outer modules. Every body section and its input order come directly from `PAPER_PLAN.paper_structure`; the initializer does not generate per-question subsection trees or a LaTeX AST. Purpose, covered-subproblem IDs, and claim IDs appear only as comments for the writer and never render.

Remove placeholder markers before final status. Add only figures/tables selected for a real claim. Keep internal IDs out of rendered text; `paper_visible_text_check.py` measures that on the PDF. The generic scaffold is submission-neutral; adapt a user-supplied official package when required.

## Typography the scaffold already settles

Table captions sit above the table, figure captions below. Tables are three-line (`booktabs`): `\toprule`, one `\midrule` under the header, `\bottomrule`, and no vertical rules. A symbol table with more than a handful of entries is grouped by module rather than listed flat — `\symgroup{几何光学}` opens a block, and the reader finds a symbol by knowing which part of the model it belongs to:

```latex
\begin{tabular}{lll}
\toprule 符号 & 含义 & 单位 \\
\symgroup{几何光学}
$d$ & 外延层厚度 & \si{\micro\metre} \\
\symgroup{色散模型}
$\varepsilon_\infty$ & 高频介电常数 & 1 \\
\bottomrule
\end{tabular}
```

Units are typed in math mode (`$7.413\,\mathrm{\mu m}$`, `$970\,\mathrm{cm}^{-1}$`) rather than through a units package, so the scaffold compiles on a minimal TeX install; keep the spacing and the roman unit consistent across the paper. `\keyresult{}` bolds a value that is itself an answer; see `references/06-paper-writing.md` for when to use it.

TikZ (`texlive-pictures` on a Debian-family TeX install) is loaded with `arrows.meta`, `positioning`, `calc`, `shapes.geometric`, `fit` and `backgrounds`. This is a capability, not an instruction: mechanism sketches, decision flows and state diagrams carry no data and so are easy to overlook, and the packages are present so that drawing one is cheap when a claim needs it. Whether any figure belongs is decided per claim in `representation_plan`. The scaffold ships no figure and no figure placeholder.

For plotted figures, `assets/plot-style/cumcm.mplstyle` fixes sizes, fonts, grid and colours so every plot in the paper reads as one system. Point matplotlib at it and set a CJK family that exists on the machine; the file's header shows both lines. It does not decide what to plot either.

The generic style uses restrained heading/equation/float spacing, booktabs-friendly tables, `tabularx`/`longtable`, and subfigure support. Do not shrink dense tables reflexively or force floats away from their argument. Compile with `record_compile.py`. It runs the declared engine, writes `COMPILE_RECEIPT.json` with the PDF hash and a `sha256-tree-v1` snapshot of every required source file, reads the page count out of the PDF, rasterises every page to `.cumcm/tmp/pages/`, and derives the layout checks (overfull boxes, undefined references, missing glyphs, font errors) from the engine log:

```bash
python3 "$S/record_compile.py" --project <p> --update-quality
```

With `--update-quality` it refreshes the machine fields of `PAPER_QUALITY_REPORT.layout_report` — page count, rendered pages, checks, bound artifact. The report carries no decision of its own; the single approval before submission is `DELIVERY_MANIFEST.final_check`, and the pages rendered here are what it must present. Then actually look at the rendered pages: equations, tables, captions, figure placement, page density, whitespace, fonts and cross-page continuity are human QA, not a machine score.

The initializer records each planned `section_id` and its generated TeX path in `LATEX_TEMPLATE_MANIFEST.section_paths`, including sections with no subproblem IDs. Preserve this mapping when adapting or moving sections. Redo planning uses it for claim dependencies; an unmapped claim-only section conservatively invalidates all declared sections.
canvas-designanthropics/skillsCreate beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.Stars: 198kUpdated Claude CodeCodexVerifiedInstall
docxanthropics/skillsUse this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files) or Word templates (.dotx files). Triggers include: any mention of 'Word doc', 'word document', '.docx', '.dotx', or requests to produce professional documents with formatting like tables of contents, headings, page numbers, or letterheads. Also use when extracting or reorganizing content from .docx or .dotx files, inserting or replacing images in documents, performing find-and-replace in Word files, working with tracked changes or comments, or converting content into a polished Word document. If the user asks for a 'report', 'memo', 'letter', 'template', or similar deliverable as a Word or .docx file, use this skill. Do NOT use for PDFs, spreadsheets, Google Docs, or general coding tasks unrelated to document generation.Stars: 198kUpdated Claude CodeCodexVerifiedInstall
pdfanthropics/skillsUse this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill.Stars: 198kUpdated Claude CodeCodexVerifiedInstall
pptxanthropics/skillsUse this skill any time a .pptx or .potx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx or .potx file (even if the extracted content will be used elsewhere, like in an email or summary); editing, modifying, or updating existing presentations; combining or splitting slide files; working with templates (.potx), layouts, speaker notes, or comments. Trigger whenever the user mentions "deck," "slides," "presentation," or references a .pptx or .potx filename, regardless of what they plan to do with the content afterward. If a .pptx or .potx file needs to be opened, created, or touched, use this skill.Stars: 198kUpdated Claude CodeCodexVerifiedInstall