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/huawei-delivery.md

View on GitHub
# Huawei Cup / graduate modeling contest delivery

Read this for 华为杯 / 中国研究生数学建模竞赛 (Huawei Cup, GMCM/CPGMCM/CPMCM). Reuse the existing stages, evidence and three human checkpoints. This guide supplies adaptation mechanics, not a permanent edition of organizer rules. The agent performs these commands; users supply the current official materials and review the final pages/files.

## Editable Huawei typography preset

When no complete official LaTeX package is supplied, initialize with `--competition '华为杯' --language zh`. Default `--template auto` recognizes 华为杯, 研究生数学建模竞赛, Huawei Cup, GMCM, CPGMCM and CPMCM and selects `huawei-ctex` for Chinese output. Explicit `--template generic` preserves generic typography; `--template huawei-ctex` can also select the preset directly. English output keeps the English scaffold. Keep the existing validation checkpoint and `PAPER_PLAN` prerequisites.

```bash
python3 "$S/init_latex_paper.py" --project <p> --competition '华为杯' \
  --language zh --competition-year <actual-year> \
  --title '<actual paper title>' --keywords '<actual keywords>'
```

The independently authored CTeX preset takes structural lessons from the supplied `gmcmthesis` (2018) reference, without copying its class, fonts or logos. Defaults: centered 三号黑体 title, centered 四号黑体 first-level headings, 小四宋体 body and full-width abstract, body-sized table/figure/subfigure captions, centered continuous footer numbering, and no running header. The 16bp body baseline and 2.5cm margins are adjustable layout choices, not certified current official requirements. Edit the generated `paper/main.tex` against the current materials; `\huaweibodybaseline` controls body/abstract spacing. Tables inherit body size: split, wrap or use `longtable` before reducing text; a later explicit `\small` can still override this preset and needs page review.

Abstract length is not fixed to one page. There is no fixed year, institution, chapter list, code appendix quota or mandatory TOC. Chapters still follow `PAPER_PLAN`. Add a TOC only when useful and permitted. The preset shares the generic Chinese macros and section scaffolds, so shared writing guidance remains single. Its manifest identifies `huawei-ctex`, keeps `official_compliance: unverified`, and uses the existing compile, evidence and delivery chain. It does not bypass a declared official paper template. Use the cover adapter below when applicable.

## Current materials and the historical template

Collect the current official template, format specification and submission instructions through the existing intake/source manifest. Record the competition/year and source locations of each interpreted requirement in `PROJECT_BRIEF.md`. Missing materials block final compliance, not unrelated exploratory modeling. Do not infer current requirements from a competition label.

The inspected reference asset used `gmcmthesis` v2.3 (2018) with a separate cover, abstract, and body. Reuse that separation and its distinction between cover identity and anonymous body. Do not inherit its bundled fonts, logos, institution fields, fixed section list, one-page abstract instruction, or catalog's 50-page target as current rules. No third-party class, font or logo is redistributed here.

Confirm from the supplied edition: cover/logos and allowed identity fields; abstract layout and limit; body typography; which pages must be anonymous; exact PDF filename; attachment names/formats/size limits; MD5 and upload order/deadlines. Record byte limits explicitly instead of silently choosing MB versus MiB. Do not hard-code a year, team-number length, paper-page quota, or assume that an example `.rar` name proves ZIP is forbidden/accepted.

## Cover and paper adaptation

Prefer the complete official LaTeX package when one exists; adapt it using the existing `official_package_adapter` manifest and retain the planned argument structure. For an official cover supplied in Word/PDF, fill the current official cover with real team information and export **only that cover** as a one-page PDF. Preserve its required logos and appearance. Register the original official template as `paper_template` in `SOURCE_MANIFEST`; the filled cover is a project-local derivative, not an invented official source.

For this cover-first route, after the existing validation checkpoint:

```bash
python3 "$S/init_latex_paper.py" --project <p> --competition '华为杯' \
  --competition-year <actual-year> --language zh \
  --title '<actual title>' --keywords '<actual methods>' \
  --cover-pdf paper-materials/filled-official-cover.pdf
```

The initializer requires a declared, existing official template and a one-page cover. It copies the cover into the editable source, includes it as the first PDF page and records `official_package_adapter`; `official_compliance` stays `unverified`. For recognized Huawei names in Chinese, the remaining abstract/body automatically use the editable Huawei preset; explicit `--template generic` retains the generic Chinese scaffold. Adjust typography and abstract layout against the current official template. This is not automatic DOCX conversion or proof of matching the organizer template. Preserve existing paper sources; initialization refuses overwrites.

Compile/render through `record_compile.py`, then inspect every page. The embedded cover joins the compile-bound source snapshot and editable package. Set compliance only after the current official requirements and rendered result have actually been reviewed. Check cover logos, field placement, page order, abstract styling, and identity in image-based text visually.

## Submission declarations and measured checks

Use the existing `delivery/DELIVERY_MANIFEST.json`. Add `submission.rules` after reading the current materials. The following is a **synthetic example**, not current official limits/names; replace every value with the actual project requirements:

```json
{
  "submission": {
    "rules": {
      "sources": ["problem/official/format.pdf", "problem/official/submission.pdf"],
      "pdf_name": "A123456.pdf",
      "cover_pages": 1,
      "identity_tokens": ["Actual University", "Actual Member", "123456"],
      "abstract": {
        "start_marker": "摘要",
        "body_marker": "1 问题重述",
        "max_pages": 2
      },
      "attachments": [
        {"path": "delivery/A123456.zip", "name": "A123456.zip",
         "max_bytes": 10000000, "formats": ["zip"]}
      ]
    }
  }
}
```

Include all known institution/team/member/student identifiers (including meaningful spelling variants) in `identity_tokens`. This declaration cannot establish that every identifier was listed. `sources` must reference local official format/submission/template materials classified in the source manifest; cite exact sections in the brief. `attachments` is empty only when no attachments are being submitted. The tool cannot infer missing required attachments from prose.

The abstract markers are unique visible headings in the actual PDF, not declared page counts. Use the full first body heading including its numbering; whitespace is normalized. The tool derives occupied abstract pages from their positions. Ambiguous/repeated markers, blank/image-only pages, or missing Poppler tools fail closed; adapt the extraction/markup and inspect the PDF rather than inventing a successful record. Running heads may require more specific markers. Text extraction is not OCR or visual compliance certification.

After final compilation, required submission naming, packaging and metadata refresh, run:

```bash
python3 "$S/submission_check.py" --project <p>          # inspect without writing
python3 "$S/submission_check.py" --project <p> --record # save measured checks
python3 "$S/cumcm_check.py" --project <p> --stage delivery --gate-mode preflight
```

`--record` writes only on success, into the existing manifest. The observed record includes actual PDF MD5/SHA256/size/page count, abstract span, rule-file hashes, rule-declaration hash, compile-receipt hash and attachment measurements. Never type these fields. `DELIVERY-E022` recomputes them: missing/inconsistent checks warn in working and block finalizing. Huawei-labeled projects require this check; other contests may opt in by declaring `submission`. Existing compile/source/approval checks remain in force.

The name in the final PDF declaration must match the name required for actual upload. Preserve the compile receipt's PDF and its source binding; if delivering a renamed copy, it must have identical bytes. Existing final-PDF binding checks still apply. Internal editable/computation ZIPs remain separate from organizer-facing attachments. The submission checker validates ZIP containers and recognizes RAR/7z signatures; it does not build RAR/7z, unpack those formats, inspect archive-member anonymity, or prove their contents are complete. Open and review the actual submission archive separately.

## Freeze, review, then submit the exact bytes

Create the submission record **before** the existing final human review, so the approval covers it and the exact rendered PDF. The record is a local byte-identity check, not an organizer upload receipt and not another human checkpoint. Submission remains user-controlled. Use the official platform/tool when the current rules require it.

When the current rules use MD5 -> PDF -> attachment stages, the MD5 must come from the exact PDF that will be uploaded. After sending MD5, do not recompile, edit metadata, optimize/compress, stamp, or otherwise regenerate the PDF. Re-run the read-only check before upload; a mismatch means stop, not silently issue a replacement MD5. Keep any platform acknowledgement separately as user-supplied evidence.

The recorder refuses to replace a different existing record, and `refresh_evidence.py` does not refresh it. Before submission, if a revision is deliberately authorized, use the existing revision/review procedure, explicitly remove the obsolete `submission.recorded` field, and re-record/review the new final artifact. After MD5 submission, do not erase the old record to bypass a mismatch: resolve the change through the current organizer process. Source hashes remain integrity evidence; MD5 exists solely for the contest submission protocol.
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