capwitf/My-MathModeling-skills / math-literature
math-literature
VerifiedUse when 高教社杯/CUMCM mathematical modeling papers need lightweight literature search, citation verification, method/background references, standards or policy sources, Chinese-English source routing, DOI/BibTeX checks, or claim-to-citation mapping without fabricated sources.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 3.1 KB |
| agents/openai.yaml | config | 306 B |
| references/citation-evidence-contract.md | markdown | 2.4 KB |
| references/contest-scope.md | markdown | 2.3 KB |
| references/search-workflow.md | markdown | 3.1 KB |
| references/source-tiers.md | markdown | 1.9 KB |
references/search-workflow.md
View on GitHub# Literature Search Workflow
## Query Construction
Start from the paper need, not from generic keywords.
This workflow verifies sources for paper claims. If the active need is to find modeling ideas, baseline schemes, transferable variables, or route candidates before the model is chosen, record the route-search need and return it to `math-hub`; return only citation candidates here for verification.
1. Extract the modeling object: grid, traffic, logistics, epidemic, reservoir, energy storage, scheduling, routing, allocation, risk, or policy.
2. Extract the modeling action: optimization, prediction, simulation, evaluation, classification, control, dispatch, planning, or sensitivity analysis.
3. Extract the evidence need: method precedent, parameter source, baseline, dataset, standard, policy, limitation, or application context.
4. Build bilingual terms when the problem statement is Chinese.
5. Combine terms with Boolean logic and test narrow/broad versions.
## Contest Modeling Query Patterns
| Need | Query shape |
| --- | --- |
| Method precedent | `"[object]" AND "[modeling action]" AND (optimization OR simulation OR evaluation)` |
| Parameter source | `"[object]" AND (parameter OR coefficient OR efficiency OR cost OR emission factor)` |
| Baseline method | `"[decision problem]" AND (baseline OR benchmark OR comparison) AND model` |
| Energy system | `(renewable OR photovoltaic OR wind) AND (dispatch OR storage OR hydrogen) AND optimization` |
| Transportation/logistics | `(routing OR location allocation OR scheduling) AND (optimization OR integer programming)` |
| Risk/evaluation | `(risk assessment OR comprehensive evaluation) AND (indicator system OR weighting)` |
| Chinese contest context | Chinese official term plus English translation, checked separately |
## Search Sequence
1. Start with structured scholarly sources for bibliographic records.
2. Search official standards, policy pages, or contest attachments separately when the claim is regulatory or rule-based.
3. Use broad web search only to discover leads, then verify the bibliographic record from a stable source.
4. For each accepted source, record what exact claim it supports before drafting prose.
5. Stop once the paper has enough verified sources for the active contest claim; do not chase exhaustive coverage by default.
## Broadening And Narrowing
If too many results:
- add the object domain, method family, year range, or "case study";
- require title/abstract matches when the source supports method precedent;
- add "review" only when seeking a map of the field.
If too few results:
- remove contest-specific phrasing;
- replace Chinese proper nouns with standard English technical terms;
- search for the mathematical problem class rather than the application name.
## Search Log
Record every nontrivial search:
```csv
search_id,source,query,date_checked,result_count,accepted_reference_ids,notes
```
Do not treat an unlogged search result as paper-ready evidence for important method, parameter, policy, standard, or data claims. For simple contest background, keep at least a compact note with title/source/date checked.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| add-product-e2e-evalpaperclipai/paperclipAdd or extend a Paperclip full-stack runner E2E workflow, fixture, matcher, or report evidence path for local or Daytona execution. | Stars: 115k | Updated | Claude CodeCodex | Verified | Install |
| add-runner-evalpaperclipai/paperclipAdd or extend a Paperclip Runner protocol evaluation definition, roster, assertion, or report fixture with provenance and narrow validation. | Stars: 115k | Updated | Claude CodeCodex | Verified | Install |
| diagnose-why-work-stoppedpaperclipai/paperclipCompatibility entry point for failed, stalled, looping, or over-recovered Paperclip work. Use fix-failed-paperclip-run for the full diagnosis, regression, repair, real verification, and green-PR workflow; honor an explicitly requested diagnosis-only scope. | Stars: 115k | Updated | Claude CodeCodex | Verified | Install |
| fix-failed-paperclip-runpaperclipai/paperclipDiagnose and fix failed, stuck, slow, or incorrectly blocked Paperclip tasks and runs. Use with a task/run URL or failure report to trace the root cause, prove a regression red then green, check second-order effects, verify the real workflow, and deliver a PR with passing checks. | Stars: 115k | Updated | Claude CodeCodex | Verified | Install |