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/source-tiers.md
View on GitHub# Source Tiers
Use this tiering to decide how much trust a source can carry.
## Tiers
| Tier | Source type | Use |
| --- | --- | --- |
| T1 | Official APIs, publisher pages, DOI records, PubMed/CrossRef/arXiv records, official standards or policy pages | Primary bibliographic and rule evidence |
| T2 | Semantic Scholar, institutional repositories, university pages, repository metadata, verified preprint servers | Secondary discovery and citation graph support |
| T3 | Google Scholar snippets, web pages without stable metadata, scraped databases, forum posts, unverified Chinese database snippets | Discovery only unless manually verified |
## Domain Routing
| Domain | Primary route | Secondary route | Manual route |
| --- | --- | --- | --- |
| Math/CS/optimization | arXiv, CrossRef, publisher DOI | Semantic Scholar | Google Scholar |
| Engineering/energy/power systems | CrossRef, IEEE/Elsevier/Springer DOI pages, official standards | Semantic Scholar | CNKI/Wanfang export if provided |
| Biomedical/clinical | PubMed | Semantic Scholar | journal site |
| Policy/standards | official ministry, standards body, regulator, contest notice | institutional mirror | web snippets only as leads |
| Chinese literature | verified CNKI/Wanfang export, DOI page when available | author/institution pages | manual check required |
## Reliability Rules
- Use T1 whenever a paper-ready citation, DOI, publication year, or rule claim matters.
- Use T2 when T1 coverage is incomplete, but verify final metadata before citation.
- Use T3 only to discover leads or identify Chinese titles that require manual confirmation.
- If the source cannot be opened or metadata cannot be verified, keep the reference as `candidate`.
- For changing policies, standards, model versions, or journal instructions, check the current source date.
## Fallback
If T1 search fails, broaden terms before dropping to weaker sources. If all sources fail, report the gap and do not fabricate a reference.
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 |