Menu

Individual skill

math-abstract

0upvotes

Use when 高教社杯/CUMCM/电工杯 mathematical modeling abstracts, keywords, highlights, first-page claims, or high-density summaries need drafting, revision, audit, or style diagnosis, especially when feedback mentions too many numbers, weak focus, process-listing, empty official prose, buzzwords, missing structure, weak keywords, unsupported values, or first-page claim verification.

math-abstract/SKILL.md

Read pinned source

Source commit da53b41cab7e25be906f5899488229387e7921c0

What was checked

Matches the observed repository HEAD
Yes
Scanner rules are current
No
Repository scan complete
No
Skill scan complete
Yes
Observed behavior
Not checked yet
Last checked
Nov 5, 2026

These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.

Install this skill

Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.

An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.

Repository context

Repository stars (not skill ratings)
58
Repository last updated
Jul 19, 2026
License
MIT

Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.

Files and excerpt

File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.

Browse files
Read excerpt

# Contest Abstract

## Purpose

Turn contest evidence into a dense, judge-friendly abstract, keywords, and first-page claim set.

Two modes:

- **Style coaching mode**: diagnose or rewrite a user-provided abstract for readability, focus, number burden, contest prose, and first-screen judge value. Use only claims supplied by the user; mark evidence gaps instead of inventing support.
- **Paper-ready mode**: generate or approve a final abstract only from verified paper evidence, using the evidence gates below.

Core rule: the abstract follows evidence. No number, ranking, feasibility statement, robustness statement, or innovation claim may appear in paper-ready text unless traceable to the body, table, figure, formula, registry row, or run log.

National-first quality gate: `国一候选` is a quality target, not an award promise (`不承诺获奖`). The abstract may compress only conclusions that show 题目贴合, 建模洞察, 证据可信, 可复现, and 边界清楚. A catchy but unsupported claim must be downgraded to an evidence gap.
Back to top