360 Secure SkillHub
360 安全技能中心

originality-check

基于 UIBC 赛事规范的零依赖命令行决策支持工具:将提交作品指纹与历史/公开库指纹比对,输出含结果、退出码、错误码与告警的 JSON IR,用于原创性预审;权限声明为不联网、不读写文件、不调用子进程,且非最终裁决。

zhaoxinghua09-cell
zhaoxinghua09-cell
热度 62.23
最近更新 2026-10-17 07:23:23
分类:安全依赖:代码执行应用场景:报告撰写

安装技能

复制下面的话术发给你的 Agent,它会通过 secure-skills 检索并安装该技能。

执行命令安装此 skill: npx secure-skills-cli add originality-check
Metadata
name
originality-check
slug
originality-check
displayName
赛事作品原创性查重器
version
1.1.1
category
ai-agent
display_name
赛事作品原创性查重器
title
赛事作品原创性查重器
author
诺源(SynomosAI)
author_note
"SynomosAI" / "SynomosAI" — 未申请实体注册、未申请商标注册(not a registered legal entity; no trademark registered)
license
MIT
allowed-tools
Read, Glob, Grep, Bash, Write, WebFetch
license_scope
代码(.py 文件)MIT;本 SKILL.md 与其中理论文本不在 MIT 覆盖范围内(见文末「License & attribution」)
description
赛事作品原创性查重器——基于 UIBC 赛事规范的零依赖决策支持工具,JSON IR 输出,覆盖TH-EVT-005域。 适用场景:当需要赛事作品原创性查重器能力时使用本技能;触发词:赛事、判定器、TH-EVT-005、originality-check。
tags
["赛事","判定器","TH-EVT-005","originality-check","原创性","查重"]
description_zh
赛事作品原创性查重器——基于 UIBC 赛事规范的零依赖决策支持工具,JSON IR 输出,覆盖TH-EVT-005域。
description_en
Contest submission originality and plagiarism checker: zero-dependency decision support with JSON IR output (UIBC spec, domain TH-EVT-005).
read_when
["参赛者提交作品前需做原创性预审","担心作品与历史/公开库雷同、违反学术道德","需要零依赖的原创性合规检查报告供决策","赛事评审要批量比对作品指纹"]
classification
{"skillhub":["community-events"],"iso_25010":["Usability"]}
risk_tier
medium
risk_rationale
门禁批量补丁默认 medium(内部约定:本 skill 设计为中等风险):调用 API/读写文件/本地执行,最小权限,密钥走 Secret;若实际涉对外代执行(push/发布/发送/上架)须人工复评,改 high 并走负责人批准。
platforms
["windows","macos","linux"]
platform_compatibility
["windows","macos","linux"]
ai_protocol
true
spec
usk/1.0
interface
{"type":"cli","entry_point":"originality-check.py","runtime":"python3","call_pattern":"args"}
input_schema
{"submission_hash":{"type":"string","description":"作品指纹(必填,缺失时报错 rc=2)","required":false},"known_hashes":{"type":"string","description":"历史/公开库指纹 JSON 字符串列表(缺省按空库从严告警)","required":false},"demo":{"type":"bool","description":"跑内置冒烟案例","required":false},"json":{"type":"bool","description":"输出 JSON IR(默认)","required":false}}
output_schema
{"stdout":"结构化 JSON IR(含 result / rc / error_code / warnings)","exit_code":"rc=0 正常 / rc=1 告警或从严推定 / rc=2 输入不足或非法"}
capabilities
["originality","plagiarism","contest"]
permissions
{"network":false,"filesystem":false,"subprocess":false}
requirements
{"python_packages":[],"min_python":"3.8"}
changelog
1.1.1: Bilingual rewrite (full EN+ZH, English first); 1.0.0: initial upload (USK v3)

凡自治之物 · LGD 治理学 · 创造术家族 | 评测协议:skill-quality-gate

English

When to use

  • When a contestant is preparing to submit a work and needs an originality pre-check per UIBC contest rules.
  • When working in technical (TH) domains such as TH-EVT-005 and you worry about content overlap or violations of academic-integrity standards.
  • When you need a quick compliance check report, produced by a zero-dependency tool, to support decision-making.

Usage

  • Invocation: trigger the skill directly through system instructions or conversation context; no external script loading is required.
  • Parameters: pass work_content (work text or file summary) and target_domain (e.g. TH-EVT-005).
  • Output format: the response strictly follows JSON IR and includes similarity metrics and a risk rating.

Workflow

  1. The user prepares and uploads or types the work content to be checked into context.
  2. The required check-standard domain is specified (e.g. the TH-EVT-005 technical spec).
  3. The system performs an internal comparison, invoking the built-in knowledge base for duplicate detection.
  4. It generates a JSON IR feedback report containing the originality score.
  5. Based on the risk level in the feedback, adjust the work or the submission decision.

Evidence & safety statement

  • Evidence: TBD (no evaluation / badge link yet; update here once produced)
  • Version: 1.1.1
  • Safety: no independent security scan has been performed (TBD); the conclusion is pending and no endorsement is given until it is completed.

中文

何时用

  • 当参赛者准备提交作品,需依据 UIBC 赛事规范进行原创性预审时。
  • 在涉及技术类(TH)领域(如 TH-EVT-005),担心内容雷同或违反学术道德标准时。
  • 需要快速生成符合零依赖工具要求的合规性检查报告供决策参考时。

用法

  • 调用方式:通过系统指令或对话上下文直接触发技能,无需加载外部脚本。
  • 参数定义:需传入 work_content(作品文本或文件摘要)及 target_domain(指定如 TH-EVT-005)。
  • 输出规范:响应将严格遵循 JSON IR 格式,包含相似度指标与风险评级。

流程

  1. 用户准备并上传或输入待检作品内容至上下文。
  2. 明确指定核查标准域(如 TH-EVT-005 技术规范)。
  3. 系统执行内部比对,调用内置知识库进行查重分析。
  4. 生成包含原创性评分的 JSON IR 反馈报告。
  5. 依据反馈中的风险等级调整作品或提交决策。

证据与安全声明

  • 证据:TBD(暂无评测/徽章链接;产生后在此更新实际链接)
  • 版本:1.1.1
  • 安全:未做独立安全扫描(TBD),结论待补;补全前不作推荐背书。