ia-qa.com/mcp llm and RAG testing - Dev/QA toolbox
IA-QA as an MCP Server
目录 / 搜索检索 / citation-coverage-check
--- name: citation-coverage-check description: citation-coverage-check — 扫描文章中含数字/日期/论断的句子,统计带来源标注(据/来源/source/链接/文献)的比例;低于阈值 rc=1,逐句列出缺出处清单。 适用场景:当需要引用覆盖率检查器能力时使用本技能;触发词:citation-coverage-check。 slug: citation-coverage-check version: 1.0.1 display_name: 引用覆盖率检查器 display_name_en: Citation Coverage Check agent_created: true author: 诺声(Logos)@SynomosAI license: MIT 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」) allowed-tools: Read, Glob, Grep, Bash, Write, WebFetch category: AI 治理 platforms: [claude-code, codebuddy, workbuddy, openai-agents] copyright: SynomosAI description_zh: "citation-coverage-check — 扫描文章中含数字/日期/论断的句子,统计带来源标注(据/来源/source/链接/文献)的比例;低于阈值 rc=1,逐句列出缺出处清单。" description_en: "Scan articles for sentences with numbers, dates or claims and measure source-attribution coverage; below threshold rc=1 with a per-sentence missing-citation list." classification: skillhub: ["security-compliance"] iso_25010: ["Security"] risk_tier: medium risk_rationale: "门禁批量补丁默认 medium: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。" tags: [citation-coverage-check, AI 治理] ai_protocol: true read_when: - 用户提及本技能触发词或面临描述中的典型问题时 - 用户说「citation-coverage-check」或需要该能力时 spec: usk/1.0 interface: type: cli entry_point: scripts/citation_coverage_check.py runtime: python3 call_pattern: args input_schema: - name: file type: string description: 文件 required: false - name: text type: string description: 内联文本 required: false - name: threshold type: float description: 覆盖率阈值默认0.6 required: false - name: json type: bool description: JSON 输出 required: false output_schema: stdout: 无出处论断清单与覆盖率 exit_code: type: integer description: "0=OK/PASS; 1=findings/warnings; 2=usage or argument error" capabilities: - citation - academic_writing - fact_check permissions: network: false filesystem: false subprocess: false requirements: python_packages: [] min_python: "3.8" changelog: "1.0.1: bilingual rewrite (English-first, Chinese-after, full body) + read_when/desensitization; 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(外部公开评测门禁文档) ## English ### When to use - When writing academic papers or technical reports, to review whether key claims carry source citations. - To verify citation coverage of factual info (numbers, dates) in a document. - When content review requires the literature-source ratio to meet a threshold. ### Usage - Run: `python citation_coverage_check.py --input article.txt`. - Set citation markers to "据/来源/source/链接/文献" to match document style. - Tune `--rc` sensitivity (default 1 for strict checking). ### Process 1. Parse the input and extract candidate sentences with numbers, dates, and claims. 2. Scan each sentence end for citation markers (据/来源/source/链接/文献). 3. Compute the attributed-sentence ratio and compare against the threshold. 4. Generate a per-sentence missing-citation list with positions and excerpts. 5. Output a summary of non-compliant paragraph counts and ratios. 6. Help the user locate and fill missing citations. ### Evidence & safety statement - Evidence: TBD (no evaluation/badge link yet; fill in the real link here once produced). - Version: 1.0.1 - Safety: No independent security scan has been done (TBD); the conclusion is pending. No endorsement is given until it is completed. ## 中文 ## 何时用 - 在撰写学术论文或技术报告时,审查关键论断是否附带来源标注。 - 用于验证文档中涉及数字、日期等事实性信息的引用覆盖率是否达标。 - 当内容审核要求明确文献出处比例不低于 rc=1 阈值时调用此技能。 ## 用法 - 执行命令行命令:`python __pycache__/citation_coverage_check.py --input article.txt`。 - 指定引用标注类型为“据/来源/source/链接/文献”以适配不同文档风格。 - 通过调整参数 `--rc` 设置敏感度阈值,默认情况下设为 1 进行严格检查。 ## 流程 1. 解析输入文本,提取包含数字、日期及论断的候选句子。 2. 扫描每句末尾是否匹配“据/来源/source/链接/文献”等引用标记。 3. 统计标注句子比例并与阈值 rc=1 进行数值比对判定。 4. 生成缺失引用的逐句清单,列出具体位置及对应原文片段。 5. 输出分析结果摘要,提示不达标段落数量及占比情况。 6. 辅助用户定位并补充缺失的文献引用信息或标注。 ## 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:1.0.0 - 安全:未做独立安全扫描(TBD),结论待补;补全前不作推荐背书。
| 版本 | 存档时间 | 内容哈希 | 内容 |
|---|---|---|---|
| v1 | 2026-09-29 11:33 | f2e5c160 | 已过保留期 |
| v2 | 2026-10-17 15:59 | e6b12645 | 可取 |
版本索引永久保留;内容副本只保留最新 1 份,更早版本仅留索引与哈希(存档时间线的证据链不会因此断裂)。
IA-QA as an MCP Server
DACH B2B opportunity intelligence with FIT/NEED/NOW scoring and MCP access
Chemical intelligence for compound structure search, fragment analysis, and ADMET property prediction
Provide a comprehensive spellbook for Dungeons & Dragons 5th Edition to enhance your gameplay experience
Calculate and compare global shipping costs including detention, demurrage, and local port charges
Calculate detention, demurrage, and local shipping charges for ports worldwide
侵权举报经核验成立后,我们会即时下线该条目并删除已存的内容副本。