GitHub user
Agent skills by larbare12
- skills
- 9
- repository
- 1
Repositories by larbare12
Skills by larbare12, ranked
Ranked by score. Sort bymost stars,trending,newest,recently updated
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 1 | 学术文献检索与质量验证。覆盖 Semantic Scholar / CrossRef / arXiv / OpenAlex 四源,内置 Tier 0 反幻觉校验(DOI 反查 + Levenshtein ≥ 0.70) 和 venue quality 过滤(CCF + JCR 影响因子,arXiv 引用阈值)。任何需要 查文献、验证引用真实性、评估期刊/会议质量、生成… | larbare12/ | 116 | — | ~1.9k | Automated safety check: Notes | No licence | 4 mo ago |
| 2 | M0 项目仪表盘——流程外的常驻横切模块,不属于线性步骤。任何时点 扫描 relate-work/ + draft/ 输出三态报表:已完成 / 待回填(NEEDS-EVIDENCE / TODO / 未读论文)/ 阻塞。M1-M7 任何阶段都可以调用 M0 看状态。/paper- assistant:init 命令首次扫描就是它。M0 只读不写,不动 manifest 也不动 draft。 | larbare12/ | 116 | — | ~809 | Automated safety check: Notes | No licence | 4 mo ago |
| 3 | 3.M1 Topic M1 选题诊断——数据驱动的研究 idea 可行性 / 创新性 / 领域契合度评估. An agent skill from larbare12/paperfactory-from-idea-to-manuscript. | larbare12/ | 116 | — | ~1.2k | Automated safety check: Notes | No licence | 4 mo ago |
| 4 | M2 文献管理(IMRAD 中的 Related Work + References)。消费 M1 沉淀的 search-.jsonl,做精读、引用网络分析、bibkey 整理、四类标签(基础/方法/ baseline/相关)、引用密度审计、BibTeX 格式规范化,产出 manifest.jsonl + ref-.md 笔记卡 + 引用校验报告,供 M3 baseline / M5 论证链… | larbare12/ | 116 | — | ~1.8k | Automated safety check: Notes | No licence | 4 mo ago |
| 5 | M3 实验设计——方案检查、指标选择、对比方法、消融、显著性、误差分析. An agent skill from larbare12/paperfactory-from-idea-to-manuscript. | larbare12/ | 116 | — | ~1.2k | Automated safety check: Notes | No licence | 4 mo ago |
| 6 | M4 结构规划——生成 IMRAD 大纲、章节边界、篇幅分配、写作顺序。只管 骨架,不管论证逻辑(论证主线归 m5-argument)。消费 M3 实验结果概要 和 M1 选题定位,产出 outline 写入 passport,供 M5/M6 按章节展开。 | larbare12/ | 116 | — | ~952 | Automated safety check: Notes | No licence | 4 mo ago |
| 7 | M6 写作辅助——按 M5 论证骨架展开正文,按 M4 章节边界控制内容. An agent skill from larbare12/paperfactory-from-idea-to-manuscript. | larbare12/ | 116 | — | ~2.3k | Automated safety check: Notes | No licence | 4 mo ago |
| 8 | M7 投稿前总检——三段:A 内容红队(回扫 M5 反驳预判 + M3 实验缺陷清单) / B 格式合规(LaTeX 编译、章节顺序、图表参考文献、期刊特定要求)/ C rebuttal 撰写(投稿后)。本模块不重新造审稿人清单,只触发并回扫 M5/M3 已有的清单。进入前必须通过 m0-dashboard 看 pending=0,必须先 跑 verifycitations.sh(Tier 0… | larbare12/ | 116 | — | ~2k | Automated safety check: Notes | No licence | 4 mo ago |
| 9 | M9 合规与伦理——投稿前最后一道硬门控。三段:A PRISMA-trAIce 17 项 (AI 披露完整性)/ B RAISE 五维(可复现/可追责/诚信/安全/伦理)/ C 期刊 AI 披露声明生成 / D 完整性门控(PASS/WARN/BLOCK)。任何 RED 级别失败阻止投稿。包含 Tier 0 引用 audit 复检、剽窃检测、AI 失败模式扫描、IRB… | larbare12/ | 116 | — | ~2.4k | Automated safety check: Notes | No licence | 4 mo ago |
Questions, answered from the data.
What is the best skill by larbare12?
Citation Search from larbare12/paperfactory-from-idea-to-manuscript ranks first of the 9 skills by larbare12 listed here, with the highest score: its repository has 116 GitHub stars, its SKILL.md loads about 1.9k tokens and it has informational notes only in the automated safety check. Next come M0 Dashboard and M1 Topic.
Are larbare12's skills official?
None yet. All 9 skills by larbare12 listed here come from community repositories; a skill counts as official when the product's own GitHub organization publishes it.
How are these skills ranked?
By Skill Navigator score, which combines the GitHub stars of the skill's repository (shared across that repo's skills and discounted for large collections), how many other GitHub owners carry a copy of the skill, and automated SKILL.md quality checks, minus penalties for safety-check warnings and for each further skill from the same repository. Skills that fail the safety check are not listed.