GitHub user
Agent skills by bosprimigenious
- skills
- 8
- repository
- 1
Repositories by bosprimigenious
Skills by bosprimigenious, ranked
Ranked by score. Sort bymost stars,trending,newest,recently updated
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 1 | 对 AutoResearch 的正式 Baseline 做只读合理性审查，检查训练不足、实现故障、预算或 seed 不公平及缺乏代表性的弱对照，区分合理 naive Starter 与评分锚点。适用于专家提交包和 Baseline/Reference 证据复核，不用于求解任务或要求 Baseline 达到 SOTA。 | bosprimigenious/ | 152 | — | ~1.1k | Automated safety check: Pass | MIT | 4 days ago |
| 2 | 自主检索、去重并筛选可转化为 AutoResearch 优化任务的论文，核查论文与源码许可、优化面、评测、资源、效应噪声和目标 Harness 可交付性。用于从零找论文、维护候选池或在投入实现前做选题预检；不用于已经确定论文后的实验执行。 | bosprimigenious/ | 152 | — | ~506 | Automated safety check: Pass | MIT | 4 days ago |
| 3 | 对 AutoResearch 目录或 ZIP 做只读质检；先审优化面是否仅调参、Baseline 是否合理、Reference 提升是否充分，再查 21 项实现、严格 Docker 路径、Harbor 接口与成对训练证据。输出方法介绍、完整跑分、专家退回说明及 TXT/Markdown/JSON 报告；不用于求解任务。 | bosprimigenious/ | 152 | — | ~1.6k | Automated safety check: Pass | MIT | 4 days ago |
| 4 | 为 AutoResearch 的双 Agent 轨迹、付费 GPU 长跑、Docker 执行、可信评测与恢复建立共享协议、成本决策和隔离边界。用于小时/包日选择、启动或恢复 campaign、设计证据与防止题目或轨迹串用；不替代具体任务算法或最终平台 QA。 | bosprimigenious/ | 152 | — | ~553 | Automated safety check: Pass | MIT | 4 days ago |
| 5 | 从论文与代码仓设计可交付的 AutoResearch 工程题，确定 Starter、Baseline、Reference、评分器、Harbor 结构和证据契约。用于出题、改题或审题；不替代提交包最终 QA。 | bosprimigenious/ | 152 | — | ~390 | Automated safety check: Pass | MIT | 4 days ago |
| 6 | 在已获授权的飞书/Lark 多维表格中处理 AutoResearch 的领题、完成提交/验收和组长初检三表流转，核对当期题号、字段权限、证据和写后回读。用于领取题目、提交验收材料或回填初检结论；不用于绕过组织权限、恢复离职账号或替代任务 QA。 | bosprimigenious/ | 152 | — | ~413 | Automated safety check: Pass | MIT | 4 days ago |
| 7 | 将 AutoResearch 的 Claude、Codex、Cursor 对话、命令输出和外部提交状态整理为可执行交接，区分事实、失败、待办和证据边界。用于总结长会话、换 agent 或收尾归档；不把对话陈述当作已验证事实。 | bosprimigenious/ | 152 | — | ~183 | Automated safety check: Pass | MIT | 4 days ago |
| 8 | 从论文、代码和评测资源中筛选 AutoResearch 优化面，排除纯调参、不可隔离、不可复算或收益不足的方向，并产出可验证题目合同。用于选优化面和更换失败方向。 | bosprimigenious/ | 152 | — | ~127 | Automated safety check: Pass | MIT | 4 days ago |
Questions, answered from the data.
What is the best skill by bosprimigenious?
Autoresearch Baseline Quality from bosprimigenious/autoresearch-skills ranks first of the 8 skills by bosprimigenious listed here, with the highest score: its repository has 152 GitHub stars, its SKILL.md loads about 1.1k tokens and it passes the automated safety check with no findings. Next come Autoresearch Paper Discovery and Autoresearch Task QA.
Are bosprimigenious's skills official?
None yet. All 8 skills by bosprimigenious 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.