GitHub user
Agent skills by HughYau
- skills
- 14
- repositories
- 2
Repositories by HughYau
- qiushi-skillQiushi-Skill: Build agents that investigate first, focus on the main contradiction, validate in practice, and keep pushing until the work is actually done. 求是Skill——从经典唯物辩证法与实践哲学中提炼出一条总原则和九大方法论工具武装AI大脑。3.8k stars · 11 skills
- AcademicForgeOne Forge, All Skills: A curated skill collection for academic writing and research. 点开即用，按需配置的一站式学术研究skills平台。2.6k stars · 3 skills
Skills by HughYau, ranked
Ranked by score. Sort bymost stars,trending,newest,recently updated
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 1 | 集中兵力：多件事同时争抢时间、注意力或预算时，列出全部待办，选定唯一主攻目标并公开锁定，彻底解决、验证后再转向下一个。当待办过多、推进分散、"每件都做了一点但都没做完"、需要决定先做什么时触发；只有一个任务、任务彼此独立可并行、用户明确要求同时推进时不触发。 | HughYau/ | 3.8k | — | ~379 | Automated safety check: Pass | MIT | 7 days ago |
| 2 | 矛盾分析法：把复杂问题拆成若干对立面，找出规定其他矛盾的主要矛盾及其主要方面，判定对抗性 / 非对抗性，并据此选择处理方式。当问题头绪多、多个因素互相牵制、优先级不清、根因不明、反复修不好、trade-off 说不清时触发；直接执行类任务或用户已定方案时不触发。 | HughYau/ | 3.8k | — | ~485 | Automated safety check: Pass | MIT | 7 days ago |
| 3 | 批评与自我批评：在工作完成、阶段验收、收到批评或同类错误反复出现时，对成果和过程做诚实、具体、基于事实的审视，输出可执行的改进项，并处理外来批评而不辩解。触发信号包括 review、复盘、审查、"帮我看看有没有问题"、"你确定吗"；任务刚开始或只是单步查询时不触发。 | HughYau/ | 3.8k | — | ~423 | Automated safety check: Pass | MIT | 7 days ago |
| 4 | 调查研究：在下判断、做决策、给建议之前，先用第一手材料弄清现状，产出「事实 / 推断 / 未知」三栏调查结论。当上下文不完整、证据薄弱、领域陌生、用户说"先别动手"、或你发现自己在凭印象作答时触发；已充分调查后的执行阶段不要重复触发。 | HughYau/ | 3.8k | — | ~425 | Automated safety check: Pass | MIT | 7 days ago |
| 5 | A skill your agent uses when the user has attached a PDF, paper, report, or other document and the answer needs content from more than one place in it: summarize the methods or any other section… | HughYau/ | 2.6k | — | ~3.1k | Automated safety check: Pass | Apache-2.0 | 1 mo ago |
| 6 | 群众路线：从持有真实情况的多方（用户、使用者、代码库、日志、运行结果）收集分散意见，系统化为方案，再带回去对齐与检验，循环改进。当多方意见分歧、需要汇总零散反馈、方案要拿回给真实使用者确认、或你发觉自己在闭门造车时触发；信息源单一且完整、处于执行阶段时不触发。 | HughYau/ | 3.8k | — | ~467 | Automated safety check: Pass | MIT | 7 days ago |
| 7 | 统筹兼顾：当多个目标、指标或利益方相互制约、优化一项会伤害另一项时，识别全部辩证关系对，检查片面性，为每对关系定出当前阶段的侧重与底线，评估系统性影响，并设失衡预警。触发信号包括 trade-off、目标冲突、速度 vs 质量、短期 vs 长期、"顾此失彼"；只有单一目标、用户已定取舍、或属硬性二选一时不触发。 | HughYau/ | 3.8k | — | ~416 | Automated safety check: Pass | MIT | 7 days ago |
| 8 | 实践认识论：把方案、假说或判断放回实践中检验，按「实践 → 认识 → 再实践」螺旋迭代，并在开始前写明循环终止条件。当你提出了假说要验证、一次尝试失败要复盘再来、发现自己只想不做或只做不想时触发；一次性输出、答案可直接查阅、还没形成假说（先调查）时不触发。 | HughYau/ | 3.8k | — | ~416 | Automated safety check: Pass | MIT | 7 days ago |
| 9 | Compose one publication-grade multi-panel figure. An agent skill from HughYau/AcademicForge. | HughYau/ | 2.6k | — | ~2.5k | Automated safety check: Pass | Apache-2.0 | 1 mo ago |
| 10 | 持久战略：面对长期、复杂、短期不可能速胜的任务，客观评估态势，划分战略防御 / 相持 / 反攻三阶段，判定当前所处阶段，设置阶段转换条件，并在困难阶段仍给出局部进攻点。当任务跨多个会话或多轮迭代、资源暂时不足、或出现"想放弃"与"一把梭"两种情绪时触发；任务能在当前会话完成时不触发。 | HughYau/ | 3.8k | — | ~446 | Automated safety check: Pass | MIT | 7 days ago |
| 11 | Judge and reshape the STORY a paper's figures tell. An agent skill from HughYau/AcademicForge. | HughYau/ | 2.6k | — | ~936 | Automated safety check: Pass | Apache-2.0 | 1 mo ago |
| 12 | 星火燎原：从零起步、资源极少时，先评估客观条件，选定一个能站稳、能复用、能扩展的"根据地"（最小切入点），扎根后再逐步扩张，拒绝四处出击的流寇主义。当启动新项目、做 MVP / pilot、面对宏大目标不知从何下手、或做了很多零散事却没有积累时触发；项目已有稳固基础、只是修改现有系统时不触发。 | HughYau/ | 3.8k | — | ~414 | Automated safety check: Pass | MIT | 7 days ago |
| 13 | 13.Workflows 工作流组合：当一个任务明显需要多件思想武器接力时，提供四种标准组合模式（新项目启动、复杂问题攻坚、方案迭代优化、阶段复盘），定义调用顺序、每步交接物和终止条件。触发信号包括从零启动、疑难攻坚、迭代优化、阶段复盘；单一 skill 就够用时不触发。 | HughYau/ | 3.8k | — | ~542 | Automated safety check: Pass | MIT | 7 days ago |
| 14 | 求是方法论的入口与总原则。在每次新的顶层会话开始时加载一次，用「实事求是」约束全部判断，并只在明确适用时把任务路由到对应的方法论 skill；被派遣执行单一具体任务的子 agent 直接跳过。 | HughYau/ | 3.8k | — | ~393 | Automated safety check: Pass | MIT | 7 days ago |
Questions, answered from the data.
What is the best skill by HughYau?
Concentrate Forces from HughYau/qiushi-skill ranks first of the 14 skills by HughYau listed here, with the highest score: its repository has 3.8k GitHub stars, its SKILL.md loads about 379 tokens and it passes the automated safety check with no findings. Next come Contradiction Analysis and Criticism Self Criticism.
Are HughYau's skills official?
None yet. All 14 skills by HughYau 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.