all publishers

openJiuwen-ai

@openjiuwen-ai source repo

137 published skills · page 2 of 2

  1. ▌
    Aet Req Analysis · openjiuwen-ai bundle
    Requirements analysis skill - transforms raw requirements into structured specifications through Socratic dialogue, behavior analysis, and requirement specification design. Use when: (1) requirements are unclear or need decomposition, (2) you need to produce a requirements analysis specification from user input, (3) you need structured functional and non-functional requirements with priority labels, (4) you need acceptance criteria and test case definitions, or any requirements clarification and specification generation tasks.
    8.6k repo stars
  2. ▌
    Ascend Moe Optimizer Trace Analyzer · openjiuwen-ai bundle
    在用户提供 Chrome/Perfetto trace.json、或排查 Ascend 上 MoE/FusedDeepMoe 等算子性能时使用。按 phase、category、core group、tid 统计耗时、overlap、bubble,输出 CSV、Markdown 报告与确定性诊断;可选外部 LLM 扩写分析。默认 phase 映射面向 UMDK FusedDeepMoe,其它 trace 需替换或扩展 config/phase_map.yaml。
    8.6k repo stars
  3. ▌
    Skill Name 1 · openjiuwen-ai
    对 Leader 分派的专业问题进行结构化分析,返回有证据支撑的结论、不确定性和下一步建议。用于专家团 Member 收到需要独立研究、评估或方案建议的子任务时。
    8.6k repo stars
  4. ▌
    Devflow Fix · openjiuwen-ai bundle
    Devflow Fix
    8.6k repo stars
  5. ▌
    Devflow Tdd · openjiuwen-ai bundle
    在实现任何功能或修复任何缺陷、即将编写实现代码时使用;设计确认后的整个实现期都适用。强制测试先行的 RED→GREEN→REFACTOR 循环。不用于规格编写、设计决策或纯文档修改。
    8.6k repo stars
  6. ▌
    Devflow Ship · openjiuwen-ai bundle
    在工作项全部任务完成、测试与代码评审闭环后收尾时使用:对照 Definition of Done 核验完成证据、把已确认的规格与设计沉淀为长期文档资产(promotion)、写 closeout 记录。不用于实现、评审或修复。
    8.6k repo stars
  7. ▌
    Using Devflow · openjiuwen-ai bundle
    DevFlow 工作流的入口。在以下情况使用:开始一个新的开发任务、不确定当前该做规格/设计/实现中的哪一步、需要从已有工件恢复进度、或用户提到 DevFlow / 规范驱动开发 / 高质量开发流程时。
    8.6k repo stars
  8. ▌
    Devflow Design · openjiuwen-ai bundle
    在规格确认后、写代码前做软件设计时使用;也在设计评审被打回、或实现中发现模块边界/接口契约/错误处理需要重新设计时使用。涵盖模块划分、接口契约、错误模型、数据所有权、方案取舍与测试设计。
    8.6k repo stars
  9. ▌
    Devflow Review · openjiuwen-ai bundle
    在规格、设计、测试或代码需要独立评审时使用:阶段产物完成后的把关、人要求 review、或对既有产物做专项检查时。评审必须由作者之外的独立上下文执行,产出 findings 与 verdict。
    8.6k repo stars
  10. ▌
    Refactor Guide · openjiuwen-ai bundle
    Project Refactoring Standards and Process Governance
    8.6k repo stars
  11. ▌
    Workflow Guide · openjiuwen-ai bundle
    Workflow Application Building Guide
    8.6k repo stars
  12. ▌
    Caveman Install · openjiuwen-ai
    Install and configure the caveman plugin for Claude Code on the current machine. Trigger when user says "install caveman", "setup caveman", "配置 caveman", "安装 caveman", or when caveman hooks/statusline are missing from settings.json. Also applies when user wants to verify, troubleshoot, or uninstall caveman. Not applicable to: using caveman mode (that's the built-in caveman skill), general Claude Code configuration unrelated to caveman.
    8.6k repo stars
  13. ▌
    Devflow Specify · openjiuwen-ai bundle
    在开始一个新的开发工作项(功能、变更、需要正式规格的缺陷)时使用,把一句话需求或散乱输入澄清成可测试的规格;也在规格评审被打回需要修订时使用。不用于产品方向决策或实现设计。
    8.6k repo stars
  14. ▌
    Agent Team Guide · openjiuwen-ai bundle
    Agent Team Quick Build Guide
    8.6k repo stars
  15. ▌
    Jvm Troubleshoot · openjiuwen-ai bundle
    JVM Production Troubleshooting Handbook
    8.6k repo stars
  16. ▌
    Devflow Clean Code · openjiuwen-ai bundle
    在编写、修改或重构任何实现代码与测试代码时使用;TDD implementer 进入 GREEN/REFACTOR 和返回 clean_code_check 时必须作为通用基准加载。也在代码评审需要内在质量判据,或发现命名混乱、函数过长、嵌套过深、直接变异状态、类型/契约含混、错误处理散乱等代码异味时使用。语言无关的整洁代码标准;语言细则见对应的 <language>-coding-standards 技能,领域或框架规范按各自 description 叠加在本技能之上,不能替代本技能。
    8.6k repo stars
  17. ▌
    Performance Tuning · openjiuwen-ai bundle
    Java Performance Tuning Guide (JDK 17 baseline)
    8.6k repo stars
  18. ▌
    Team Skill Creator · openjiuwen-ai
    Team Skill Generator
    8.6k repo stars
  19. ▌
    Coding Standard Full · openjiuwen-ai bundle
    华为 CodeArts Check Java 编程规则集(144条规则,按分类拆分,按需加载)。在用户编写或修改 Java 代码、做 Code Review、要求检查代码规范时主动应用。覆盖命名、异常、日志、并发、格式化、安全等全部规则。涉及关键词:编程规范、代码规范、coding standard、code convention、规范检查、代码风格、Code Review、华为规则、CodeArts Check、G.FMT、G.NAM、G.ERR。不适用于:只问 Java 语法概念、非 Java 代码、调试运行错误、配置部署问题。
    8.6k repo stars
  20. ▌
    Disk Analyzer · openjiuwen-ai
    Disk analyzer skill that runs shell commands in sandbox environment
    8.6k repo stars
  21. ▌
    Data Processor · openjiuwen-ai
    Data processor skill that installs Python dependencies in sandbox and runs numerical analysis
    8.6k repo stars
  22. ▌
    Skill 01 · openjiuwen-ai
    ---
    8.6k repo stars
  23. ▌
    Skill 02 · openjiuwen-ai
    ---
    8.6k repo stars
  24. ▌
    Skill 03 · openjiuwen-ai
    ---
    8.6k repo stars
  25. ▌
    Skill 04 · openjiuwen-ai
    ---
    8.6k repo stars
  26. ▌
    Skill 05 · openjiuwen-ai
    ---
    8.6k repo stars
  27. ▌
    Team Skill Name · openjiuwen-ai bundle
    <Team Name>
    8.6k repo stars
  28. ▌
    Investment Analysis Team · openjiuwen-ai bundle
    8-role debate-pattern investment analysis team with direct peer-to-peer debate for balanced decisions. Use when analyzing a security for investment decision with adversarial debate. Do NOT use for single-perspective analysis or quick price checks.
    8.6k repo stars
  29. ▌
    Plan · openjiuwen-ai
    规划规范 — 将评估结果收敛为结构化任务计划
    8.6k repo stars
  30. ▌
    Assess · openjiuwen-ai
    评估方法论 — 指导 agent 如何系统性评估代码库状态
    8.6k repo stars
  31. ▌
    Evolve · openjiuwen-ai
    已并入 implement skill,请勿新用
    8.6k repo stars
  32. ▌
    Implement · openjiuwen-ai
    实现阶段主操作手册 — 指导 agent 完成改码与局部验证,并把提交留给独立 commit phase
    8.6k repo stars
  33. ▌
    Dev Test Parallel · openjiuwen-ai bundle
    Dev-Test Parallel Team
    8.6k repo stars
  34. ▌
    Skills · openjiuwen-ai bundle
    com.openjiuwen.core.single_agent.skills.Skill
    8.6k repo stars
  35. ▌
    Select Pipeline · openjiuwen-ai
    流水线选择规范 — 根据任务和事实选择最合适的 pipeline
    8.6k repo stars
  36. ▌
    Skill Evaluation · openjiuwen-ai
    Evaluate another skill by inspecting its SKILL.md, referenced assets, and runnable helpers, then write a concise audit report plus a machine-readable score summary. Use when the caller asks to evaluate a skill, assess its readiness, or review quality/safety/testability. Do NOT use when the task is to create a new skill from scratch.
    8.6k repo stars
  37. ▌
    Agent Memory1 0 Skill · openjiuwen-ai bundle
    通过 HTTP API 调用 agent-memory1.0 记忆服务,召回与写入历史处理记忆
    8.6k repo stars