Coding Agent 完整工作流——自主理解 codebase、制定修改计划、执行修改、运行验证、失败换路，交付可验证的代码改动。ENGINEER 路由且任务涉及代码修改时触发。
longClaw 运行时体检与诊断。用于检查 skill 不触发、hook 不生效、DEV LOG 异常、state.db 记账异常、memory 检索退化、配置迁移不完整等问题。Use when the user says 体检、自检、诊断、doctor、status、排查 longClaw、skill 不触发、hook 有问题、sidecar 异常、DEV LOG 乱了.
Generate publication-quality academic diagrams, methodology figures, architecture illustrations, and statistical plots from text descriptions using the PaperBanana multi-agent AI pipeline. Also evaluate diagram quality against reference images. Use when: (1) user asks to generate, create, or make a research diagram, methodology figure, system architecture illustration, pipeline diagram, or framework figure, (2) user asks to create a statistical plot, bar chart, or data visualization from CSV/JSON data, (3) user asks to evaluate or score a generated diagram against a reference, (4) user asks to refine or improve a previously generated diagram. NOT for: analyzing existing images, general image generation (non-academic), or chart/graph discussions without explicit generation intent.
记忆增强陪伴——BRO/SIS 回复前自动 spawn MemoryAgent 检索近期记忆，让陪伴有"记得你"的感觉。无需用户触发，CTRL 路由到 BRO/SIS 时自动激活。
面向实现闭环的工程 workflow。用于把“需求/思路/方案”转成可交付改动，强调验收标准、最小改动、立即验证、明确回滚点。冲突优先级最低：若请求同时包含“接入审计”或“修 bug/继续查”等排障闭环意图，应让位于 skill-safety-audit 或 research-execution-protocol。
研究型工程执行协议。用于复杂实现、排障、代码修改、配置修复与实验验证。强调先证据后判断、先验证后宣称完成、失败后系统性换路，不改变全局人格。冲突优先级次高：当请求包含“修 bug/继续查/验证闭环”与“交付落地”混合意图时，优先于 research-build。
分析岗位 JD，给出匹配度评级、核心要求拆解、简历叙事建议和投递优先级。
论文深度解读——Fact/Inference 分离、方法论、SOTA 对比、Reviewer#2 批判、工业落地评估、面试压缩版。