jiuwenswarm

Must use first when skill capabilities may help complete a task.

Creates, converts, or modifies Swarm Skills — the multi-role (多角色团队) extension of the Skills standard, optionally with an executable SwarmFlow orchestration script. Use when building or refactoring a multi-agent team, generating workflow (工作流/编排) orchestration code, or upgrading a single-agent skill into a collaborating team. Do NOT use for ordinary single-agent skills — use create-skill instead.

Use when initializing or updating structured in-repository project-maintenance docs; exploring existing code; analyzing a full project or repository; documenting complete source symbol coverage, coverage maps, symbol audit maps, or health for every top-level class, top-level function, and class method; summarizing git history; using project-maintainer as maintenance-aware context during a bug fix, feature change, or refactor; or syncing docs after verified code changes.

进阶版日报生成器，支持多数据源采集、工作分析、趋势对比、周报月报聚合

当用户说「从这个链接/URL生成skill」「把这个网页/教程做成skill」「从这个视频提取步骤」时触发。先用 read_file 读取此 SKILL.md，再按步骤用 bash 调用 scripts/ 下的 Python 脚本完成：爬取网页或下载视频 → 下载图片/抽帧 → 生成标准 Skill Markdown 文件。

使用 gitcode-api 命令行工具访问 GitCode REST API。适用于需要查询仓库、Issue、Pull Request、文件内容、用户、组织、搜索结果，或需要获取 Issue 与 Pull Request 模版的场景。还可用于总结仓库最近 commit / PR / issue、责任人、模块、风险或对外接口影响。

Turn SOPs, URLs, or stated intent into an installed skill package. Use when the user asks to generate a skill from a document, link, or workflow. Follow SKILL.md, reference/sop-structure-pipeline.md, and reference/generator-worker-spec.md; finish by promoting the draft into the runtime skills directory (see reference/operator-playbook.md) in the same turn.

运行 JiuwenSwarm Web UI 端到端测试并收集截图、日志、report.md、report.json。用于验证 Todo 和 Cron Web UI 流程、复现浏览器交互问题、选择运行解释器、准备 Playwright 环境，或返回可操作的失败证据时。

Build and maintain a persistent knowledge base (LLM Wiki) using native backend tools. Supports ingesting PDFs, Markdown, and TXT files, and querying or linting the data. Use this whenever the user wants to add, retrieve, or manage their own local knowledge base and documents.

代理执行 AKG 算子任务。先检查固定仓库与分支；若 `~/.akg/check_env.md` 不存在则强制 `FULL_SETUP=true`；忽略所有 `akg_cli` 检查和使用；后端代码生成直接执行 `run_workflow.py --workflow kernelgen`。

为昇腾算子在源码中接入 TRACE_POINT 与 MoeTracing，串通 trace_preprocessor、profiling tensor、point_map.json、 save_profiling_data 与 trace_collector 生成 Chrome trace。强调门禁 G1–G5：全链路预处理与 OPP、profiling 为数据输出最后一位、 整条编译与示例脚本联调、落盘路径在 spawn 前 resolve。遵循函数级粒度与就地扩展，禁止另注册 xxx_profiling 类第二入口， 保持原 Op 与 torch.ops 名称及签名不变。在用户提到算子打点、Profiling、Chrome trace、MoeTracing，或将结论写入本 skill 时读取。

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。

跨会话检索聊天原文（记忆不足时再用）。在回答任何关于历史事件、日期、人物、过去对话的问题时，如果记忆中没有相关信息或不足以回答，则需要使用跨会话检索聊天原文。用 mcp_exec_command 执行 scripts/search_history.py，读 ~/.jiuwenswarm/agent/sessions/*/history.json。支持 channel、session_id、关键词、时间窗。如果搜索结果不足，尝试用不同的关键词再次搜索。

识别代码中可替换为CAM算子的DeepEP算子，基于实际运行参数校验约束，自动完成通信域转换（NCCL->HCCL）、设备适配（CUDA->NPU）及算子替换。

安排延迟重启本 Agent 所在的服务（JiuwenSwarm app）。执行后当前 Agent 进程会被终止并重新启动，当前会话会断开。用于用户要求重启、配置更新需生效、或服务异常需重载时。使用 bash 调用脚本。

以源码为唯一事实来源，系统性核对并更新项目文档，确保内容与实现一致、多语言文档 1:1 对齐、结构完整。

Extract and analyze data from invoices, receipts, bank statements, and financial documents. Categorize expenses, track recurring charges, and generate expense reports. Use when user provides financial PDFs or images.

知识增强型深度检索与深度研究，支持查询规划、信息收集、理解反思、研究报告生成等多 Agent 协同。使用场景：金融分析研报、学术与政策研究、企业级深度搜索等复杂推理任务，可以生成Markdown、Doc和Html格式的研究报告。**每次使用该技能之前都先完整阅读一遍SKILL.md学习技能。**

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

Drive the skvm CLI on behalf of a user to profile models, AOT-compile skills, run skill-assisted tasks, run benchmarks, and manage compiled proposals. Trigger when the user asks to "profile", "aot-compile", "bench", "run a single ad-hoc task with a skill", or asks about skvm proposals. Do NOT trigger for `jit-optimize` or when the user wants to optimize/improve a skill — use the sibling `skvm-jit` skill instead.

Trigger `skvm jit-optimize` with post-task evidence so it generates a reviewable optimization proposal for a skill. Use after finishing a task that was driven by any skill (not just SkVM-compiled ones) when the outcome was a failure, was partial, or the skill's instructions clearly caused confusion or an unnecessary detour. Clean successful runs usually do not need an optimization pass. For general skvm usage (profile/aot-compile/bench/proposals), use the sibling `skvm-general` skill instead.