任务终止 —— 用户主动取消或任务到期时触发，调 `miloco-cli task delete --reason X` 一笔走完 backend（写 task_terminate_log + 删 task，FK CASCADE 同步清 rule / cron / task_record_* 主表/子表），顺序跑返回的 agent_pending 让 openclaw 老通路 external cron 一并下线。

家庭信息首次初始化 / onboarding —— 用户说"初始化家庭""配置家庭成员""首次设置""帮我建家庭档案""onboarding"时激活；收到后端推送的 `[系统事件]` onboarding 消息（全新安装检测）时主动发起；也在身份库成员为空 + 家庭档案为空时由 agent 提议。通过访谈把家庭成员与家庭档案一次性建起来。

Debug a broken SD.Next or Diffusers model integration. Use when a newly added or ported model fails to load, misdetects, crashes during prompt encoding or sampling, or produces incorrect outputs.

NestJS backend development patterns for the RedisInsight API: module structure, services, controllers, DTOs, dependency injection, and error handling. Use when editing any file under redisinsight/api/**, writing or modifying NestJS modules, controllers, services, DTOs, providers, or when the user mentions the backend, API, or NestJS.

Use this skill when updating, reviewing, or creating architecture documentation in the architecture/ directory. This includes after refactors, feature additions, component changes, or when auditing docs for accuracy. Use it any time code changes affect how Cog's internals work -- new packages, changed IPC protocols, modified build pipeline, runtime behavior changes. Also use it proactively when reviewing PRs that touch core systems to check whether the architecture docs need updating.

Use when another PPT Skill needs web search, image search or download, or image generation and the host Agent's equivalent native capability is absent or has failed.

需要把演示 / 幻灯片 / PPT / slides 做成单文件 HTML 动态 deck（动效、跨页过渡、键盘翻页、1280×720）时使用。本 skill 非入口：使用前必须先确认 sn-ppt-entry 与 sn-ppt-story 两个前置 skill 可用，依次执行 entry（建 DECK_DIR / task_pack.json）→ story（生成 outline.md）完成后才可开始；前置缺失或未完成时停止并回报，严禁绕过（如改用生图+手写 HTML 等方式）。

Use when a user asks what SenseNova Team Harness is, wants an introduction or overview, is getting started, or is deciding whether it fits — a self-hosted workspace where people and local AI agents collaborate on conversations, projects, work items, and artifacts. Covers its core concepts (Workspace, Project, Conversation, Agent, WorkItem, Resource, Artifact, Local Computer), main capabilities, how to run it, and the basic usage flow.

Word / PDF / PPT 文档解析与数据分析引擎。覆盖三类文件格式的全量提取、表格数值化、图表理解与跨文档汇总分析。**遇到以下任一情况就主动使用本 skill**：①用户上传或指定了 .docx / .doc / .pdf / .pptx / .ppt 文件并要求分析、提取或统计其中内容；②用户出现触发词：Word分析 / PDF解析 / PPT提取 / 文档分析 / 报告解析 / 幻灯片分析 / 发票提取 / 合同分析 / 文档统计 / 错别字 / 语病 / 字号检查 / 简历分析 / 多文档对比；③任务涉及从文档中提取表格、数值、图表、格式（颜色/高亮/字号）、组织架构、时间线等结构化信息。仅不用于：Excel/CSV 数据分析（使用 sn-da-excel-workflow）、纯图片分析（使用 sn-da-image-caption）。

Excel 数据分析多步编排器。覆盖：(1) 读取多 Sheet Excel 文件并统计行数，(2) 大文件检测（≥10k 行自动 Parquet 优化），(3) 数据清洗（缺失值、文本标准化、无效字符），(4) 条件筛选与分类提取，(5) 跨 Sheet 统计聚合，(6) 导出 Excel/CSV 并提供下载链接。覆盖从数据读取到报告生成全流程，按步骤编排 capability 子 skill。**遇到以下任一情况就主动使用本 skill，不要自行写几行 pandas 就回答**：①用户出现触发词：Excel 分析 / 表格分析 / 数据分析 / 数据清洗 / 数据统计 / 数据筛选 / 数据可视化 / 数据导出 / 汇总统计 / 透视表 / 分组统计 / 交叉分析 / 趋势分析 / 对比分析 / 异常值检测 / 去重 / 缺失值处理 / Excel 报告 / 生成报表 / analyze Excel / data analysis / data cleaning / pivot table；②用户上传或指定了 .xlsx / .xls / .csv 文件并要求分析、清洗、统计或可视化；③任务涉及多 Sheet 读取、条件筛选、分类汇总、图表生成中的任意一项；④用户要求导出带格式的 Excel 报告或下载链接。仅不用于：不涉及表格数据的纯文本处理、图片分析（使用 sn-da-image-caption）、单个公式计算的简单问答。

Reverse JavaScript-based custom DSL/VM interpreters, non-standard WASM-like runtimes, and risk-control engines. Use when analyzing IIFE or switch-based opcode dispatchers, extracting instruction tables, recovering bytecode semantics, capturing VM state at runtime, or reconstructing execution flow.

Use for authorized Android or iOS application reverse engineering and security testing, including APK or IPA analysis, runtime instrumentation, SSL pinning, and platform protection checks.

IDA Pro 逆向分析辅助技能。当用户提到逆向、反编译、分析二进制/PE/ELF/APK/DLL/SO、破解、找密码、漏洞分析、病毒分析、firmware 固件分析，或需要分析 exe/dll/so/elf/macho/sys 等文件时，务必使用此技能。 Ensure to use this skill when the user wants to analyze any binary file, regardless of whether they explicitly mention "IDA" or "reverse engineering". This includes requests like "看看这个exe", "分析这个dll", "帮我破解", "找一下密码", "这个软件怎么注册", etc. Use the bundled scripts (scripts/start.ps1, scripts/open.ps1) for deterministic server management and file opening — do NOT write ad-hoc PowerShell commands for these operations.

Use for authorized cloud, container, and Kubernetes security assessment including metadata SSRF, IAM misconfig, container escape paths, and cluster RBAC review.

Internal downstream skill for ctf-sandbox-orchestrator. CTF-sandbox workflow for kernel attack surface, namespace and cgroup boundaries, container isolation assumptions, syscall paths, and escape primitive verification. Use when the user asks to analyze container-to-host escape paths, kernel exploit prerequisites, namespace crossover, capability misuse, or prove whether an exploit primitive crosses the sandbox boundary. Use only after `$ctf-sandbox-orchestrator` has already established sandbox assumptions and routed here.

Deploy MiniCPM5-2B with vLLM on Huawei Ascend NPU using vLLM-Ascend. Use when the user mentions vLLM-Ascend, Ascend NPU, Huawei Ascend, CANN, torch_npu, davinci devices, or wants an OpenAI-compatible MiniCPM5 server on Ascend hardware.

Generate and track comprehensive due diligence checklists tailored to the target company's sector, deal type, and complexity. Covers all major workstreams with request lists, status tracking, and red flag escalation. Use when kicking off diligence, organizing a data room review, or tracking outstanding items. Triggers on "dd checklist", "due diligence tracker", "diligence request list", "what do we still need", or "data room review".

Structure and draft a Confidential Information Memorandum for sell-side M&A processes. Organizes company information into a professional, investor-ready document with consistent formatting and narrative flow. Use when preparing sell-side materials, drafting a CIM, or organizing company data for a sale process. Triggers on "CIM", "confidential information memorandum", "offering memorandum", "info memo", "draft CIM", or "sell-side materials".

Signals scout for PostHog distributed tracing (APM / OpenTelemetry spans). Watches per-service RED metrics for error-rate and latency regressions, new error signatures, and traffic cliffs.

Finds the most informative session recording linked to an error tracking issue. Use when a user has an error tracking issue ID and wants to watch a replay showing what the user was doing when the error occurred. Ranks linked sessions by recency, activity score, and journey completeness, then summarizes the pre-error context. Replaces blind session picking from potentially hundreds of linked recordings.