Skills — le catalogue de compétences de vos agents

备份恢复管理器，定时备份关键数据（MEMORY.md、训练数据、模型权重、配置文件），支持快速恢复和灾难演练。 增强方法(v1.1): SHA256重复检测(避免备份冗余)、感知哈希检测相似图片、文件版本管理(保留最近3个版本+一键恢复)。 触发词: 备份数据/恢复数据/灾难演练/检查备份 不触发: 日志分析/性能监控/模型训练 (DEF-56激活版)

从小宇宙下载播客音频与节目说明。从小宇宙(xiaoyuzhoufm。com)下载播客音频和Show Notes。自动转换为MP3格式（兼容Sanag、小游等骨传导蓝牙耳机、水下游泳时离线播放）。支持多种输入格式,输出结构化结果,适用于独立开发者与一人公司效率提升。Use。Use when 需要代码生成、编程辅助、调试测试、开发部署时使用。不适用于无明确技术栈的模糊需求。 when 需要代码生成、编程辅助、调试测试、开发部署时使用。不适用于无技术栈的通用场景。

从小宇宙下载播客音频与节目说明。从小宇宙(xiaoyuzhoufm。com)下载播客音频和Show Notes。自动转换为MP3格式（兼容Sanag、小游等骨传导蓝牙耳机、水下游泳时离线播放）。支持多种输入格式,输出结构化结果,适用于独立开发者与一人公司效率提升。Use。Use when 需要代码生成、编程辅助、调试测试、开发部署时使用。不适用于无明确技术栈的模糊需求。 when 需要代码生成、编程辅助、调试测试、开发部署时使用。不适用于无技术栈的通用场景。

企业级钉钉日历管理工具，支持批量操作、组织架构集成、会议室资源优化及团队协作，提升工作效率与自动化水平。

企业级飞书日历管理，支持共享日历、多人协作、跨时区同步、智能调度及批量操作，提升团队日程管理效率。

Use when a user asks what the Alibaba Cloud Remote Skills Connector can do, which hosted Alibaba Cloud skills are currently available, or requests Alibaba Cloud capability onboarding; wants to inspect, query, diagnose, audit, create, deploy, configure, update, resize, restart, repair, restore, or delete Alibaba Cloud (阿里云/Aliyun) resources; uses Chinese triggers such as 查询, 诊断, 巡检, 创建, 删除, 更新, 升配, 扩缩容, 重启, and 修复; continues an existing AgentHub task; or troubleshoots this connector's discovery/authentication—even without a product name. Exclude other clouds, general knowledge/architecture/pric

bash prefix: export LJ_SKILL_DIR="${LJ_SKILL_DIR:-$HOME/.qoder/skills/alibabacloud-lingjun-node-diagnose}" && source "$LJ_SKILL_DIR/lib/lj_init.sh" i18n: detect language each turn (CJK ratio ≥ 0.30 → LJ_LANG=zh, else en); inject LJ_LANG=zh|en prefix before source. Intelligent diagnosis for Alibaba Cloud Lingjun (regular & hyper) compute nodes: submit diagnostic tasks (BasicCheck / NodeHardwareCheck / CheckByAiJobLogs), produce structured diagnostic reports, propose repair plans (reboot / reimage / stop / report-node-status), track fault reports (list-fault-reports / describe-fault-report / sto

多层记忆系统，提供分层存储、按需检索、持久化的完整方法论。触发词：记忆系统、长期记忆、上下文管理、知识管理、信息存储、meta-skill-system

强大的屏幕理解与控制，并创建可维护流程

Route Remotion tasks to the right workflow

Plan daily meals and workouts from a user's age and health profile with customizable ingredients, then schedule localized plans via OpenClaw automations.

Planificación y ejecución de campañas de lanzamiento completas para comunidades Skool, cursos, productos digitales o servicios con la metodología F100K. Usar cuando una creadora va a lanzar algo nuevo o relanzar algo existente y necesita: posicionamiento, guiones de reels, secuencia de historias, emails, landing copy y calendario. Orquesta los demás skills F100K para producir todo el arsenal de lanzamiento desde un solo brief.

Query all Huawei Cloud resources under a tenant across all regions and display their inter-resource relationships in grouped tables. Aggregates ECS / BMS / RDS / EVS / DCS / CCE / VPC / Subnet / EIP / ELB / NAT / DNS resources in a single run, builds an in-memory relationship index (network topology, storage mount, dependency), and outputs results as plain-text tables grouped by resource type. Read-only — never creates, modifies, or deletes any resource. Use this skill when the user needs a full resource inventory, resource relationship audit, network topology overview, or cross-region resourc

Use this skill whenever the user needs to operate a redis cache or a rabbitmq broker — a one-shot overview, redis memory posture (used vs maxmemory, eviction policy, fragmentation), SLOWLOG and a SCAN-budgeted big-key sample (never KEYS *), connected clients, CONFIG get/set, rabbitmq queues with backlog depth, connections/channels, policies and node watermark alarms, four flagship RCAs (redis memory pressure, redis latency/slowlog, rabbitmq queue backlog, connection churn on both platforms), and governed writes (set a config parameter, kill a client, declare/purge/delete a queue, set/delete a

Use when the user asks to query Volcengine CloudTrail audit logs, investigate login or resource operations, or manage CloudTrail trails and backfill delivery tasks. Trigger on 操作审计, 审计日志, CloudTrail, cloud_trail, trail, 跟踪, 历史补投, or backfill in a Volcengine context. Audit queries are read-only; trail and backfill mutations require an explicit preview and confirmation.

Use Atoll for project, issue, goal, KPI, initiative, milestone, artifact, PRD, implementation plan, comment, dependency, runner, and workflow operations. Activate for Atoll planning, execution, project-management, local-runner, or integration requests.

怎样开会——从《怎样开会》（任仲然著，党建读物出版社）提炼的会议方法论技能库。当用户要筹备、主持、讲话、写纪要、抓落实等任何会议相关任务（工作部署会、决策会、座谈会、现场会、视频会、学习会），或问及会议规则、议事规则、讲话稿写法、会议精神落实时使用。Use when planning, chairing, speaking at, or following up on any meeting, or referencing the book's frameworks.

Use this skill whenever the user needs to operate an XCP-ng virtualization fleet through Xen Orchestra — a one-shot fleet health overview; VMs (list/get/RRD stats), hosts, pools, storage repositories (SRs) and VDIs, VM snapshots, backup jobs and run logs, XO tasks; four RCA analyses (VM health, SR usage, backup-job failures, pool patch & HA posture); and governed writes (VM start/stop/reboot/migrate, snapshot create/delete/revert, SR rescan). Always use this skill for "xcp-ng vm", "xen orchestra", "xo backup failed", "sr full", "orphaned vdi", "xcp-ng snapshot", "migrate vm to another host", "

Pharmaceutical-manufacturing edition of iaiops — GMP drug/biologics plants as a distinct vertical from generic buildings and municipal water. BACnet/IP BMS+EMS (cleanroom pressure cascade, temperature/RH), Modbus (PW/WFI skids, stills, EDI, analysers), HART-IP (conductivity / TOC / level transmitters), OPC-UA (DCS, bioreactors, plant SCADA), plus the cross-protocol brain. Three signature checks: cleanroom_pressure_cascade (EU GMP Annex 1 cascade, door by door), cleanroom_particle_check and pharma_water_check (USP <645> stage-1 procedure). Use when the task mentions pharma, 制药, 药厂, GMP, cleanro

Coordinate multi-step detached tasks as one durable TaskFlow job with owner context, state, waits, and child tasks.

Condense scattered chat messages, notes, or logs into a concise structured daily standup summary. Use when: (1) asked to summarize a team's daily standup from raw chat logs or messages, (2) converting unstructured notes into a standup format (What I did / What I'll do / Blockers), (3) preparing a standup report from multiple sources of team activity, (4) generating a daily progress update for agile/standup meetings.

Generate a daily digest summarizing workspace activity, memory entries, and completed tasks. Use at end of day to produce a readable summary of what happened in the workspace.

讨论 ESP（职业用途或专门用途英语）教材设计，生成或修改需求分析、教材结构和编写方案。教师询问设计问题或要求生成、重写、按建议修改上述成果时使用；成果以 Tiptap JSON 交付，不用于完整教材正文编写。

Internal NVFLARE conversion references and templates. Use only when another NVFLARE skill directs you to a shared workflow, policy, or asset.