Loading...
Loading...
Found 63 Skills
Integrate and unbind OpenViking long-term memory with coding agents running in bwrap sandboxes. Supports 7 agents (CodeArts CLI, OpenCode, OpenClaw, Hermes, JiuwenSwarm, KimiCode, DeepSeek Harness) via their native mechanism — MCP or HTTP memory provider. Both integration and unbinding require explicit user authorization. Use this skill when the user wants to: (1) integrate OpenViking memory into a coding agent, (2) unbind OpenViking from a coding agent, (3) check the integration status of all agents, (4) verify the OpenViking MCP endpoint, (5) rebuild the OpenClaw sandbox to apply template changes. Trigger words: "OpenViking integration", "agent memory binding", "MCP setup", "OpenViking MCP", "integrate OpenViking", "unbind OpenViking", "记忆集成", "记忆解绑", "OpenViking 集成", "OpenViking 解绑", "agent long-term memory", "context database".
Migrate vision/detection/segmentation small models to Ascend NPU, covering the full workflow: model structure analysis, migration verification, performance profiling, and optimization. Based on torch_npu and msprof Use this skill when the user wants to: (1) migrate encoder-only models like ResNet, YOLO, UNet to Ascend NPU, (2) analyze model structure for migration feasibility, (3) verify model inference on NPU, (4) identify performance bottlenecks and get optimization suggestions Trigger: user mentions "migrate", "migration", "Ascend", "NPU", "YOLO", "ResNet", "encoder-only", "detection", "segmentation", "adaptation", "adapt", "迁移", "昇腾迁移", "小模型", "适配", "昇腾适配", "GPU迁移", "NPU适配", "适配NPU", "适配昇腾"
Comprehensive SQL statement checking for Apache Doris (based on Doris 3.1.4 Nereids ANTLR4 grammar), supporting two check modes: 1. Syntax Check - Keyword validation, statement structure verification, clause completeness, Doris-specific syntax compatibility (DISTRIBUTED BY, PARTITION BY, ENGINE, DUPLICATE/AGGREGATE/UNIQUE KEY, INSERT OVERWRITE, LOAD, EXPORT, MTMV, BACKUP/RESTORE etc.) 2. Specification Check - Object design standards, data operation standards, naming conventions based on Apache Doris development best practices. Built-in custom Doris SQL tokenizer (504 keywords from DorisLexer.g4) and recursive descent parser supporting 100+ Doris statement types. Applicable when users need SQL quality review, syntax validation, or specification compliance checking for Apache Doris SQL (versions 2.1.x / 3.0.x / 3.1.x / 4.x). 触发词："Doris SQL检查"、"Doris SQL规范"、"Doris SQL审计"、"Doris SQL语法"、"检查Doris SQL"、"Doris SQL review"
Calculate MFU (Machine FLOP Utilization) for operators like matmul/GEMM/FlashAttention on Ascend NPU, providing clear formulas and derivation process Use this skill when the user wants to: (1) calculate MFU for matrix operations, (2) analyze operator performance efficiency, (3) understand hardware utilization, (4) optimize operator implementation Trigger: user mentions "MFU", "machine flop utilization", "operator FLOPs", "matmul performance", "GEMM efficiency", "Ascend MFU", "算子MFU", "算力利用率", "矩阵乘效率", "GEMM性能", "FlashAttention性能"
Analyze CDN domain traffic anomalies using hcloud CLI. Query billing mode and traffic/bandwidth metrics for specified domains, compare against 3-month baseline and absolute thresholds to identify traffic theft or abuse. Use this skill when the user wants to: (1) analyze CDN domain traffic anomalies, (2) check if a domain has traffic theft or abuse, (3) query CDN billing mode and traffic/bandwidth metrics, (4) compare current traffic against historical baseline. Triggers include: CDN流量异常, 流量异常分析, 域名流量分析, 流量盗刷, 带宽异常, 95带宽异常, 流量突增, 流量对比, 基准分析, traffic anomaly, bandwidth anomaly, CDN traffic analysis, traffic theft detection, baseline comparison
Analyze candidate models before adapter implementation. Determine model implementation source (transformers or model-local), structural features, layer-by-layer loading requirements, and MoE fused weight risks. Use this skill when the user wants to: (1) assess model adaptation feasibility before creating msModelSlim adapters, (2) analyze model structure and type classification, (3) evaluate MoE compatibility for quantization. Trigger: user mentions "model analysis", "msModelSlim", "adapter", "transformers", "MoE", "layer-by-layer", "model assessment", "feasibility", "模型分析", "适配可行性", "模型评估", "MoE分析"
Create basic Transformers model adapters for msModelSlim. Implements required interfaces and completes a four-step verification workflow: generate test model -> full fallback quantization -> weight verification -> quantization description validation. Use this skill when the user wants to: (1) create msModelSlim adapters for decoder-only LLM, (2) adapt understanding VLM text backbones for quantization, (3) implement W8A8/W4A16 quantization workflow for new models. Trigger: user mentions "msModelSlim", "adapter", "model adapter","quantization", "W8A8","W4A16", "transformers", "LLM", "VLM", "adapter creation", "适配器","模型适配", "量化", "模型适配器", "LLM量化"
Develop and optimize custom operators using AscendC programming language. Analyze operator performance bottlenecks and conduct optimization validation. Based on AscendC and CANN toolkit Use this skill when the user wants to: (1) optimize performance-critical operators on Ascend NPU, (2) develop custom operators for specific workloads, (3) improve model inference performance through operator optimization Trigger: user mentions "AscendC", "operator optimization", "custom operator", "performance", "NPU optimization", "Ascend operator", "算子优化", "自定义算子", "算子开发", "AscendC算子", "性能优化"
Search, discover, browse and install AI Gallery Agent skills via natural language. Triggers include: "AI Gallery", "AI Gallery有什么skill", "有什么skill", "AI Gallery相关skill", "AI Gallery agent skill 市场", "AI Gallery skill类目", "skill 市场", "搜索AI Gallery skill", "安装skill", "订阅skill", "有没有XX skill", "有没有XX的能力", "帮我找 XX skill", "帮我找一个能XX的工具", "我想扩展功能", "介绍 XX Skill 内容", "XX Skill 具体做什么", "explore AI Gallery skills", "show AI Gallery skill categories", "does an AI Gallery skill exist for...", "which AI Gallery skills exist", "search skill", "find skill".
Huawei Ascend NPU natural language management skill, supporting both local direct connection and SSH remote modes. Provides comprehensive npu-smi command capabilities including device queries, configuration management, firmware upgrade, vNPU virtualization, certificate management, and compute power testing (FLOPS). Enables remote management and monitoring of Ascend NPU devices with real-time metrics tracking. Use this skill when the user wants to: (1) query NPU device status and health, (2) monitor temperature, power, memory/HBM utilization, (3) configure ECC settings and fan modes, (4) perform firmware upgrades, (5) manage vNPU virtualization, (6) run compute power tests, (7) check certificate information. Trigger: user mentionsnpu', 'ascend', 'NPU', 'Ascend', 'temperature', 'power', 'HBM', 'firmware', 'upgrade', 'vNPU', 'virtualization', 'certificate', 'FLOPS', 'compute', 'health', 'memory', 'utilization', 'ECC', 'fan', '昇腾', '昇腾卡', '昇腾状态', '显存', '算力', '设备查询', 'NPU监控'"
指导在华为云 ModelArts 推理平台通过 vLLM-Ascend 推理框架部署开源大语言模型(GLM/Qwen/DeepSeek/Llama 等)为昇腾 NPU 在线推理服务的完整流程。覆盖:确认模型后按 vllm-ascend 社区文档与用户确认部署形式(单节点/多节点/PD分离/PD共置 4 种形式,统一单部署单元承载),从 HuggingFace/ModelScope 下载模型权重并上传 OBS、从 Quay.io 拉取 vllm-ascend 镜像并推送 SWR、按确认的部署形式选用专用脚本模板(单节点/多节点/PD/PD共置 四套,脚本内不做部署形式运行时分支)生成启动/探针/角色识别脚本并上传 OBS、按 ModelArts 平台适配要点(端口 8080、OBS 挂载、bash 数组、探针命令检查、超节点亲和组)通过新版在线服务部署(二选一: 方式A 调用 CreateInferService API(POST /v2/{project_id}/services)自动部署 / 方式B 在 ModelArts 控制台按一步步点击指导手动部署;不再创建 AI 应用——该模块已废弃)、通过 OpenAI 兼容 API 调用验证。Triggers include: "ModelArts 部署大模型/开源模型", "vllm-ascend", "昇腾 NPU 推理", "HuggingFace/ModelScope 模型上云", "OBS/SWR 镜像迁移", "大模型在线服务", "多机部署", "多副本部署", "PD 分离部署", "PD 共置部署", "超节点亲和组", "新版在线服务", "CreateInferService", "控制台手动部署在线服务"。当用户提到以上任一场景时都应使用本技能,即使没有明确说出'部署'二字。
Manage CloudRobo model training tasks and simulation reinforcement learning (SimRL) tasks — create pretrain (TRAIN_FROM_SCRATCH) and finetune (MODEL_TUNING) tasks with FFT/SFT/LORA/QLORA/DEEPSPEED methods; manage the full task lifecycle (create/read/update/delete/stop/restart/resume/draft); save and resubmit draft configs; count tasks by status; monitor execution stages, resource usage, training logs, signed URLs, and events; diagnose failures. SimRL tasks (simulation reinforcement learning) are managed via the same CLI with a --sim-rl flag and cover the same CRUD + lifecycle + monitoring surface (except resume, which is train-only). Triggers include: model training, fine-tuning, pretraining, training task, training stages, resource usage, training logs, training events, draft task, restart training, stop training, resume training, task stats, simulation reinforcement learning, SimRL, 仿真强化学习, 模型训练, 模型微调, 训练任务, 训练阶段, 资源使用, 训练日志, 训练事件, 草稿任务, 重启训练, 克隆训练, 停止训练, 续训训练, 任务统计.