DevOps & Infra

ndpvt-web Skill

Agentic system for answering questions about semi-structured tables using tree-based structural modeling and multi-step agent reasoning. Use when: 'analyze this spreadsheet and answer questions', 'parse this complex table with merged cells', 'extract data from a semi-structured table', 'answer questions about this financial/HR table', 'convert messy table to structured format', 'build a table QA pipeline'.

whyzsm Bundle

CloudBase CLI (tcb, 云开发CLI, Tencent CloudBase命令行) resource management skill. This skill should be used when users need to deploy cloud functions, manage CloudRun apps, upload files to storage, query NoSQL/MySQL databases, deploy static hosting, set access permissions, or configure CORS/domains/routing via tcb commands. Also use for CI/CD pipeline scripting, batch operations, terminal-based CloudBase management, or when the user prefers CLI over SDK/MCP.

whyzsm Bundle

AIOps-style one-click inspection skill for CloudBase resources. Use this skill when users need to diagnose errors, check resource health, inspect logs, or run a comprehensive health check across cloud functions, CloudRun services, databases, and other CloudBase resources.

whyzsm Bundle

Use this skill for Node.js backend AI via @cloudbase/node-sdk (>=3.16.0) — cloud functions, CloudRun, Express, Koa, NestJS, serverless APIs, scheduled jobs, LLM proxies. Only SDK supporting image generation (ai.createImageModel + generateImage). Text models via ai.createModel with groups cloudbase, hunyuan-exp, or custom-*. Model IDs (deepseek-v4-flash, deepseek-v3.2, hunyuan-2.0-instruct-20251111, glm-5, kimi-k2.6) go in the model field of generateText/streamText. MUST run two-step preflight before code — see body. Keywords: backend, 云函数, 云托管, serverless, LLM proxy, agent orchestration, generateText, streamText, generateImage, createModel, hunyuan-image, Token Credits, TokenHub, Hunyuan, DeepSeek, GLM, Kimi, MiniMax. NOT for browser/Web (use ai-model-web) or Mini Program (use ai-model-wechat).

whyzsm Bundle

Use this skill for WeChat Mini Program AI via wx.cloud.extend.AI (小程序, 企业微信小程序, wx.cloud apps). Features generateText and streamText with callbacks (onText, onEvent, onFinish). Models via wx.cloud.extend.AI.createModel with groups hunyuan-exp (小程序成长计划), cloudbase (main managed), or custom-*. Model IDs (deepseek-v4-flash, deepseek-v3.2, hunyuan-2.0-instruct-20251111, glm-5, kimi-k2.6) go in the data wrapper model field. API differs from JS/Node SDK — streamText needs data wrapper, generateText returns raw response. MUST run two-step preflight before code — see body. Keywords: Mini Program AI, wx.cloud.extend.AI, 小程序成长计划, ai_miniprogram_inspire_plan, Token Credits 资源包, generateText, streamText, createModel, hunyuan-exp, TokenHub, Hunyuan, DeepSeek, GLM, Kimi, MiniMax. NOT for browser/Web (use ai-model-web), Node.js backend (use ai-model-nodejs), or image generation (use ai-model-nodejs).

whyzsm Bundle

CloudBase function runtime guide for building, deploying, and debugging your own Event Functions or HTTP Functions. This skill should be used when users need application runtime code on CloudBase, not when they are merely calling CloudBase official platform APIs.

whyzsm Bundle

Build and deploy AI agents with CloudBase Agent SDK (TypeScript & Python). Implements the AG-UI protocol for streaming agent-UI communication. Use when deploying agent servers, using LangGraph/LangChain/CrewAI adapters, building custom adapters, understanding AG-UI protocol events, or building web/mini-program UI clients. Supports both TypeScript (@cloudbase/agent-server) and Python (cloudbase-agent-server via FastAPI).

whyzsm Bundle

Complete guide for CloudBase cloud storage using Web SDK (@cloudbase/js-sdk) - upload, download, temporary URLs, file management, and best practices.

whyzsm Bundle

Unified skill for ALL Tencent Cloud operations via tccli. Supersedes any single-product skills (e.g. Lighthouse-only). Covers: Lighthouse, CVM, CBS, COS, VPC, DNSPod, SSL, CAM, Monitor, TAT, Domain, CloudAudit. Load when user mentions: 腾讯云, 轻量服务器, Lighthouse, CVM, 安全组, 域名, DNS, SSL, 云硬盘, 部署, 监控, CAM, instance ID, whoami, tccli, 防火墙, 快照, 镜像, 流量包, 建站, 安全检查, OpenClaw, 退出登录. Use for: 查看/创建/管理云资源, 安全巡检, 资源巡检, 应用部署, 建站, 云硬盘挂载, 证书检查, 登录/退出/切换账号. [INSTANCE ID] For instance ID / whoami / which machine: read SKILL.md for whoami.sh — the ONLY correct method. Do NOT use tccli or curl metadata directly. For all operations, read SKILL.md first. Biases: queries over modifications, confirm before execution, use tccli --help for latest params over pretrained knowledge.

whyzsm Bundle

Build reliable, fast E2E test suites with Playwright and Cypress. Critical user journey coverage, flaky test elimination, CI/CD integration.

whyzsm Bundle

工程实践专家。用于基于 Google 工程师的 Agent Skills，覆盖规范驱动开发、代码评审、CI/CD 发布。来源于 WorkBuddy 技术卡片，并转换为 Codex 可安装的专家入口格式。

whyzsm Skill

CloudBase WeChat Mini Program native authentication guide. This skill should be used when users need mini program identity handling, OPENID/UNIONID access, or `wx.cloud` auth behavior in projects where login is native and automatic.

whyzsm Bundle

腾讯云技术支持专家团。用于 CloudQ 多云治理、AndonQ 工单与智能问答、MigraQ 迁移支持、云运维排障和架构可视化。来源于 WorkBuddy 技术工程卡片，并转换为 Codex 可安装的专家团入口格式。

whyzsm Bundle

腾讯云上云迁移专家团。用于产品选型、Landing Zone、目标架构、迁移计划、交付实施、运维交接、FDE 部署和回滚准备。来源于 WorkBuddy 技术工程卡片，并转换为 Codex 可安装的专家团入口格式。

whyzsm Bundle

开发流水线编排专家。用于编排开发流水线，拆解为测试驱动的细粒度任务，子代理逐任务实现并双重评审。来源于 WorkBuddy 技术卡片，并转换为 Codex 可安装的专家入口格式。

jesusgarciafernandez Bundle

La Seguridad en la Nube y Ciber-resiliencia (v2.0) es la competencia de "Asegurar que tu castillo digital es inexpugnable pero accesible para los tuyos". Úsala para tareas de Desarrollo y Tecnología: cloud-security, cybersecurity, devsecops, identity-management, iam, data-protection.

jesusgarciafernandez Bundle

La Computación sin Servidor y Arquitecturas de Eventos (v2.0) es la competencia de "Pagar solo por lo que ejecutas". Úsala para tareas de Desarrollo y Tecnología: serverless, aws-lambda, cloud-functions, event-driven, scalability, fass.

jesusgarciafernandez Bundle

La Migración Ágil de Datos (v2.0) es la competencia técnica de trasladar estructuras de datos desde sistemas locales limitados (Microsoft Access, Excel) hacia bases de datos relacionales en la nube (PostgreSQL, MySQL, Supabase). No es solo "copiar y pegar"; es Re-ingeniería de Datos para la Nube. Úsala para tareas de Datos y Analítica: data-migration, cloud-databases, legacy-systems, access-to-sql, excel-to-cloud, database-architecture.

jesusgarciafernandez Bundle

La Gestión de Dependencias y SBOM (v2.0) es la competencia de "Saber qué hay dentro de tu software". Úsala para tareas de Desarrollo y Tecnología: dependency-management, sbom, supply-chain-security, package-manager, npm, pip.

jesusgarciafernandez Bundle

La Orquestación de Sistemas y Kubernetes (v2.0) es la competencia de "Ser el director de una orquesta de miles de servidores". Úsala para tareas de Desarrollo y Tecnología: kubernetes, orchestration, k8s, cloud-native, auto-scaling, high-availability.

jesusgarciafernandez Bundle

El Liderazgo en Ventas (v2.0) es la disciplina de orquestar equipos comerciales de alto rendimiento mediante la combinación de inteligencia emocional y rigor analítico. No es ser el "mejor cerrador"; es Ingeniería del Rendimiento Humano en Ventas. Úsala para tareas de Ventas y Comercio Electrónico: sales-leadership, sales-enablement, sales-pipeline, revenue-operations, sales-coaching, incentive-design.

jesusgarciafernandez Bundle

La Computación en el Borde y Redes de Baja Latencia (v2.0) es la competencia de "Procesar los datos lo más cerca posible del problema o del usuario". Úsala para tareas de Desarrollo y Tecnología: edge-computing, low-latency, cdn, serverless-edge, 5g, real-time-data.

ndpvt-web Skill

Extract structured key information from document images using schema-guided prompting for LMMs. Builds KIE pipelines that output normalized JSON from receipts, invoices, forms, medical records, tax documents, and more. Trigger phrases: 'extract fields from this document image', 'build a document KIE pipeline', 'parse invoice fields into JSON', 'extract key information from scanned documents', 'structured data extraction from document photos', 'benchmark document extraction accuracy'

ndpvt-web Skill

Implement Vista-style scene-aware streaming video processing pipelines with dynamic segmentation, hierarchical compression, and selective recall. Use when building video QA systems, streaming video analysis, real-time surveillance analytics, or any application that processes continuous video and must answer queries against an ever-growing visual context. Trigger phrases: - "streaming video question answering" - "scene-aware video segmentation and compression" - "build a video stream processing pipeline with memory management" - "real-time video QA with GPU/CPU memory offloading" - "long-form video understanding with selective recall" - "process continuous video frames and answer queries efficiently"

ndpvt-web Skill

Build multi-agent LLM negotiation systems where buyer and seller agents reach deals through natural language. Use when asked to 'build a negotiation system', 'create buyer-seller agents', 'implement price bargaining with LLMs', 'simulate a marketplace with AI agents', 'design an agentic commerce pipeline', or 'build a multi-round trading framework'.

ndpvt-web Skill

Implement AlienLM-style API-boundary privacy layers that protect sensitive text sent to black-box LLM APIs using vocabulary-scale bijective token remapping. Use when: 'add privacy layer to LLM API calls', 'protect prompts sent to external API', 'alienize text for API privacy', 'build token-level encryption for LLM pipeline', 'implement bijective vocabulary mapping', 'privacy-preserving LLM deployment'.

ndpvt-web Skill

Build multi-agent AI systems for high-throughput scientific workflows with metacognitive self-assessment. Implements the Polymer Research Lifecycle (PRL) architecture: a Planner Agent decomposes complex scientific tasks into subtasks assigned to specialized domain agents (Research, Characterization, ML Model, Safety, Synthesis, Execution, Reporting), which produce consensus predictions with uncertainty estimates and continuously self-optimize via three-layer metacognitive reflection. Trigger phrases: - "Build a multi-agent pipeline for materials property prediction" - "Create a high-throughput screening system with agent consensus" - "Implement metacognitive self-assessment for an agent swarm" - "Design an autonomous scientific workflow with specialized agents" - "Set up a polymer informatics pipeline with uncertainty quantification" - "Orchestrate domain-specific agents for computational chemistry"

ndpvt-web Skill

Generate high-quality multi-step LLM workflows using Bayesian inference with parallel look-ahead rollouts and importance-weighted resampling. Use when: 'build a workflow for this task', 'generate an agent pipeline', 'create a multi-step LLM chain', 'optimize my prompt chain', 'design an agentic workflow', 'Bayesian workflow generation'.

ndpvt-web Skill

Build autonomous cloud operations using a four-plane cognitive architecture (Sensing, Reasoning, Orchestration, Experience) with Kubernetes, Terraform, OPA, and ML anomaly detection. Use when: 'set up self-healing Kubernetes infrastructure', 'add anomaly detection to my cloud platform', 'create OPA policies for autonomous remediation', 'build a cognitive operations pipeline', 'implement intent-based infrastructure management', 'add intelligent auto-scaling with feedback loops'.

ndpvt-web Skill

Build LLM-powered graph analytics systems using the GraphSeek two-plane architecture: a Semantic Catalog for planning over graph schemas and operations, separated from deterministic database-grade query execution. Use when: 'query a property graph with natural language', 'build a graph analytics pipeline', 'connect LLM reasoning to Neo4j/Cypher', 'analyze a knowledge graph without writing queries', 'create a semantic layer for graph databases', 'multi-step graph traversal with LLM planning'.

ndpvt-web Skill

Apply the HQP framework to compress and accelerate PyTorch models for edge deployment using sensitivity-aware structural pruning followed by 8-bit post-training quantization. Trigger phrases: 'optimize model for edge', 'prune and quantize model', 'compress model for Jetson', 'reduce inference latency on edge device', 'hybrid quantization and pruning', 'deploy model to edge with size constraints'

ndpvt-web Skill

Extract and geocode location mentions from humanitarian and crisis texts using a two-step LLM pipeline: few-shot NER for toponym extraction followed by agent-based geocoding for coordinate resolution. Handles ambiguous place names, distinguishes literal from associative mentions, and reduces geographic bias. Use when: 'extract locations from crisis reports', 'geocode humanitarian text', 'find place names in disaster documents', 'NER for geographic entities in unstructured text', 'resolve ambiguous toponyms from news articles', 'geolocate mentions in humanitarian datasets'.

ndpvt-web Skill

Multi-agent query reformulation and LLM reranking for retrieval over legal, regulatory, or domain-specific corpora. Use when building legal search systems, statute retrieval pipelines, or any RAG system where user queries are ambiguous, colloquial, or multi-issue. Triggers: 'build a legal search system', 'improve statute retrieval', 'multi-agent query reformulation', 'legal RAG pipeline', 'rerank legal search results', 'query understanding for retrieval'

ndpvt-web Skill

Build omnimodal benchmarks and evaluation pipelines for interactive video understanding (livestreams, real-time comments, multi-speaker audio). Applies LiViBench's multi-agent annotation workflow, seed-question-driven QA generation, and Video-to-Comment Retrieval (VCR) module design. Trigger phrases: 'build a livestream video benchmark', 'evaluate multimodal models on interactive video', 'create annotation pipeline for video QA', 'design a multi-agent video description system', 'implement comment retrieval for video understanding', 'build an omnimodal evaluation dataset'.

ndpvt-web Skill

Build anomaly detection pipelines for Advanced Persistent Threat (APT) detection by encoding system logs into semantic embeddings with sentence-transformer LLMs and training autoencoders on reconstruction error. Trigger phrases: "detect APT in system logs", "semantic log anomaly detection", "autoencoder on log embeddings", "LLM-based threat detection", "provenance log analysis", "system log anomaly pipeline".

ndpvt-web Skill

Ontology-guided multi-agent reasoning for culturally aligned LLM outputs. Use when building systems that must respect cultural values, when designing multi-agent pipelines with demographic grounding, or when implementing value-aware decision making. Triggers: 'culturally aligned generation', 'ontology-guided agents', 'value-persona reasoning', 'demographic-aware LLM', 'cultural sensitivity pipeline', 'WVS-style value alignment'