Loading...
Loading...
Found 2,006 Skills
Use when user explicitly asks Flink/Ververica/Realtime Compute Console workspace operations: 草稿(draft), SQL校验/执行, 部署(deployment), 作业(job), Session Cluster, namespace, 表(table), 成员(member), 变量(variable), 或 checkpoint timeout 诊断, especially with workspace/deployment/job IDs (w-*, d-*, j-*, sc-*, draft-*). Also use when prompt asks to test/verify Flink Console lifecycle flow, safety guardrails, or parameter validation for these operations. This includes prompts such as create draft, deploy draft, list deployments, start/stop job, create/list session cluster, get tables, list variables. Also use when prompt explicitly asks to run `python scripts/flink_ververica_ops.py` for Flink Console workspace operations. Do not trigger for unrelated "workspace" contexts or generic cloud/platform tasks (ECS, OSS, RDS, Kafka, Spark, Kubernetes, billing, weather). Do not trigger for Flink instance lifecycle operations (create/scale/delete/renew); those belong to alibabacloud-flink-instance-manage.
Agent Platform Model Tuning. Use when you need to fine-tune open models or Gemini models using Agent Platform infrastructure. Don't use for model training outside Agent Platform, model deployment to endpoints (use `agent-platform-deploy`), or managing serving endpoints (use `agent-platform-endpoint-management`).
Guideline for designing, implementing, and verifying secure Python applications following OWASP Top 10 best practices. Use when the user wants to: (1) review Python code for security vulnerabilities, (2) design a secure Python application architecture, (3) implement security features (authentication, authorization, cryptography, input validation), (4) audit Python dependencies for known vulnerabilities, (5) create security checklists or verification plans, (6) fix security bugs or harden existing Python code, (7) set up security testing and static analysis (bandit, safety, semgrep), or (8) handle any Python security concern including injection prevention, secure deserialization, SSRF protection, secrets management, and secure deployment.
Run an autonomous Humanize-governed vLLM SOTA performance loop for one LLM model: first perform the fixed fair vLLM/SGLang/TensorRT-LLM deployment search and benchmark, then start one RLCR loop that repeatedly decides the gap, profiles the current bottleneck, runs layer/kernel pipeline analysis, patches vLLM code, optionally uses ncu-report-skill for kernel evidence, and revalidates until vLLM matches or beats the best observed framework under the same workload and SLA.
Manages and orchestrates prompts in Agent Platform. Use when you need to create, list, retrieve, version, or delete managed prompts in Agent Platform. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform prompts.
Strategic frameworks for Product/Business Owners. Use this skill for Product Market Research, defining Jobs-To-Be-Done (JTBD), understanding Diffusion of Innovations, planning MVPs, and separating deployment (Ship) from business launch (Release).
Systematically find blind spots in code, architecture, APIs, and deployment — structured critique that catches what familiarity hides
Use when verifying local, preview, production, or recurring critical user flows with browser evidence and selective on-demand deployments.
Kubernetes workload patterns, resource management, RBAC, probes, autoscaling, ConfigMap/Secret handling, and kubectl debugging for production-grade deployments.
This skill should be used when users want to train or fine-tune language models using TRL (Transformer Reinforcement Learning) on Hugging Face Jobs infrastructure. Covers SFT, DPO, GRPO and reward modeling training methods, plus GGUF conversion for local deployment. Includes guidance on the TRL Jobs package, UV scripts with PEP 723 format, dataset preparation and validation, hardware selection, cost estimation, Trackio monitoring, Hub authentication, and model persistence. Should be invoked for tasks involving cloud GPU training, GGUF conversion, or when users mention training on Hugging Face Jobs without local GPU setup.
Master Flutter development with Dart 3, advanced widgets, and multi-platform deployment. Handles state management, animations, testing, and performance optimization for mobile, web, desktop, and embedded platforms. Use PROACTIVELY for Flutter architecture, UI implementation, or cross-platform features.
Master Django 5.x with async views, DRF, Celery, and Django Channels. Build scalable web applications with proper architecture, testing, and deployment. Use PROACTIVELY for Django development, ORM optimization, or complex Django patterns.