Agent测试
- 作者仓库星标 0
- 作者更新于 实时读取
- 作者仓库 skills-registry
- 领域
- 设计与多媒体
- 兼容 Agent
-
- Claude Code
- Cursor
- Cline
- Codex
- Windsurf
- Gemini CLI
- +20
- 信任分
- 88 / 100 · 社区维护
- 作者 / 版本 / 许可
- @tomevault-io · 未声明 license
- Token 消耗评级
- 低消耗
- 接入复杂程度
- 需手动接入
- 是否需要外部 API Key
- 不需要
- 兼容的系统
- Docker
- 底层运行要求
- Python · Docker
- 文件与系统权限
-
- 只读
- 允许写入 / 修改
- Shell 执行
- 网络行为
- 仅限本地
- 安装命令数
- 26 条
档案由构建时根据 SKILL.md 与安装命令自动衍生，可能与作者实际意图存在差异。
需要注意： 未限定 allowed-tools，默认拥有全部工具权限。
---
name: machine-learning-ops-ml-pipeline
description: Design and implement a complete ML pipeline for: $ARGUMENTS Use when this capability is needed.…
category: 设计与多媒体
runtime: Python / Docker
---
# machine-learning-ops-ml-pipeline 输出预览
## PART A: 任务判断
- 适用问题：视觉内容、演示材料、信息图或设计交付。
- 输入要求：目标材料、限制条件、期望输出和验收方式。
- 证据边界：围绕“Use this skill when / Do not use this skill when / Instructions”读取原文规则，不把推断写成作者承诺。
## PART B: 执行结果
- **01** 任务判断：确认你的需求是否属于视觉内容、演示材料、信息图或设计交付，并标出输入、限制和预期结果。
- **02** 执行计划：优先按“Use this skill when / Do not use this skill when / Instructions”拆成步骤，说明每一步会读取什么、修改什么、产出什么。
- **03** 交付结果：给出可复制的命令、文件改动、检查清单或内容草稿，并说明如何继续迭代。
- **04** 风险边界：结合 读取文件、写入/修改文件、执行终端命令、主要在本地完成、通常不需要额外 API Key 给出执行前确认项。
## Running Rules
- 读取文件、写入/修改文件、执行终端命令；主要在本地完成；通常不需要额外 API Key。
- 先小样例验证，再放大到真实任务。
- 交付时同时给结果、检查口径和下一步迭代建议。 先确认触发方式
原文没有稳定的斜杠命令要求。安装验证后通常全局生效，直接在对话里点名这个 Skill 并描述任务即可。
给清楚输入和边界
告诉 Agent 目标文件或材料、期望结果、不可改范围、是否允许联网或执行命令。本 Skill 的权限画像是：读取文件、写入/修改文件、执行终端命令。
小样例验证后再放大
先用一个小任务确认它会围绕“Use this skill when / Do not use this skill when / Instructions”工作；涉及文件或命令时，先看 diff、日志、预览或测试结果。
复核后再交付
检查最终产物是否包含明确结果、必要证据和下一步动作；如果输出泛泛而谈，就补充输入、边界和验收标准后重跑。
---
name: machine-learning-ops-ml-pipeline
description: Design and implement a complete ML pipeline for: $ARGUMENTS Use when this capability is needed.…
category: 设计与多媒体
source: tomevault-io/skills-registry
---
# machine-learning-ops-ml-pipeline
## 什么时候使用
- 把设计与视觉方向的常用动作沉淀成 Agent 可调用的技能 适合处理界面、视觉、封面、信息图或演示材料交付，核心价值是把输入、判断、执行、验证和交付边界固定下来，避免 Agent 泛泛回答。 把任务拆成可执行、可检查、可继续迭代的步骤…
- 面向视觉内容、演示材料、信息图或设计交付，优先处理能明确输入、步骤和验收标准的工作。
## 需要提供什么
- 目标材料、目录范围、期望结果和不可改动内容。
- 是否允许联网、执行命令、读写文件或调用外部服务。
## 执行规则
- 围绕「Use this skill when / Do not use this skill when / Instructions」组织步骤，不把推断写成作者事实。
- 读取文件、写入/修改文件、执行终端命令；主要在本地完成；通常不需要额外 API Key。
- 先跑小样例，确认结果可检查后再扩大任务范围。
## 输出要求
- 给出最终产物、关键证据、验证方式和下一步动作。
- 信息不足时标记 unknown，不编造命令、平台或依赖。 证据边界与执行链路
作者原文负责流程事实；仓库文件负责来源和命令；流狐只补充适用场景、限制和质量判断。
skill "machine-learning-ops-ml-pipeline" {
输入层 -> 用户目标 + 目标文件 + 禁止范围 + 验收标准
上下文层 -> Use this skill when / Do not use this skill when / Instructions
规则层 -> SKILL.md 触发条件 / 执行顺序 / 输出格式
运行层 -> Python / Docker | 读取文件、写入/修改文件、执行终端命令 | 主要在本地完成
安全层 -> 通常不需要额外 API Key + 小任务验证 + diff / 日志复核
输出层 -> 可复制结果 + 检查清单 + 下一步迭代
}Machine Learning Pipeline - Multi-Agent MLOps Orchestration
Design and implement a complete ML pipeline for: $ARGUMENTS
Use this skill when
- Working on machine learning pipeline - multi-agent mlops orchestration tasks or workflows
- Needing guidance, best practices, or checklists for machine learning pipeline - multi-agent mlops orchestration
Do not use this skill when
- The task is unrelated to machine learning pipeline - multi-agent mlops orchestration
- You need a different domain or tool outside this scope
Instructions
- Clarify goals, constraints, and required inputs.
- Apply relevant best practices and validate outcomes.
- Provide actionable steps and verification.
- If detailed examples are required, open
resources/implementation-playbook.md.
Thinking
This workflow orchestrates multiple specialized agents to build a production-ready ML pipeline following modern MLOps best practices. The approach emphasizes:
- Phase-based coordination: Each phase builds upon previous outputs, with clear handoffs between agents
- Modern tooling integration: MLflow/W&B for experiments, Feast/Tecton for features, KServe/Seldon for serving
- Production-first mindset: Every component designed for scale, monitoring, and reliability
- Reproducibility: Version control for data, models, and infrastructure
- Continuous improvement: Automated retraining, A/B testing, and drift detection
The multi-agent approach ensures each aspect is handled by domain experts:
- Data engineers handle ingestion and quality
- Data scientists design features and experiments
- ML engineers implement training pipelines
- MLOps engineers handle production deployment
- Observability engineers ensure monitoring
Phase 1: Data & Requirements Analysis
Deliverables:
Data source audit and ingestion strategy:
- Source systems and connection patterns
- Schema validation using Pydantic/Great Expectations
- Data versioning with DVC or lakeFS
- Incremental loading and CDC strategies
Data quality framework:
- Profiling and statistics generation
- Anomaly detection rules
- Data lineage tracking
- Quality gates and SLAs
Storage architecture:
- Raw/processed/feature layers
- Partitioning strategy
- Retention policies
- Cost optimization
Provide implementation code for critical components and integration patterns.
Deliverables:
Feature engineering pipeline:
- Transformation specifications
- Feature store schema (Feast/Tecton)
- Statistical validation rules
- Handling strategies for missing data/outliers
Model requirements:
- Algorithm selection rationale
- Performance metrics and baselines
- Training data requirements
- Evaluation criteria and thresholds
Experiment design:
- Hypothesis and success metrics
- A/B testing methodology
- Sample size calculations
- Bias detection approach
Include feature transformation code and statistical validation logic.
Phase 2: Model Development & Training
Build comprehensive training system:
Training pipeline implementation:
- Modular training code with clear interfaces
- Hyperparameter optimization (Optuna/Ray Tune)
- Distributed training support (Horovod/PyTorch DDP)
- Cross-validation and ensemble strategies
Experiment tracking setup:
- MLflow/Weights & Biases integration
- Metric logging and visualization
- Artifact management (models, plots, data samples)
- Experiment comparison and analysis tools
Model registry integration:
- Version control and tagging strategy
- Model metadata and lineage
- Promotion workflows (dev -> staging -> prod)
- Rollback procedures
Provide complete training code with configuration management.
Focus areas:
Code quality and structure:
- Refactor for production standards
- Add comprehensive error handling
- Implement proper logging with structured formats
- Create reusable components and utilities
Performance optimization:
- Profile and optimize bottlenecks
- Implement caching strategies
- Optimize data loading and preprocessing
- Memory management for large-scale training
Testing framework:
- Unit tests for data transformations
- Integration tests for pipeline components
- Model quality tests (invariance, directional)
- Performance regression tests
Deliver production-ready, maintainable code with full test coverage.
Phase 3: Production Deployment & Serving
Implementation requirements:
Model serving infrastructure:
- REST/gRPC APIs with FastAPI/TorchServe
- Batch prediction pipelines (Airflow/Kubeflow)
- Stream processing (Kafka/Kinesis integration)
- Model serving platforms (KServe/Seldon Core)
Deployment strategies:
- Blue-green deployments for zero downtime
- Canary releases with traffic splitting
- Shadow deployments for validation
- A/B testing infrastructure
CI/CD pipeline:
- GitHub Actions/GitLab CI workflows
- Automated testing gates
- Model validation before deployment
- ArgoCD for GitOps deployment
Infrastructure as Code:
- Terraform modules for cloud resources
- Helm charts for Kubernetes deployments
- Docker multi-stage builds for optimization
- Secret management with Vault/Secrets Manager
Provide complete deployment configuration and automation scripts.
Kubernetes-specific requirements:
Workload orchestration:
- Training job scheduling with Kubeflow
- GPU resource allocation and sharing
- Spot/preemptible instance integration
- Priority classes and resource quotas
Serving infrastructure:
- HPA/VPA for autoscaling
- KEDA for event-driven scaling
- Istio service mesh for traffic management
- Model caching and warm-up strategies
Storage and data access:
- PVC strategies for training data
- Model artifact storage with CSI drivers
- Distributed storage for feature stores
- Cache layers for inference optimization
Provide Kubernetes manifests and Helm charts for entire ML platform.
Phase 4: Monitoring & Continuous Improvement
Monitoring framework:
Model performance monitoring:
- Prediction accuracy tracking
- Latency and throughput metrics
- Feature importance shifts
- Business KPI correlation
Data and model drift detection:
- Statistical drift detection (KS test, PSI)
- Concept drift monitoring
- Feature distribution tracking
- Automated drift alerts and reports
System observability:
- Prometheus metrics for all components
- Grafana dashboards for visualization
- Distributed tracing with Jaeger/Zipkin
- Log aggregation with ELK/Loki
Alerting and automation:
- PagerDuty/Opsgenie integration
- Automated retraining triggers
- Performance degradation workflows
- Incident response runbooks
Cost tracking:
- Resource utilization metrics
- Cost allocation by model/experiment
- Optimization recommendations
- Budget alerts and controls
Deliver monitoring configuration, dashboards, and alert rules.
Configuration Options
- experiment_tracking: mlflow | wandb | neptune | clearml
- feature_store: feast | tecton | databricks | custom
- serving_platform: kserve | seldon | torchserve | triton
- orchestration: kubeflow | airflow | prefect | dagster
- cloud_provider: aws | azure | gcp | multi-cloud
- deployment_mode: realtime | batch | streaming | hybrid
- monitoring_stack: prometheus | datadog | newrelic | custom
Success Criteria
Data Pipeline Success:
- < 0.1% data quality issues in production
- Automated data validation passing 99.9% of time
- Complete data lineage tracking
- Sub-second feature serving latency
Model Performance:
- Meeting or exceeding baseline metrics
- < 5% performance degradation before retraining
- Successful A/B tests with statistical significance
- No undetected model drift > 24 hours
Operational Excellence:
- 99.9% uptime for model serving
- < 200ms p99 inference latency
- Automated rollback within 5 minutes
- Complete observability with < 1 minute alert time
Development Velocity:
- < 1 hour from commit to production
- Parallel experiment execution
- Reproducible training runs
- Self-service model deployment
Cost Efficiency:
- < 20% infrastructure waste
- Optimized resource allocation
- Automatic scaling based on load
- Spot instance utilization > 60%
Final Deliverables
Upon completion, the orchestrated pipeline will provide:
- End-to-end ML pipeline with full automation
- Comprehensive documentation and runbooks
- Production-ready infrastructure as code
- Complete monitoring and alerting system
- CI/CD pipelines for continuous improvement
- Cost optimization and scaling strategies
- Disaster recovery and rollback procedures
Source: benjaminasterA/antigravity-awesome-skills — distributed by TomeVault.
先判断是否适合
作者设计意图
作者的方法与取舍
边界和复核