ai-ml-pipeline
End-to-end AI/ML pipeline orchestration from data collection and preparation through annotation, training, evaluation, and inference deployment. Use when building or reviewing ML pipelines, model training or serving infrastructure, or MLOps workflows.
- License 许可
- MIT
- 最近更新
- 2026-11-13
- Stars
- ★ 0
- Forks
- 0
01 前言 Front Matter
- name
- ai-ml-pipeline
- description
- End-to-end AI/ML pipeline orchestration from data collection and preparation through annotation, training, evaluation, and inference deployment. Use when building or reviewing ML pipelines, model training or serving infrastructure, or MLOps workflows.
03 SKILL.md 正文
# AI/ML Pipeline Skill
Overview
End-to-end AI/ML pipeline orchestration from data collection through model deployment.
Pipeline Stages
1. Data Collection
- web-scraper: Web data extraction, crawl design
- api-collector: REST/GraphQL API integration
- data-harvester: Multi-source data lake population
- telemetry-engineer: Product telemetry and event tracking
2. Data Preparation
- corpus-builder: Text corpus construction
- data-cleaner: Deduplication, missing values, outliers
- data-preprocessor: Feature scaling, encoding, splitting
- data-validator: Schema validation, drift detection
- feature-engineer: Feature store, selection, monitoring
- data-quality-engineer: Quality frameworks, observability
3. Dataset Management
- dataset-curator: Documentation, composition, representativeness
- dataset-versioner: DVC/Git LFS, lineage, reproducibility
- data-annotator: Labeling workflows, quality control
- synthetic-data-generator: Augmentation, GAN-based generation
- dataset-auditor: Bias detection, legal compliance
4. Model Development
- model-trainer: Training pipeline, hyperparameters, distributed training
- fine-tuning-engineer: LoRA/QLoRA, RLHF, DPO, alignment
- prompt-engineer: System prompts, few-shot, optimization
- embedding-engineer: Embedding models, semantic search
- vector-db-engineer: Vector indexing, hybrid search
5. Model Evaluation
- model-evaluator: Benchmarks, robustness, fairness testing
- ml-ops-engineer: Pipeline automation, experiment tracking
- model-monitor: Drift detection, health dashboards
6. Model Governance
- ai-ethics-reviewer: Ethics, transparency, accountability
- bias-auditor: Fairness metrics, mitigation strategies
- explainability-engineer: SHAP/LIME, audit trails
- ai-safety-engineer: Red teaming, guardrails
When to Use
- Building or improving ML models
- Designing data pipelines for AI
- Evaluating model performance
- Addressing bias or safety concerns
- Deploying models to production
Agent Selection
Use agent-selector to pick the right agents for your pipeline stage. Use workflow-orchestrator to coordinate multi-agent pipelines.
04 同仓库更多 Skills
wrangler
Cloudflare Workers CLI for deploying, developing, and managing Workers, KV, R2, D1, Vectorize, Hyperdrive, Workers AI, Containers, Queues, Workflows, Pipelines, and Secrets Store. Load before running wrangler commands to ensure correct syntax and best practices. Biases towards retrieval from Cloudflare docs over pre-trained knowledge.
workers-best-practices
Reviews and authors Cloudflare Workers code against production best practices. Load when writing new Workers, reviewing Worker code, configuring wrangler.jsonc, or checking for common Workers anti-patterns (streaming, floating promises, global state, secrets, bindings, observability). Biases towards retrieval from Cloudflare docs over pre-trained knowledge.
web-perf
Analyzes web performance using Chrome DevTools MCP. Measures Core Web Vitals (LCP, INP, CLS) and supplementary metrics (FCP, TBT, Speed Index), identifies render-blocking resources, network dependency chains, layout shifts, caching issues, and accessibility gaps. Use when asked to audit, profile, debug, or optimize page load performance, Lighthouse scores, or site speed. Biases towards retrieval from current documentation over pre-trained knowledge.
web-design-master
Professional web design standard ("AI Professional Web Design Master Prompt") covering page/section/layout design, visual hierarchy, color systems, typography scales, 8-point grid spacing, responsive breakpoints, accessibility, and design QA review. Use when designing or building any page, section, or layout so it looks deliberately designed by a professional product team rather than a generic AI template.
verification-before-completion
Require command evidence before claiming done. Use proactively before VERIFY_PASS, ORCHESTRA_COMPLETE, or "all fixed" statements. Run tests, lint, health, or git checks — never trust claims without output.
ui-ux-pro-max
UI/UX design intelligence for web and mobile. Searchable local database with 84 styles, 192 color palettes, 74 font pairings, 192 product types, 98 UX guidelines, 104 icon entries, 16 GSAP motion presets, and 25 chart types across 22 stacks (React, Next.js, Vue, Nuxt, Svelte, Astro, SwiftUI, React Native, Flutter, Tailwind, shadcn/ui, Jetpack Compose, Angular, Laravel, JavaFX, WPF, WinUI, Avalonia, Uno Platform, UWP, Three.js, and HTML/CSS). Use when designing, building, or reviewing UI: pages, components, color schemes, typography, layout, accessibility, animation, or data visualization.