搜索技能.../

机器学习 | Skills Pool

分类机器学习

机器学习

搜索查看全部分类

AI 推荐

机器学习

分类

机器学习调试销售与营销大语言模型与 AI 系统管理效率与集成代码质量 Git 工作流架构模式文档项目管理测试金融与投资安全知识库技术文档后端前端教育 CI/CD 自动化工具内容创作数据工程游戏开发学术脚本 CMS 与平台移动端云计算 IDE 插件打包与分发数据分析框架内部媒体设计全栈房产与法律生物信息学命令行工具 SQL 数据库计算化学容器实验室工具数据库工具健康与健身智能合约监控域名与 DNS 工具 Web3 工具健康养生支付文学与写作电商开发哲学与伦理天文与物理电子商务占卜与神秘学手工艺术科学计算商业应用 DeFi NoSQL 数据库烹饪艺术 $Undefined

查看全部分类

机器学习调试销售与营销大语言模型与 AI 系统管理效率与集成代码质量 Git 工作流架构模式文档项目管理测试金融与投资安全知识库技术文档后端前端教育 CI/CD 自动化工具内容创作数据工程游戏开发学术脚本 CMS 与平台移动端云计算 IDE 插件打包与分发数据分析框架内部媒体设计全栈房产与法律生物信息学命令行工具 SQL 数据库计算化学容器实验室工具数据库工具健康与健身智能合约监控域名与 DNS 工具 Web3 工具健康养生支付文学与写作电商开发哲学与伦理天文与物理电子商务占卜与神秘学手工艺术科学计算商业应用 DeFi NoSQL 数据库烹饪艺术 $Undefined

机器学习

Ievo

Trigger the Evolution agent to analyze a mistake and log a lesson. Use when you or another agent made an error worth learning from.

Previous 1…508 509 510…519 Next

Skill Name

One sentence describing when to use this skill, with concrete keywords for matching.

Fashion Garment Precision

Skill for high-fidelity garment reproduction in AI image generation. Should be used when the goal is to accurately describe clothing items, fabrics, textures, draping, layered constructions (such as lace over lining), transparency, fit, and silhouette for maximum visual accuracy. Provides a structured vocabulary for textile properties, construction details, and light interaction that AI models respond to with higher precision. Relevant for: fashion photography, e-commerce product shots, lookbooks, catalog images, virtual try-on, any scenario involving clothing or textile reproduction.

Marketplace-Lompa0

Enforce Provenance

Use this skill when validating whether outputs, rules, and recommendations are traceable, confidence-appropriate, and explicit about assumptions.

Time

LLM temporal reasoning scaffold for the temporal CLI.

Plant Phenotyping Pipeline

Build repeatable plant imaging workflows from preprocessing through trait extraction and explainable modeling.

Integration Regression Sentinel

Use when a legacy prompt, old workflow, or older skill reference explicitly names `integration-regression-sentinel`; this retired skill exists to redirect that request to `orchestration-router` for integration and regression gating across multi-track work. Do not select it for new tasks.

Feature Importance Analyzer

Feature Importance Analyzer - Auto-activating skill for ML Training. Triggers on: feature importance analyzer, feature importance analyzer Part of the ML Training skill category.

Agency Ai Engineer

Expert AI/ML engineer specializing in machine learning model development, deployment, and integration into production systems. Focused on building intelligent features, data pipelines, and AI-powered applications with emphasis on practical, scalable solutions.

Edge Ai Model Deployment Serving

Deploy and serve ML models at the edge with auto-scaling, A/B testing, and monitoring

Research Pipeline

"[TODO: 1-2 sentences explaining what this skill enables]"

JansenAnalytics0

Context Degradation

Language models exhibit predictable degradation patterns as context length increases. Understanding these patterns is essential for diagnosing failures and designing resilient systems.

Geoffrey Hinton

Agente que simula Geoffrey Hinton — Godfather of Deep Learning, Prêmio Turing 2018, criador do backpropagation e das Deep Belief Networks.

Angular

Modern Angular (v20+) expert with deep knowledge of Signals, Standalone Components, Zoneless applications, SSR/Hydration, and reactive patterns.

Lex

Centralized 'Truth Engine' for cross-jurisdictional legal context (US, EU, CA) and contract scaffolding.

Self-Improving AI Skill

Captures learnings about GenAI/LLM configuration, model selection, inference optimization, fine-tuning, RAG pipelines, prompt engineering, multimodal processing, and cost management. Use when: (1) Model response quality degrades after a provider update or version change, (2) Inference latency exceeds acceptable thresholds, (3) Fine-tuned model regresses on evaluation benchmarks, (4) RAG retrieval returns irrelevant or stale chunks, (5) Token costs exceed budget projections, (6) Hallucination rate increases on factual queries, (7) Context window overflows cause critical information truncation, (8) Multimodal pipeline fails on specific input types (image, audio, video, PDF), (9) A better model or configuration is discovered for a task, (10) Guardrails block valid output or miss harmful content.

Electrical

Use this skill when the user needs an outlet installed, a circuit added, a fixture wired, or a panel upgraded. Also triggers on 'my outlet doesn't work', 'the lights are flickering', 'I want to add a dedicated circuit for my workshop', or 'I'm upgrading to a 200-amp panel'. Do NOT use for low-voltage electronics, network cabling, or Arduino projects.

Di Engine

Understand and work with the custom Dependency Injection engine of this project. Use this skill when debugging DI resolution errors, adding new tokens, working in the engine/ folder, or understanding how constructor injection works.

Model Selection

Choose the right LLM model for a task based on complexity, cost, speed, and capability requirements. Use when creating tasks, dispatching sub-agents, or when the daemon needs to decide which model to assign.

Antigravity Ecosystem Master

Skill maestra que integra y documenta el ecosistema completo de Antigravity Nexus Core Protocol. Proporciona una visión holística de los 4 arquetipos de expertos, 8 skills subordinadas, 3 protocolos de seguridad, y el banco de memoria persistente. Úsala como guía arquitectónica integral para orquestar todas las capacidades del agente Antigravity en proyectos complejos.

Memory Never Forget

Memory system v3.1: Atkinson-Shiffrin temporal layering + 4-type taxonomy (User/Feedback/Project/Reference) + auto-extract + Dream consolidation + memory drift handling. Merges cognitive psychology with Claude Code's memory architecture.

Refactor Workflow

Disciplined refactoring with analysis-first approach and incremental changes

Eval

Run IsaacSim evaluation on a trained checkpoint. Use when user wants to evaluate a model after training.

Tier Review

Use after implementation to run tier-ordered review agents and produce a consolidated verdict.

Senior ML Engineer

ML engineering skill for productionizing models, building MLOps pipelines, and integrating LLMs. Covers model deployment, feature stores, drift monitoring, RAG systems, and cost optimization. Use when the user asks about deploying ML models to production, setting up MLOps infrastructure (MLflow, Kubeflow, Kubernetes, Docker), monitoring model performance or drift, building RAG pipelines, or integrating LLM APIs with retry logic and cost controls. Focused on production and operational concerns rather than model research or initial training.

konankirajesh7-raj0

Teammate Voices — Master Architecture

Master architecture skill for the Teammate Voices survey application. Ties together all tier-specific skills and covers cross-cutting concerns: authentication flow, authorization matrix, error handling strategy, logging, deployment pipeline, environment configuration, testing strategy, API versioning, CORS, monitoring, and the end-to-end workflow for building a new feature across all three tiers. Use this skill whenever the user asks about the overall system, cross-cutting concerns like auth or deployment, how the tiers connect, end-to-end feature implementation, testing strategy, CI/CD pipeline, environment setup, or any question that spans multiple tiers. Also trigger when the user mentions 'how does auth work', 'deployment', 'testing', 'CI/CD', 'environments', 'monitoring', 'logging', 'end to end', 'full stack', or asks how to add a new feature to Teammate Voices.

Bug Fix

Ce skill orchestre la correction d'un bug identifie via un mini-pipeline : prime_planner analyse le bug + codebase, produit un plan de correction cible, un builder applique le fix, puis le testeur QA revalide. Use when l'utilisateur signale un bug, un rapport QA contient des FAIL, ou un finding de securite doit etre corrige.

Trm Interp

Standardize mechanistic interpretability experiments for TRM-style recurrent models with a fixed trace to SAE feature to intervention to report loop. Use when implementing or running reproducible tomography studies, feature ablation and patch tests, and baseline versus intervened evaluation reports from stepwise traces.

Hti Zen Orchestrator

Guidelines for using Zen MCP tools effectively in this repo. Use for complex multi-model tasks, architectural decisions, or when cross-model validation adds value.

Pytorch Model

PyTorch CNN scaffold for CIFAR-10 image classification with training loop, early stopping, and checkpointing