AgentArea
  • Цены
  • Docs
СвязатьсяСоздать аккаунт
Создать аккаунт
Agent Area Logo

Открытая инфраструктура для команд агентов. Работайте в нашем облаке или разверните в своём контуре.

Платформа
  • Продукт
  • Инструменты
  • Модели
  • Вопросы
Ресурсы
  • Документация
  • Блог
Компания
  • О нас
  • Контакты
Юридическое
  • Тарифы
  • Оплата и возврат
  • Политика конфиденциальности
  • Пользовательское соглашение

© 2026 AgentArea. Все права защищены.

ООО «Джамакаси Технолоджис»
ОГРН 1207700353101
ИНН/КПП 9728013548 / 772801001
117342, г. Москва, ул. Бутлерова, д. 17, этаж 3, комната 95, офис 182
Сделано в Джамакаси Технолоджис

Каталог навыков агентов

В каталоге 183 730 навыков в 14 категориях.

Категории

model-condition-comparison

Use when the operator wants two or more model conditions (Opus 5, Fable 5.1, Sol) compared on one source head and one pr...

Автор: s-smits

model-configuration

AI model configuration patterns for this project. Single source of truth for model definitions. Triggers on "MODEL_CONFI...

Автор: planetaryescape

model-context

MCP (Model Context Protocol) - Build AI-native servers with tools, resources, and prompts. TypeScript/Python SDKs for Cl...

Автор: bobmatnyc

model-context-builder

MCP (Model Context Protocol) server build and evaluation guide, including local conventions for tool surfaces, config, a...

Автор: bobmatnyc
Страница 1064 из 1838 · Показано 100 из 183 730 навыков · по числу звёзд
Назад1…106310641065…1838Далее

model-context-protocol

Model Context Protocol (MCP) - Open standard for connecting AI applications to external data sources, tools, and systems...

Автор: enuno

model-conventions

Standards, conventions, and struct tag reference for models

model
conventions
Автор: griffnb

model-coordination

Use this skill when coordinating multiple AI models (Claude, GPT, Gemini, DeepSeek) for competitive trading analysis, ru...

model
coordination
Автор: AkhilGurrapu

model-cost-router

Decide when to use cheaper, local, or frontier models and how to measure cost tradeoffs. Use for token limits, model rou...

Автор: Arnie016

model-council

Use only for an explicitly requested council of named models or agents with a judge. Ordinary review and brainstorming d...

Автор: MVPavan

model-council-voting

LLM council/panel voting: multi-model coders, consensus rules, inter-rater agreement (kappa, alpha), correlated-error di...

Автор: scdenney

model-critique-coach

当使用者说“帮我批判这个模型”“找漏洞和反例”“模拟评委审稿”“这个结论站得住吗”“为什么验证不充分”时使用。先重建现有模型及其证据链,再从核心主张倒查方程、参数、数据、代码与假设,检查量纲、边界、可辨识性、泄漏、基线、验证、灵敏度、稳健性...

Автор: ChromiteCr

model-data

Design and build database schemas and data models in MotherDuck. Produces a file-based project scaffold. Use when creati...

Автор: motherduckdb

model-debugging

Debug and diagnose model errors in Pollinations services. Analyze logs, find error patterns, identify affected users. Fo...

Автор: pollinations

model-deployment

Generates code that deploys fine-tuned models from SageMaker Serverless Model Customization to SageMaker endpoints or Be...

Автор: awslabs

model-deployment

Deploy trained machine learning models as production-ready services using REST APIs, containers, serverless functions, a...

Автор: seb1n

model-deployment

Deploy ML models with FastAPI, Docker, Kubernetes. Use for serving predictions, containerization, monitoring, drift dete...

Автор: secondsky

model-deployment

Deploy a new LLM model via LiteLLM (GitOps) and/or Azure (Terraform + node backend), add it to the ai toolkit, create th...

Автор: Unique-AG

model-deployment-helper

This skill enables Claude to deploy machine learning models to production environments. It automates the deployment work...

Автор: intent-solutions-io

model-detection

Universal model detection and capability assessment for optimal cross-model compatibility

Автор: bejranonda

model-development

Model-Development standards for model development in Ml Ai environments.

Автор: williamzujkowski

model-diagnostics

MCMC diagnostics for Bayesian models including convergence assessment, effective sample size, divergences, and posterior...

Автор: choxos

model-discovery

Fetch current model names from AI providers (Anthropic, OpenAI, Gemini, Ollama), classify them into tiers (fast/default/...

Автор: NovaAI-innovation

model-dispatch

Resolve Maigo role models and delegation from an explicitly selected profile and the current host's tools. Use before ro...

Автор: Lee-W

model-dos

Detects LLM endpoints missing token caps, rate limits, or prompt-length bounds, enabling cost and resource exhaustion. U...

Автор: thejefflarson

model-drift-detector

Detect model drift detector operations. Auto-activating skill for ML Deployment. Triggers on: model drift detector, mode...

Автор: Brmbobo

model-drift-detector

Model Drift Detector - Auto-activating skill for ML Deployment.Triggers on: model drift detector, model drift detectorPa...

Автор: jeremylongshore

model-entity-validator

This skill should be used when the user asks to "create a model", "add a Django model", "create database table", "add en...

Автор: smicolon

model-escalation

Advisory model escalation based on task outcome tracking

Автор: baekenough

model-escalation

Automatic model switching based on task complexity for OpenClaw agents. Dynamically escalates between Haiku (simple), So...

Автор: Geralt1983

model-evaluation

Renamed to /model-assessment in v6 (removed in v7).

Автор: Aperivue

model-evaluation

Generates python code that evaluates SageMaker models. Supports two evaluation types: LLM-as-Judge and Custom Scorer. Us...

Автор: awslabs

model-evaluation

This skill focuses on comprehensive evaluation of machine learning models across the entire ML lifecycle. It covers metr...

Автор: cosmix

model-evaluation

LLM evaluation methodology — side-by-side comparison, domain-specific benchmarking, regression detection for fine-tuned...

Автор: scoobydont-666

model-evaluation

Every metric encodes an opinion about which mistake hurts.

Автор: snoodleboot-io

model-evaluation-benchmark

Automated reproduction of comprehensive model evaluation benchmarks following the Benchmark Suite V3. Auto-activates for...

Автор: rysweet

model-evaluation-benchmark

Skill from rysweet/AzureHayMaker

Автор: rysweet

model-evaluation-metrics

Build model evaluation metrics operations. Auto-activating skill for ML Training. Triggers on: model evaluation metrics,...

Автор: Brmbobo

model-evaluation-metrics

Model Evaluation Metrics - Auto-activating skill for ML Training. Triggers on: model evaluation metrics, model evaluatio...

Автор: jeremylongshore

model-evaluator

Comprehensive ML model evaluation with multiple metrics, cross-validation, and statistical testing. Activates for "evalu...

Автор: anton-abyzov

model-evaluator

Evaluate and compare ML model performance with rigorous testing methodologies

Автор: eddiebe147

model-experiments

Managing ML experiments, metrics, parameters, and artifacts using MLflow, Weights & Biases, and best practices for repro...

Автор: AmnadTaowsoam

model-explainability

Techniques and tools for understanding how machine learning models make decisions and explaining those decisions to stak...

Автор: AmnadTaowsoam

model-explainability-tool

Build model explainability tool operations. Auto-activating skill for ML Training. Triggers on: model explainability too...

Автор: jeremylongshore

model-explainer

Model interpretability and explainability using SHAP, LIME, feature importance, and partial dependence plots. Activates...

Автор: anton-abyzov

model-export-helper

Model Export Helper - Auto-activating skill for ML Deployment. Triggers on: model export helper, model export helper Par...

Автор: byteworthy

model-export-helper

Assist with model export helper operations. Auto-activating skill for ML Deployment. Triggers on: model export helper, m...

Автор: jeremylongshore

model-extraction-relu-logits

Guidance for extracting weight matrices from black-box ReLU neural networks using only input-output queries. This skill...

Автор: letta-ai

model-fallback

模型自动降级与故障切换。当主模型请求失败、超时、达到速率限制或配额耗尽时,自动切换到备用模型,确保服务连续性。支持多供应商、多优先级的智能模型选择,提供健康监控、自动重试和错误恢复机制。

Автор: aAAaqwq

model-fallback

为 Hermes Agent 配置模型故障转移,自动切换到备用模型。类似于 FreeRide 的"速率限制自动切换"概念,但专为 Hermes Agent 设计。

Автор: clowlove

model-faults

Modellfehler aus Straßenfotos, run weekly by a scheduled task (or by hand): put recent Panoramax street photos beside re...

Автор: mdugue

model-first

相互依存ルール+状態+関与が多いシステムを実装する前に、モデル(実体・不変条件・語彙)を明示して固定する front-load。暗黙モデルの連鎖破綻(多実体の整合が silent に崩れる型)を loud な不変条件に変える。ゲーム/シミュ...

Автор: YutoMizutani

model-first-reasoning

Two-phase reasoning paradigm that reduces hallucinations and constraint violations in complex planning tasks. Use when t...

Автор: j0KZ

model-fit-auditor

当已经有观测与模型预测(或一份拟合输出)、要判断这个拟合信不信时使用。看残差结构、带不确定度的拟合优度、杠杆值与影响点、信息准则。残差里有结构,说明模型、测量过程或不确定度模型三者之一不完整:必须说出可能是哪一处、用什么检查分辨,而不是加参...

Автор: ChromiteCr

model-fit-cheapskate

Explicit model-selection preflight only. Budget-minded advice for the whole submitted task; recommend available model/ef...

Автор: yuezjo

model-fit-cheapskate-staged

Explicit model-selection preflight only. Budget-minded advice for the current stage of a justified staged workflow; reco...

Автор: yuezjo

model-fit-goldilocks

Explicit model-selection preflight only. Conservative advice for the whole submitted task; recommend available model/eff...

Автор: yuezjo

model-fit-goldilocks-staged

Explicit model-selection preflight only. Conservative advice for the current stage of a justified staged workflow; recom...

Автор: yuezjo

model-guard

Budget guard for top-tier expensive models (Claude Code Fable, Codex astra): keeps one session from burning the whole pl...

Автор: hanzhangzzz

model-guided-code-repair

Automatically repair code violations of temporal properties using model-checking counterexamples as guidance. Use when w...

Автор: ArabelaTso

model-identity

Emit the agent's tier, model, and effort as a table before any other action.

Автор: Dev-Toolbelt

model-infer-fusion

基于 PyTorch 框架的昇腾 NPU 模型推理融合算子优化技能。分析模型代码,识别可替换为 torch_npu 融合算子的计算模式,生成替换方案。触发场景:torch_npu 融合算子替换、MoE/Attention/FFN/Norm...

Автор: catman626

model-infer-graph-mode

基于 PyTorch 框架的昇腾 NPU 模型推理图模式适配技能。将模型适配到 torch.compile 图模式以加速推理性能。触发场景:npugraph_ex 或 GE 图模式适配、torch.compile 在昇腾 NPU 上的使用、...

Автор: catman626

model-infer-harmony

麒麟 NPU 端侧(Kirin9030 / HarmonyOS)ASR 模型 4bit W4A16 量化、omg 离线模型转换与 CANNPAK 打包全流程技能。覆盖 dopt PTQ 标定 → 导量化参数 → 导 ONNX → 图改写 →...

Автор: catman626

model-infer-kvcache

基于 PyTorch 框架的昇腾 NPU 模型推理 KVCache 优化技能。分析并改造 LLM 推理模型的 KVCache 实现,覆盖 Legacy 连续缓存与分页注意力(Paged Attention)配 FA 融合算子、MLA 压缩缓...

Автор: catman626

model-infer-migrator

基于 PyTorch 框架的昇腾 NPU 模型推理适配与部署基线技能。支持两种部署模式:框架部署模式(接入 cann-recipes-infer 的 executor/core/)和独立部署模式(自管 Runner 不依赖框架)。从 HF...

Автор: catman626

model-infer-multi-stream

NPU 多流技术知识技能。提供整网模块 / 算子 DAG 拆解、模块间与模块内并行性判断、多流候选编排派生、TorchAir(Ascend IR/GE) 与 npugraph_ex/aclgraph 的多流 API 路由、切流 / 同步 /...

Автор: catman626

model-infer-prefetch

为模型添加 torch_npu.npu_prefetch 权重预取优化特性。触发:profiling 显示 MatMul/QBMM/GMM 算子存在 memory-bound 热点、需要为模型添加权重预取、将 prefetch 模式迁移到新...

Автор: catman626

model-infer-profiling

NPU 性能分析数据采集技能。用于华为昇腾NPU上的 PyTorch 模型性能分析。 触发场景: - 用户需要采集 NPU 性能数据 - 用户提到 profiling、性能分析、tensorboard - 用户需要分析模型推理性能瓶颈 -...

Автор: catman626

model-infer-superkernel

SuperKernel 适配技能。当用户需要启用 SuperKernel 算子二进制融合技术优化 NPU 推理性能时使用此技能。触发场景包括:用户询问 SuperKernel、算子融合、二进制融合、启用 superkernel、superk...

Автор: catman626

model-interpretability

Interpret ML model predictions using SHAP, LIME, attention visualization, and probing techniques. Use when explaining mo...

Автор: jlaws

model-interpretability

"Make it interpretable" is four different requests.

Автор: snoodleboot-io

model-inversion-membership-inference

Review an AI system for model inversion attacks that reconstruct training data from model outputs, and membership infere...

Автор: maruakshay

model-maker

Generate a 3D model (GLB mesh) from a text description or a reference photo via Tripo. Textured or bare geometry, polygo...

Автор: Mikefluff

model-management

CLI commands to add, update, list, and deprecate AI models in the database. Triggers on "add model", "new model", "updat...

Автор: planetaryescape

model-manager

Test, validate, and add new AI models to the eval suite. Use when user asks to add new models, test model access, check...

Автор: sunholo-data

model-mediated-development

Use when building any system that involves AI/model calls - integrates with brainstorming, planning, and TDD to ensure m...

Автор: dbmcco

model-merging

Merge multiple fine-tuned models using mergekit to combine capabilities without retraining. Use when creating specialize...

Автор: zechenzhangAGI

model-migration-plan

Plan the migration of an LLM feature from one model to another without breaking production. Use when a model is being de...

Автор: Slipcast-dev

model-mix

Break down Claude Code usage by model family (Opus / Sonnet / Haiku) from the Agent Monitor dashboard — each family's sh...

Автор: hoangsonww

model-monitor

Professional Model Monitor Expert skill. Integrate LLM API workflows, safe system prompt guidelines, and agentic workflo...

Автор: AtulPurohit

model-monitoring

Monitor model performance, detect data drift, concept drift, and anomalies in production using Prometheus, Grafana, and...

Автор: aj-geddes

model-monitoring

The layers trade timeliness against definitiveness.

Автор: snoodleboot-io

model-patterns

Entity and model patterns with JSON serialization, immutability, and equality

Автор: Kaakati

model-performance-debugging

Run this before anything else.

Автор: snoodleboot-io

model-prepare

Produce a first security model for a project that has none: draft it with `<governance-body>` (draft-first, provenance-t...

Автор: apache

model-profile-resolution

Resolve model profile (quality/balanced/budget) at orchestration start and map agents to specific models. Enables cost/q...

Автор: a5c-ai

model-prompt-audit

Audit the global agent configuration (CLAUDE.md / AGENTS.md, rules, settings, behavioral plugins) against the current of...

Автор: hanzhangzzz

model-prompt-pack

Use when asked to write prompts for image-to-3D or text-to-3D tools, generate 3D models of a topic's parts, plan the ass...

Автор: Slipcast-dev

model-provenance

Use when the user names a specific ML model (e.g. DINOv3, SAM 2, Whisper, Qwen2-VL) and wants its real/official code, tr...

Автор: infiniV

model-provider-setup

Configure Claude Code to use alternative AI model providers by setting up custom API endpoints and authentication. Use t...

Автор: aicodingstack

model-pruning-helper

Model Pruning Helper - Auto-activating skill for ML Deployment. Triggers on: model pruning helper, model pruning helper...

Автор: byteworthy

model-pruning-helper

Model Pruning Helper - Auto-activating skill for ML Deployment.Triggers on: model pruning helper, model pruning helperPa...

Автор: jeremylongshore

model-qa

Independent model QA expert who audits ML and statistical models end-to-end - from documentation review and data reconst...

Автор: amirhamzakhan2001

model-quantization-tool

Build model quantization tool operations. Auto-activating skill for ML Deployment. Triggers on: model quantization tool,...

Автор: Brmbobo

model-quantization-tool

Model Quantization Tool - Auto-activating skill for ML Deployment. Triggers on: model quantization tool, model quantizat...

Автор: byteworthy

model-quantization-tool

Model Quantization Tool - Auto-activating skill for ML Deployment.Triggers on: model quantization tool, model quantizati...

Автор: jeremylongshore

model-queries

Building database queries with the Options API

model
queries
Автор: griffnb

model-recommend-analysis

推荐模型昇腾NPU性能分析与优化,分析瓶颈点及图结构中的相似结构,找到融合算子和pass机会;并给出优化建议。触发场景:推荐模型在昇腾NPU上性能不达标或客户推荐业务迁移到昇腾需要调优吞吐和时延。支持推荐的推理和训练场景。

Автор: catman626

model-recommendation

Analyze chatmode or prompt files and recommend optimal AI models based on task complexity, required capabilities, and co...

Автор: beel-collab

model-recommender

Recommend the right AI model for a task by scoring candidates across six dimensions (Reasoning, Engineering, Speed, Brea...

Автор: projectious-work