В каталоге 183 730 навыков в 14 категориях.
Use when the operator wants two or more model conditions (Opus 5, Fable 5.1, Sol) compared on one source head and one pr...
AI model configuration patterns for this project. Single source of truth for model definitions. Triggers on "MODEL_CONFI...
MCP (Model Context Protocol) - Build AI-native servers with tools, resources, and prompts. TypeScript/Python SDKs for Cl...
MCP (Model Context Protocol) server build and evaluation guide, including local conventions for tool surfaces, config, a...
Model Context Protocol (MCP) - Open standard for connecting AI applications to external data sources, tools, and systems...
Standards, conventions, and struct tag reference for models
Use this skill when coordinating multiple AI models (Claude, GPT, Gemini, DeepSeek) for competitive trading analysis, ru...
Decide when to use cheaper, local, or frontier models and how to measure cost tradeoffs. Use for token limits, model rou...
Use only for an explicitly requested council of named models or agents with a judge. Ordinary review and brainstorming d...
LLM council/panel voting: multi-model coders, consensus rules, inter-rater agreement (kappa, alpha), correlated-error di...
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...
Design and build database schemas and data models in MotherDuck. Produces a file-based project scaffold. Use when creati...
Debug and diagnose model errors in Pollinations services. Analyze logs, find error patterns, identify affected users. Fo...
Generates code that deploys fine-tuned models from SageMaker Serverless Model Customization to SageMaker endpoints or Be...
Deploy trained machine learning models as production-ready services using REST APIs, containers, serverless functions, a...
Deploy ML models with FastAPI, Docker, Kubernetes. Use for serving predictions, containerization, monitoring, drift dete...
Deploy a new LLM model via LiteLLM (GitOps) and/or Azure (Terraform + node backend), add it to the ai toolkit, create th...
This skill enables Claude to deploy machine learning models to production environments. It automates the deployment work...
Universal model detection and capability assessment for optimal cross-model compatibility
Model-Development standards for model development in Ml Ai environments.
MCMC diagnostics for Bayesian models including convergence assessment, effective sample size, divergences, and posterior...
Fetch current model names from AI providers (Anthropic, OpenAI, Gemini, Ollama), classify them into tiers (fast/default/...
Resolve Maigo role models and delegation from an explicitly selected profile and the current host's tools. Use before ro...
Detects LLM endpoints missing token caps, rate limits, or prompt-length bounds, enabling cost and resource exhaustion. U...
Detect model drift detector operations. Auto-activating skill for ML Deployment. Triggers on: model drift detector, mode...
Model Drift Detector - Auto-activating skill for ML Deployment.Triggers on: model drift detector, model drift detectorPa...
This skill should be used when the user asks to "create a model", "add a Django model", "create database table", "add en...
Advisory model escalation based on task outcome tracking
Automatic model switching based on task complexity for OpenClaw agents. Dynamically escalates between Haiku (simple), So...
Renamed to /model-assessment in v6 (removed in v7).
Generates python code that evaluates SageMaker models. Supports two evaluation types: LLM-as-Judge and Custom Scorer. Us...
This skill focuses on comprehensive evaluation of machine learning models across the entire ML lifecycle. It covers metr...
LLM evaluation methodology — side-by-side comparison, domain-specific benchmarking, regression detection for fine-tuned...
Every metric encodes an opinion about which mistake hurts.
Automated reproduction of comprehensive model evaluation benchmarks following the Benchmark Suite V3. Auto-activates for...
Skill from rysweet/AzureHayMaker
Build model evaluation metrics operations. Auto-activating skill for ML Training. Triggers on: model evaluation metrics,...
Model Evaluation Metrics - Auto-activating skill for ML Training. Triggers on: model evaluation metrics, model evaluatio...
Comprehensive ML model evaluation with multiple metrics, cross-validation, and statistical testing. Activates for "evalu...
Evaluate and compare ML model performance with rigorous testing methodologies
Managing ML experiments, metrics, parameters, and artifacts using MLflow, Weights & Biases, and best practices for repro...
Techniques and tools for understanding how machine learning models make decisions and explaining those decisions to stak...
Build model explainability tool operations. Auto-activating skill for ML Training. Triggers on: model explainability too...
Model interpretability and explainability using SHAP, LIME, feature importance, and partial dependence plots. Activates...
Model Export Helper - Auto-activating skill for ML Deployment. Triggers on: model export helper, model export helper Par...
Assist with model export helper operations. Auto-activating skill for ML Deployment. Triggers on: model export helper, m...
Guidance for extracting weight matrices from black-box ReLU neural networks using only input-output queries. This skill...
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。
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。
Modellfehler aus Straßenfotos, run weekly by a scheduled task (or by hand): put recent Panoramax street photos beside re...
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...
Two-phase reasoning paradigm that reduces hallucinations and constraint violations in complex planning tasks. Use when t...
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...
Explicit model-selection preflight only. Budget-minded advice for the whole submitted task; recommend available model/ef...
Explicit model-selection preflight only. Budget-minded advice for the current stage of a justified staged workflow; reco...
Explicit model-selection preflight only. Conservative advice for the whole submitted task; recommend available model/eff...
Explicit model-selection preflight only. Conservative advice for the current stage of a justified staged workflow; recom...
Budget guard for top-tier expensive models (Claude Code Fable, Codex astra): keeps one session from burning the whole pl...
Automatically repair code violations of temporal properties using model-checking counterexamples as guidance. Use when w...
Emit the agent's tier, model, and effort as a table before any other action.
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...
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、...
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 →...
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...
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...
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 /...
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...
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 -...
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...
Interpret ML model predictions using SHAP, LIME, attention visualization, and probing techniques. Use when explaining mo...
"Make it interpretable" is four different requests.
Review an AI system for model inversion attacks that reconstruct training data from model outputs, and membership infere...
Generate a 3D model (GLB mesh) from a text description or a reference photo via Tripo. Textured or bare geometry, polygo...
CLI commands to add, update, list, and deprecate AI models in the database. Triggers on "add model", "new model", "updat...
Test, validate, and add new AI models to the eval suite. Use when user asks to add new models, test model access, check...
Use when building any system that involves AI/model calls - integrates with brainstorming, planning, and TDD to ensure m...
Merge multiple fine-tuned models using mergekit to combine capabilities without retraining. Use when creating specialize...
Plan the migration of an LLM feature from one model to another without breaking production. Use when a model is being de...
Break down Claude Code usage by model family (Opus / Sonnet / Haiku) from the Agent Monitor dashboard — each family's sh...
Professional Model Monitor Expert skill. Integrate LLM API workflows, safe system prompt guidelines, and agentic workflo...
Monitor model performance, detect data drift, concept drift, and anomalies in production using Prometheus, Grafana, and...
The layers trade timeliness against definitiveness.
Entity and model patterns with JSON serialization, immutability, and equality
Run this before anything else.
Produce a first security model for a project that has none: draft it with `<governance-body>` (draft-first, provenance-t...
Resolve model profile (quality/balanced/budget) at orchestration start and map agents to specific models. Enables cost/q...
Audit the global agent configuration (CLAUDE.md / AGENTS.md, rules, settings, behavioral plugins) against the current of...
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...
Use when the user names a specific ML model (e.g. DINOv3, SAM 2, Whisper, Qwen2-VL) and wants its real/official code, tr...
Configure Claude Code to use alternative AI model providers by setting up custom API endpoints and authentication. Use t...
Model Pruning Helper - Auto-activating skill for ML Deployment. Triggers on: model pruning helper, model pruning helper...
Model Pruning Helper - Auto-activating skill for ML Deployment.Triggers on: model pruning helper, model pruning helperPa...
Independent model QA expert who audits ML and statistical models end-to-end - from documentation review and data reconst...
Build model quantization tool operations. Auto-activating skill for ML Deployment. Triggers on: model quantization tool,...
Model Quantization Tool - Auto-activating skill for ML Deployment. Triggers on: model quantization tool, model quantizat...
Model Quantization Tool - Auto-activating skill for ML Deployment.Triggers on: model quantization tool, model quantizati...
Building database queries with the Options API
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。
Analyze chatmode or prompt files and recommend optimal AI models based on task complexity, required capabilities, and co...
Recommend the right AI model for a task by scoring candidates across six dimensions (Reasoning, Engineering, Speed, Brea...