В каталоге 183 730 навыков в 14 категориях.
Use this when authoring or refactoring slices with createSlice, selectors, create.asyncThunk, entity adapters, or lazy r...
Use this when deciding whether data belongs in Redux, component state, router state, or another external source. Covers...
Centralized management of machine learning models throughout their lifecycle, including versioning, metadata, and produc...
Centralized model versioning, staging, and lifecycle management. Activates for "model registry", "model versioning", "mo...
Curated download URLs and target directories for every model the comfyui-mcp skills reference — checkpoints, VAEs, text...
Guide for maintaining the MassGen model and backend registry. This skill should be used when adding new models, updating...
Manage model registry manager operations. Auto-activating skill for ML Deployment. Triggers on: model registry manager,...
Model Registry Manager - Auto-activating skill for ML Deployment.Triggers on: model registry manager, model registry man...
Releases a model version: checks approvals, tags code, data and parameters, updates the registry and writes release note...
Use this skill when gathering requirements for new BigQuery data models OR when asked to edit existing queries in bqetl....
Research and configure new/custom AI models not yet in models.dev. Use when user mentions a new model release, asks to a...
Model Risk Management (MRM) is a framework designed to manage the risk of adverse consequences resulting from decisions...
Choose model tier by task complexity. Keep routine work cheap. Escalate only when required.
Classifie une demande en tier de complexité (T1 simple, T2 standard, T3 complexe) avec un score 0-100, choisit l'alias d...
Pick the cheapest Claude tier (haiku / sonnet / opus / fable) that can do a task correctly, using Jev (TypeSafe System O...
Use when route AI model requests to the optimal provider based on task, cost, latency, and capability requirements. Mana...
为小说写作、翻译、编辑或研究选择已配置的模型,或者制作跨模型任务交接包。适用于 CLI 模型选择、人工盲比和 Grok Bot 交接。
Choose the best Renoise image, video, or audio model and write prompts for it. Always use before any Renoise generation...
Intelligent model selection - routes tasks to Haiku (fast/cheap), Sonnet (balanced), or Opus (complex/strategic) based o...
Model selection strategy for subagents — haiku for exploration, sonnet for implementation, opus for architecture/securit...
Use when this session is about to dispatch another one — an implementer, a review collector and its lenses, a comments a...
Choose default fal.ai endpoint IDs for genmedia production skills. Use this with commercial, marketing, ugc, character-d...
Heuristics for choosing the right model tier (haiku/sonnet/opus) when delegating to agents. Loaded by orchestrating comm...
Intelligent model selection (Opus/Sonnet/Haiku) based on task complexity and chamber
Model routing configuration templates and strategies for cost optimization, speed optimization, quality optimization, an...
Use when the operator explicitly wants to customise the native Codex model-capability-router policy.
Estimate the dollars saved by routing eligible Claude Code work to a cheaper model family, using the Agent Monitor prici...
Review model vs database schema consistency on ndestates-io using the local cache and project tooling. Use before/after...
Use when choosing the model for a medical-imaging study. Picks a paper-grounded architecture family (CNN/ViT, U-Net/nnU-...
Selects a base model for the user's use case by querying SageMaker Hub. Use when the user asks which model to use, wants...
Select an AI model for a real workload using representative evaluations, current official capability and pricing data, l...
Plan which model tier handles which work BEFORE execution begins — a high-cognition model deeply understands the problem...
Use when choosing which LLM to use for a task. Covers matching capability to task, cost and latency trade-offs, routing...
Automatically applies when choosing LLM models and providers. Ensures proper model comparison, provider selection, cost...
Choose the right LLM for a task by trading off quality, cost, latency, and constraints. Use when asked which model to us...
Select the best local Ollama model for a task and emit tuning presets. Use when choosing between reasoning, creative, fa...
当使用者说“这题该用什么模型”“A 和 B 哪个更合适”“要不要上机器学习”“我的模型选得对吗”时使用。基于已拆清的目标、变量、数据与验证条件,区分模型家族、算法和求解器,建立简单基线,比较至少两个有意义的候选,并给出条件式推荐与最低成本判...
根据用户的视频需求(场景、时长、音频、语言、平台限制、预算、是否需要本地部署/角色一致性等),从 16 个主流 AI 视频模型(12 商业 + 4 开源)中推荐最匹配的 1-3 个,并解释为什么。覆盖商业:Seedance 2.0、Happ...
Vergleicht verfügbare LLM-Modelle (Nous Portal) und hilft beim Auswählen des richtigen Modells für die jeweilige Aufgabe...
LLM and ML model deployment for inference. Use when serving models in production, building AI APIs, or optimizing infere...
Ship ML models to production: versioning, eval-gated serving, GPU efficiency, monitoring for drift. Use when a model lea...
Deploy and query Databricks Model Serving endpoints. Use when (1) deploying MLflow models or AI agents to endpoints, (2)...
Use when deploying a trained model behind an API. Covers FastAPI inference services, loading artifacts safely, request v...
Audits model-serving APIs, administrative and debug surfaces, vector stores, object storage, caches, workload identity,...
Model serving is the process of deploying ML models to production and handling inference requests efficiently at scale.
Deploy ML models on Kubernetes with KServe (formerly KFServing) and NVIDIA Triton Inference Server. Includes canary depl...
Review a model serving layer for API gateway misconfiguration, rate limit bypass, inference DoS through token exhaustion...
Give the same motion brief to three AI models, keep each first try, render all three the same way and stack them into on...
Create Pydantic v2 data models with validation, type hints, and proper configuration. Use when designing data structures...
Renamed to /model-selection in v6 (removed in v7).
Writes the model specification: equations, timing, closures, steady state, shocks, observables and known limitations.
Control model behavior through persistent edits and steering interventions. Use when modifying model outputs, applying s...
Multi-model orchestration and model-switching strategy. Score-based model selection, reasoning-effort routing, cross-age...
Secure the AI model supply chain with artifact signing, provenance attestation, SBOM workflows, dependency controls, and...
Review a model acquisition and deployment pipeline for poisoned base models, unsafe fine-tunes, trojaned adapters, unver...
Switch the agent's model at runtime and restart. Use when the user asks to change models (e.g., "switch to kimi", "use o...
Route substantial work to suitable models and reasoning effort at intake, expensive phases, handoffs, scope changes and...
タスクの複雑さに応じて Claude のモデルを自動的に切り替える。複雑なタスク(アーキテクチャ設計、大規模リファクタリング、難解なバグ修正)では opus を、単純なタスク(小さな修正、フォーマット、簡単な質問)では sonnet を自動...
ML 모델 파일 서버 간 동기화. "모델 동기화", "모델 배포", "rsync 모델", "서버로 전송" 요청 시 활성화됩니다.
Detects inference endpoints without authentication or throttling, allowing model weight reconstruction. Use when writing...
MANDATORY tracking protocol for multi-model validation. Creates structured tracking tables BEFORE launching models, trac...
模型训练-推理-组合回测-专业报告 全流程 — 提交T+N周期模型训练(13种模型类型:lightgbm/xgboost/catboost/random_forest/linear/mlp/gru/lstm/alstm/transforme...
用于诊断 PyTorch on NPU 大模型训练中的 NPU OOM(Out of Memory)问题。当用户报告训练因内存不足崩溃、出现 OOM 相关错误(OutOfMemoryError / NPU out of memory / w...
This skill should be used when users want to train or fine-tune language models using TRL (Transformer Reinforcement Lea...
Model training is the process of teaching machine learning models to make predictions or decisions based on data. This s...
QuantMind 模型训练配置文件生成器:把自然语言需求(市场/周期/模型/因子/超参/时间切分)转成前端『模型训练 → 导入配置』可直接导入的 quantmind-model-training-config 文件(YAML/JSON,....
Dress a model in a real garment or accessory from a flat-lay, hanger or mannequin photo (on-model / virtual try-on) whil...
Refresh a published security model from the project's decision history (tracker dispositions, advisories, canned respons...
Checklist for changing the default Copilot coding agent model. Use when upgrading from one model to another (e.g. gpt-5....
Summarize CodexBar local cost logs by model for Codex or Claude, including current or full breakdowns.
Use CodexBar CLI local cost usage to summarize per-model usage for Codex or Claude, including the current (most recent)...
Step-by-step guidance for model usage.
Summarize per-model usage and costs from CodexBar local data.
Working with model instances and fields
使用 CodexBar CLI 本地成本使用情况来汇总 Codex 或 Claude 的按模型使用情况,包括当前(最新)模型或完整的模型细分。当被要求提供 codexbar 的模型级别使用/成本数据,或需要从 codexbar cost J...
Renamed to /model-assessment in v6 (removed in v7).
Holds a proposed model, stage set or grouping against what actually happened and reports whether it would have got the r...
Qualify a Genesis routing model or compare a candidate against an incumbent using the isolated qualification runner, app...
Add comprehensive validation to Django models using validators, clean methods, and constraints. Use when implementing mo...
Check a published security model per repository: is it reachable via `AGENTS.md` → `SECURITY.md` at a named commit, and...
Model-trader version compatibility protocol: Embed version metadata in checkpoints, validate at load time. Trigger when:...
Model versioning is practice of tracking and managing different versions of machine learning models throughout their lif...
Model Versioning Manager - Auto-activating skill for ML Deployment. Triggers on: model versioning manager, model version...
Model Versioning Manager - Auto-activating skill for ML Deployment.Triggers on: model versioning manager, model versioni...
Review AI systems for model theft, unauthorized redistribution, and IP leakage using watermarking, fingerprinting, and b...
Skill especializada en modelado de escenarios para Domain Storytelling, enfocada en capturar el "happy path" (80% de cas...
Conjunto de herramientas de modelado estadístico y econometría para Python que admite regresión lineal, modelos lineales...
Modela dependencias causais do enredo como DAG de metas narrativas com propagacao de inconsistencias e deteccao de ciclo...
Use quando termos de produto estão ambíguos, uma relação de domínio muda ou uma decisão estrutural precisa ser registrad...
Archived skill guidance for modelagem-dominio.
Estrutura elementos do universo ficcional (personagens, faccoes, locais, itens) em uma ontologia de grafos flexivel com...
Modelica acausal equation-based multi-domain modeling via Wolfram Language. Chemputation-native simulation with automati...
当使用者说“帮我写模型假设”“这些假设合理吗”“方程里藏了哪些前提”“这些模型假设怎么检验”时使用。把题面事实、定义、校准选择、数值近似与真正假设分开,建立带类型、理由、作用域、失效后果、承重性和反证测试的假设登记表,并检查量纲、守恒、边界...
当使用者说“按我的模型写代码”“把方程实现成 Python/MATLAB/R”“调试这段建模代码”“补验证和灵敏度分析”“让结果可复现”时使用。只实现学生已确认的模型与数据契约,先写实现合同、手算小例、不变量和验收矩阵,再按读取、变换、求解...
Design analytics data models using dimensional modeling — star and snowflake schemas, fact and dimension tables, grain d...
Use when you need to work with NoSQL data modeling.This skill provides NoSQL database design with comprehensive guidance...
当使用者贴出数学建模题、数学建模竞赛题、研究问题或评分要求,说“帮我拆题”“这道题到底要什么”“有哪些隐含条件”“先别急着选模型”时使用。把原题整理成可核对的题面契约、变量与单位账本、子问题依赖图、歧义清单和下一步交接;区分原题事实、合理推...
Guides a short threat model for a design: naming the assets, trust boundaries, and entry points it creates or changes, a...
Deploy OpenCTI (Filigran) via Docker Compose and use the pycti Python client to model threat actors, intrusion sets, cam...
Integrate the Modellix API/CLI for async AI image, video, and speech generation or transcription (model run --wait, task...