Audit AIOS skills for their model-preference group callout and assign or refresh it — add a "Model preference" line to skills that lack one, change the group where behavior should…
Test which model the model-preference config actually resolves to per group, and (in live mode) spawn small test agents by group name to confirm the spawn honors it.
Audit every LLM provider's official pricing page against the `model_prices` table and ship the diff as a migration.
Использовать для первичной сборки, наполнения или расширения производственной системы в готовом каноническом шаблоне из принятых определений и проверяемых свидетельств.
Resolve model profile (quality/balanced/budget) at orchestration start and map agents to specific models.
Reduce LLM size and accelerate inference using pruning techniques like Wanda and SparseGPT. Use when compressing models without retraining, achieving 50% sparsity with mi — from…
Analyze chatmode or prompt files and recommend optimal AI models based on task complexity, required capabilities, and cost-efficiency — from general/general-misc
Curated download URLs and target directories for every model the comfyui-mcp skills reference — checkpoints, VAEs, text encoders, LoRAs — organized by family (Flux, WAN, LTX,…
Centralized model versioning, staging, and lifecycle management. Activates for "model registry", "model versioning", "model staging", "deploy to production", "rollback model",…
Model Release und Persönlichkeitsrechte prüfen: Nutzungsumfang, Territory, Dauer, Buyout, Social Media, KI-Nutzung, Retusche und Widerruf im Fashion Law Moderecht.
Scans your codebase for hardcoded AI model references, identifies context-window assumption violations, assesses fallback coverage, and generates a compliance-risk report with a…
Design a model router that sends each LLM request to the cheapest model that can handle it and escalates only the hard cases to the strongest — cutting cost and latency without…
Route model requests based on configured models, costs and task complexity. Use for routing general/low-complexity requests to the cheapest available model and for…
Loaded when user builds multi-model pipelines (Haiku/Sonnet/Opus). Covers cost-optimized routing, escalation, sub-agent delegation, and fallback chains.
模型路由工具(专业版)面向团队与企业,在三层路由决策基础上,扩展成本分析仪表盘、批量任务分发、自定义路由规则、实时监控告警与团队策略治理能力。核心能力: - 三层路由 + 自定义规则引擎 - 成本仪表盘:按任务/项目/团队追踪成本 - 批量任务分发与并发路由 - 实时监控:超预算告警、异常路由检测 - 团队策略:路由白名单、降级策略、成本上限 -…
Create or refresh this developer's user-global model-routing rubric — the file that decides which model does which work (cheap models for bulk/mechanical work, the strongest for…
Estimate the dollars saved by routing eligible Claude Code work to a cheaper model family, using the Agent Monitor pricing engine.
Scan LLM provider APIs for available models, fetch official docs for specs (parameters, context windows, capabilities, pricing), save timestamped doc snapshots, and optionally…
Automatically applies when choosing LLM models and providers. Ensures proper model comparison, provider selection, cost optimization, fallback patterns, and multi-model s — from…
Choose the right LLM for a task by trading off quality, cost, latency, and constraints. Use when asked which model to use, whether to upgrade/downgrade a model, how to cut LLM…
Automatically applies when choosing LLM models and providers. Ensures proper model comparison, provider selection, cost optimization, fallback patterns, and multi-model s — from…
Automatically applies when choosing LLM models and providers. Ensures proper model comparison, provider selection, cost optimization, fallback patterns, and multi-model s — from…
Set and manage the preferred backbone LLM for compatible AI-agent workflows. Supports manual model selection, automatic best-model selection based on task type, and a…
Model-specific prompt engineering guidelines for major LLMs. 主要 LLM 之模型專屬提示工程指引。 Use when: targeting specific model family, avoiding model-specific anti-patterns, selecting…
Model an illustrative net staking APR and annual reward — clearly NOT financial advice. Reach for this on a yield or reward question.
Control model behavior through persistent edits and steering interventions. Use when modifying model outputs, applying steering vectors, or creating persistently modified — from…
Control model behavior through persistent edits and steering interventions. Use when modifying model outputs, applying steering vectors, or creating persistently modified — from…
Multi-Modell Orchestrierung und Model-Switching Strategie. Score-basierte Modellauswahl, Cross-Agent-Delegation (Gemini, Codex, Ollama), Advisor-Pairing, Eskalations-Trigger,…
Switch the primary inference model used by the agent loop. Use when the user says "/model " or "switch to ", or asks which model is active.
模型切换工具(专业版)面向团队与企业,在三层Claude模型切换基础上,扩展成本分析仪表盘、批量任务分发、自定义切换规则、实时监控告警与团队策略治理能力。核心能力: - 三层切换 + 自定义规则引擎 - 成本仪表盘:按任务/项目/团队追踪成本 - 批量任务分发与并发切换 - 实时监控:超预算告警、异常切换检测 - 团队策略:切换白名单、降 — from…
模型切换工具(专业版)面向团队与企业,在三层Claude模型切换基础上,扩展成本分析仪表盘、批量任务分发、自定义切换规则、实时监控告警与团队策略治理能力。核心能力: - 三层切换 + 自定义规则引擎 - 成本仪表盘:按任务/项目/团队追踪成本 - 批量任务分发与并发切换 - 实时监控:超预算告警、异常切换检测 - 团队策略:切换白名单、降 — from…
Execute an approved model task plan through Microsoft Foundry, Hugging Face, or ElevenLabs and record provider evidence.
How agent runtimes dynamically route prompts across Flash/Haiku, Sonnet/GPT-4o, and o1/Reasoning tiers based on task complexity, reducing aggregate API bills by 75%.
Assign the right model tier to each job — expensive brains plan and judge, cheap hands search and grind.
Use when spawning agents (Agent tool, agent-team teammates, Workflow/ultracode agent() calls) and choosing the model parameter, when the tier-policy hook denies a workflow script,…
Improve the auto-parallelism advisor and training configuration logic. Use when optimizing parallelism search, fixing throughput heuristics, or updating mutating webhook defaults…
Update financial models with new data — quarterly earnings, management guidance, macro changes, or revised assumptions.
Read-only audit of Pi routing and second-opinion consensus model IDs against the active Pi catalog and public live model metadata; reports when Pi or configured models merit…
Use CodexBar CLI local cost usage to summarize per-model usage for Codex or Claude, including the current (most recent) model or a full model breakdown.
Use CodexBar CLI local cost usage to summarize per-model usage for Codex or Claude, including the current (most recent) model or a full model breakdown.
Use CodexBar CLI local cost usage to summarize per-model usage for Codex or Claude, including the current (most recent) model or a full model breakdown.
Use CodexBar CLI local cost usage to summarize per-model usage for Codex or Claude, including the current (most recent) model or a full model breakdown.
Use CodexBar CLI local cost usage to summarize per-model usage for Codex or Claude, including the current (most recent) model or a full model breakdown.
Every LLM call goes through a single pinned model-ID env var. Pin bumps require typed-token confirmation.
Prüft Lizenzen für Modelle, Weights, Checkpoints, Inference-Code, Datasets und kommerzielle Nutzung im Softwarerecht De Eu Us.
Model selection strategy and routing. Use when choosing between models for different task types, subagent configurations, or optimizing token cost vs quality tradeoffs.
Model zamierzenia w JSON (działka, teren, sąsiedztwo, plan miejscowy, poziomy, legenda projektu, obiekty, moduły wnętrz, przekroje) jako jedyne źródło arkuszy, zestawień, DXF, GLB…
Skill especializada en modelado de escenarios para Domain Storytelling, enfocada en capturar el "happy path" (80% de casos) sin excepciones, eliminando condicionales y manteniendo…
Modela dependencias causais do enredo como DAG de metas narrativas com propagacao de inconsistencias e deteccao de ciclos.
Huawei Cloud ModelArts platform integration. Modular design, OBS as primary storage support, environment variable authentication, includes pool plugin management and node — from…
Build, view, update, delete and simulate structured business models for Pigment OSS.
Modelica acausal equation-based multi-domain modeling via Wolfram Language. Chemputation-native simulation with automatic conservation laws.
Direct the modeling subdomain — route prediction and forecasting questions to the right specialist skill, define the learning curriculum, and resolve conflicts between model…
Calculates bond pricing with duration, convexity, OAS, and Z-spread analysis. Use when pricing bonds, calculating risk metrics, or evaluating relative value.
Structures book-building analysis with demand tiers, allocation methodology, and price sensitivity assessment.
Builds cap table models with round-by-round dilution, option pool, and exit waterfall analysis. Use when modeling cap tables, calculating ownership dilution, or projecting exit…
Builds NPV, IRR, and payback models for capital investment decisions with hurdle rate calibration and risk adjustment.
Builds carbon credit models with offset generation analysis, verification costs, and market pricing dynamics for carbon-linked investments.
Builds CLO waterfall models with coverage tests, reinvestment criteria, and distribution allocation across tranches.
Structures earnout and contingent payment mechanisms with milestone definitions, measurement periods, and payout scenarios.