MLOps
模型部署、评估与运维
economic-order-quantity
kishorkukreja
When the user wants to calculate optimal order quantities, minimize total inventory costs using EOQ models, or determine the economic lot size. Also use when the user mentions "EOQ," "Wilson formula," "economic lot size," "order quantity optimization," "production batch size," "quantity discounts," "EPQ" (Economic Production Quantity), "backorder models," or "reorder point calculations." For multi-echelon systems, see multi-echelon-inventory. For stochastic models, see stochastic-inventory-models.
computer-vision-warehouse
kishorkukreja
When the user wants to apply computer vision in warehouses, detect defects, track packages, count inventory, or automate visual inspection. Also use when the user mentions "computer vision," "image recognition," "object detection," "barcode reading," "package tracking," "quality inspection," "YOLO," "RCNN," "image classification," or "warehouse automation with vision." For general ML, see ml-supply-chain.
automotive-supply-chain
kishorkukreja
When the user wants to optimize automotive manufacturing supply chains, manage tier suppliers, implement JIT production, or handle automotive-specific logistics. Also use when the user mentions "automotive manufacturing," "OEM supply chain," "tier 1/2/3 suppliers," "sequenced parts delivery," "just-in-time automotive," "vehicle assembly," or "automotive aftermarket." For general manufacturing, see production-scheduling. For lean principles, see lean-manufacturing.
constraint-programming
kishorkukreja
When the user wants to solve complex scheduling, allocation, or combinatorial problems using constraint programming (CP). Also use when the user mentions "constraint programming," "CP-SAT," "constraint satisfaction," "all-different constraint," "global constraints," "propagation," "search strategies," or when the problem has complex logical constraints, scheduling with disjunctive resources, or allocation problems. For MIP, see optimization-modeling. For metaheuristics, see metaheuristic-optimization.
energy-logistics
kishorkukreja
When the user wants to optimize energy supply chains, coordinate oil and gas logistics, or manage energy infrastructure. Also use when the user mentions "energy transportation," "pipeline management," "energy distribution," "oil and gas supply chain," "LNG logistics," "petroleum logistics," "energy asset management," or "energy infrastructure." For renewable energy, see renewable-energy-planning. For power grids, see power-grid-optimization.
chai1
HughYau
Structure prediction for protein, nucleic-acid, and small-molecule complexes with the Chai-1 foundation model (Chai Discovery 2024, github.com/chaidiscovery/chai-lab). Reach for this skill to predict an antibody-antigen or protein-ligand complex from a single FASTA, to re-fold designed binders as an AlphaFold-multimer alternative, or to drive co-folding from Python for batched campaigns on a GPU.
assembly-line-balancing
kishorkukreja
When the user wants to balance assembly lines, assign tasks to workstations, calculate takt time, or optimize line efficiency. Also use when the user mentions "line balancing," "workstation assignment," "takt time," "cycle time balancing," "precedence constraints," "task allocation," "assembly line optimization," "mixed-model balancing," or "U-shaped line." For process optimization, see process-optimization. For production scheduling, see production-scheduling.
frontend-design
b1rdmania
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics.
demand-forecasting
kishorkukreja
When the user wants to forecast demand, build forecasting models, or improve forecast accuracy. Also use when the user mentions "demand planning," "sales forecasting," "time series," "forecast accuracy," "demand sensing," "statistical forecasting," or "predictive analytics." For capacity planning based on forecasts, see capacity-planning. For S&OP integration, see sales-operations-planning.
fuel-distribution
kishorkukreja
When the user wants to optimize retail fuel distribution, manage gasoline and diesel delivery, or plan petroleum product logistics. Also use when the user mentions "gas station supply," "fuel delivery routing," "petroleum retail," "tank truck scheduling," "fuel terminal operations," "wholesale fuel distribution," or "retail fuel network." For upstream, see drilling-logistics. For midstream, see energy-logistics.
unforce-model
weave-os
"Clear the active Weave Router model pin for this Codex session."
router-models
weave-os
"List the models the Weave Router may route to, and turn them on or off."
fm
weave-os
"Alias for force-model — pin this Codex session to a specific model through the Weave Router."
ufm
weave-os
"Alias for unforce-model — clear the active Weave Router model pin."
force-model
weave-os
"Pin this Codex session to a specific model through the Weave Router."
external-agents
kylesnowschwartz
Invoke external AI CLIs (Codex, Gemini) for second opinions, code reviews, or alternative analysis. This skill SHOULD be used when the user asks for a "second opinion", "outside review", says "ask codex", "ask gemini", "run codex", "run gemini", "get another AI's take", or needs verification from a different model.
ask
doodledood
Single-model consultation using consultant agent. Defaults to gpt-5.2-pro.
ask-council
doodledood
Multi-model ensemble consultation. Runs 3 models in parallel for diverse perspectives.
compress-prompt
doodledood
'Compresses prompts/skills into minimal goal-focused instructions. Trusts the model, drops what it already knows, maximizes action space. Use when asked to compress, condense, or minimize a prompt.'
Causal Inference
aj-geddes
Determine cause-and-effect relationships using propensity scoring, instrumental variables, and causal graphs for policy evaluation and treatment effects
capacity-planning
aj-geddes
Analyze team capacity, plan resource allocation, and balance workload across projects. Forecast staffing needs and optimize team utilization while maintaining sustainable pace.
near-ai-cloud
near
NEAR AI Cloud private inference and verification. Use when integrating NEAR AI Cloud API for verifiable private AI inference, verifying model or gateway TEE attestation (NVIDIA NRAS, Intel TDX), verifying chat message signatures, implementing end-to-end encrypted chat, or using the OpenAI-compatible API with NEAR AI Cloud.
creating-dbt-models
AltimateAI
Creates dbt models following project conventions. Use when working with dbt models for: (1) Creating new models (any layer - discovers project's naming conventions first) (2) Task mentions "create", "build", "add", "write", "new", or "implement" with model, table, or SQL (3) Modifying existing model logic, columns, joins, or transformations (4) Implementing a model from schema.yml specs or expected output requirements Discovers project conventions before writing. Runs dbt build (not just compile) to verify.
refactoring-dbt-models
AltimateAI
Safely refactors dbt models with downstream impact analysis. Use when restructuring dbt models for: (1) Task mentions "refactor", "restructure", "extract", "split", "break into", or "reorganize" (2) Extracting CTEs to intermediate models or creating macros (3) Modifying model logic that has downstream consumers (4) Renaming columns, changing types, or reorganizing model dependencies Analyzes all downstream dependencies BEFORE making changes.