Menu
SkillsMP has collected 8 skills from WenyuChiou/WAGF. Open a skill to review its source and details.
Showing 8 of 8 collected skills.
Verify the contract between WAGF/ABM agents and an external model (flood, hydrology, irrigation, seismic, catastrophe) — units, time steps, state mutation direction, feedback-loop double-counting. Use when the user says "check ABM-model coupling", "audit…
Walk a researcher through designing the LLM-external-model interface for a WAGF domain using the v0.6 coupling layer. Use when the user says "I want to couple my LLM agents to <my simulator>", "help me design the WAGF interface", "scaffold the external model…
Walk a researcher (PhD, collaborator, lab-mate) through building their first WAGF domain — from "I have a research question + maybe an external model" to "I have a working WAGF experiment producing audit traces." Conducts a structured S0-S7 interview, invokes…
First-time WAGF setup walkthrough — environment check, smoke test, first experiment, and handoff to the lifecycle skills. Use when the user says "I just cloned WAGF", "set up WAGF", "first WAGF run", "I'm new to this", "where do I start with WAGF", or opens a…
Use when a WAGF user asks to test a new domain end to end, run the smoke pipeline, decide whether a domain is done, continue after a domain runs, or verify a WAGF setup before experiment design or reproducibility audit.
Turn raw WAGF audit traces (household_governance_audit.csv + raw/*.jsonl) into paper-ready governance metrics — IBR, EHE, rejection taxonomy, retry outcomes, model-condition comparisons. Use when the user says "analyze these traces", "compute governance…
Verify another researcher can reproduce a WAGF experiment — manifests, seeds, configs, runnable commands, data provenance vs git blame, figure-script outputs match references. Use when the user says "audit reproducibility", "prepare for submission", "check…
Turn a WAGF research question into a reproducible experiment matrix (model × governance × seed × metric × artefact path). Use when the user says "design an experiment", "plan an ablation", "compare strict vs disabled", "set up cross-model evaluation", or…