AGENT SKILL

analysis-experiments

Collect Mesa experiment data, run scenario sweeps, and use experimental actions, states, signals, and meta-agent analysis helpers.

License 许可
Apache-2.0
最近更新
2026-09-03
Stars
★ 351
Forks
27

01 前言 Front Matter

name
analysis-experiments
license
Apache 2.0
metadata
{ "disco-role": "operating" }
description
Collect Mesa experiment data, run scenario sweeps, and use experimental actions, states, signals, and meta-agent analysis helpers.
disable-model-invocation
true

02 资源文件 5

03 SKILL.md 正文

Analysis Experiments

Use this sub-skill when a Mesa task is about experiment outputs, scenario orchestration, or experimental analysis helpers rather than basic model structure or visualization.

Use for

  • DataCollector reporters, model / agent / agent-type DataFrames, and manual tables.
  • Experimental mesa.experimental.data_collection datasets, registries, and recorders.
  • Experimental Scenario, RunConfiguration, run_scenarios, stores, statuses, and failure diagnostics.
  • Experimental timed Action lifecycles, continuous states, thresholds, reactive signals, and batching.
  • Experimental MetaAgent grouping utilities for higher-order agent analysis.

Start here

  • API reference for signatures, import paths, return shapes, and stability notes.
  • Workflows for copyable collection, recorder, scenario, signal/state/action, and meta-agent recipes.
  • Troubleshooting for reporter validation, recorder setup, scenario failure origins, pickling, and experimental API pitfalls.
  • DataCollector smoke script for a safe installed-package check that emits JSON summaries.
  • Scenario smoke script for a safe installed-package check of Scenario, RunConfiguration, run_scenarios, and failure recording.

Route elsewhere

  • Core Model, Agent, AgentSet, activation, RNG, and event scheduling basics: model-core
  • Spatial placement, movement, grids, networks, cells, or continuous-space geometry: spaces
  • Solara dashboards, browser visualization, plotting widgets, charts, or rendering: visualization

All APIs under mesa.experimental are experimental and may change between Mesa releases. Treat this sub-skill as the self-contained operating reference; no external repository files are required at runtime.

04 同仓库更多 Skills

VectorSpaceLab
VectorSpaceLab/AREX-Skill

passnet-triton-opt

Make a single PassNet Triton kernel fast AND numerically faithful: performance model (when a replacement can win at all), block/grid/warp tuning, autotune policy, launch overhead, and per-op numeric recipes to pass the dtype baseline tolerances. Use when a pass matches and is correct but speedup below expected, or when correctness fails by small numeric margins.

★ 351
VectorSpaceLab
VectorSpaceLab/AREX-Skill

passnet-solve

END-TO-END playbook for solving one PassNet sample: analyze the computation graphs, decide the optimization strategy (what to fuse, what to replace, what to leave alone), drive the iteration loop, and maximize the sample score. This is the ENTRY skill — invoke it first for any PassNet optimization task; it tells you when to use passnet-pattern-fusion, passnet-triton-opt and passnet-feedback.

★ 351
VectorSpaceLab
VectorSpaceLab/AREX-Skill

passnet-skill

PassNet GPU kernel optimization via compiler passes. Design and implement Triton-based optimization passes, create pass files under ./pass_dir/, self-evaluate with pass_evaluator, and iterate to maximize GPU speedup.

★ 351
VectorSpaceLab
VectorSpaceLab/AREX-Skill

passnet-pattern-fusion

Author PassNet pass files: write patterns that actually MATCH the FX graph, pick fusion regions (which ops to absorb into one Triton kernel), and structure multi-pass submissions with the mandatory shared-dispatch architecture. Use when creating or fixing pattern()/replacement_args()/replacement_func() files, when a pass "failed to match", or when deciding how to fuse multiple kernels/ops.

★ 351
VectorSpaceLab
VectorSpaceLab/AREX-Skill

passnet-orchestrate

Round/batch planning and decision support for PassNet graph optimization. Use for multi-sample triage, worker allocation, eval-budget policy, and post-eval keep/revert decisions. For solving one concrete sample end to end, use passnet-solve as the entry skill; consult this skill only when you need broader planning or a specific decision gate.

★ 351
VectorSpaceLab
VectorSpaceLab/AREX-Skill

passnet-feedback

Fast, deterministic feedback for PassNet work: pre-flight pattern/match verification WITHOUT burning a GPU evaluation, per-node bottleneck analysis of a sample's graphs, and eval-log parsing into per-variant status + estimated score + failure classification. Use BEFORE every GPU evaluation (check_pattern), at the START of a sample (analyze_graph), and AFTER every evaluation (parse_eval_log).

★ 351