AGENT SKILL

foundation-models-embeddings-vlms

Route GeoAI foundation models, embeddings, DINOv3, Prithvi, UniverSat, TESSERA, Moondream, vLLM, and caption workflows.

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

01 前言 Front Matter

name
foundation-models-embeddings-vlms
license
MIT
metadata
{ "disco-role": "operating" }
description
Route GeoAI foundation models, embeddings, DINOv3, Prithvi, UniverSat, TESSERA, Moondream, vLLM, and caption workflows.
disable-model-invocation
true

02 资源文件 4

03 SKILL.md 正文

Foundation models, embeddings, and VLMs

Use this sub-skill when the task centers on GeoAI foundation-model registry lookup, precomputed embeddings, DINOv3 similarity, Prithvi, UniverSat, TESSERA, AlphaEarth/Google satellite embeddings, Moondream, vLLM geospatial VLMs, or BLIP/spaCy captioning.

Route here

  • Foundation model discovery, registry filtering, TerraTorch-backed model loading decisions, or model-name normalization.
  • Existing embedding dataset analysis, clustering, similarity search, lightweight classifiers, or embedding GeoTIFF export.
  • DINOv3 patch similarity, feature-map visualization, and DINOv3 workflow selection.
  • Prithvi, UniverSat, TESSERA, AlphaEarth, Moondream, vLLM, and captioning API choice and preflight.

Route away

  • Generic training, broad fine-tuning, dataset layout validation, or DINOv3 segmentation training details: route to training-and-finetuning.
  • Segmentation/object-detection inference products and vectorized mask outputs: route to detection-segmentation-inference.
  • STAC search, NAIP/Overture downloads, raster tiling, CRS repair, or pipeline config prep: route to geospatial-data-pipelines.

Start points

Prefer metadata, optional-dependency probes, and existing embeddings first. Only load model weights, call Hugging Face, download embedding tiles, start a vLLM service, or run long inference when the user explicitly accepts those runtime costs.

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