imagery-raster-analysis
Route imagery layers, raster function chains, raster analytics, multidimensional rasters, and orthomapping workflows.
- License 许可
- Apache-2.0
- 最近更新
- 2026-09-03
- Stars
- ★ 351
- Forks
- 27
01 前言 Front Matter
- name
- imagery-raster-analysis
- license
- Apache 2.0
- metadata
- { "disco-role": "operating" }
- description
- Route imagery layers, raster function chains, raster analytics, multidimensional rasters, and orthomapping workflows.
- disable-model-invocation
- true
02 资源文件 4
- 参考文档references/imagery-raster-workflows.md7.2 KB
- 参考文档references/raster-api-reference.md5.2 KB
- 参考文档references/troubleshooting.md4.5 KB
- 脚本scripts/raster_import_smoke.py5.4 KB
03 SKILL.md 正文
imagery-raster-analysis
Use this sub-skill for imagery and raster workflows that center on:
ImageryLayerand image-service access- raster functions and function chains
- raster analytics tools and persisted raster outputs
- multidimensional rasters
- orthomapping project, image collection, GCP, DSM, and orthomosaic workflows
Do not use this sub-skill for:
- learned model training or inference (
deep-learning) - map display basics or widget setup (
mapping-location-services) - feature layer / SEDF / spatial analysis (
features-dataframes-analysis)
Quick routing
- If you already have an image-service URL or imagery item, start with
ImageryLayer. - If you need on-the-fly visualization or band math, use raster functions.
- If you need server-side processing, saved outputs, or large data, use raster analytics.
- If you need UAV image collections, sensor models, seamlines, DSM/DTM, or orthomosaics, use orthomapping.
- If the target GIS lacks raster analytics or orthomapping support, stop and explain the missing service.
Preflight
- Confirm the target
GISor portal connection is authenticated. - Check
arcgis.raster.analytics.is_supported(gis)andarcgis.raster.orthomapping.is_supported(gis)before server-side work. - Inspect
ImageryLayer.properties.rasterFunctionInfosbefore applying a named function. - Use unique
output_namevalues for persisted raster jobs. - Treat
future=Trueand other async outputs as jobs or result objects, not immediate rasters. - In credential-free environments, keep to imports, signatures, and static reasoning only.
Read next
04 同仓库更多 Skills
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.
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.
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.
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.
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.
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).