agentleFS
isaaccorleyisaaccorley/geospatial-skills/skills/search-stac/SKILL.md

search-stac

Skill78 starsChanged 8 months agoApache-2.0View on GitHub

Search and download satellite imagery from Microsoft Planetary Computer. Browse available collections, search by bbox and time range, list assets, and download specific items.

  • Installs packages

1 other project uses a version of this, 1 of them edited.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

8 rules. About 0 are common, 3 are distinctive, and 5 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 5

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Follow these steps in order.

    line 16
  2. Very specific:

    If the input is list, collections, or asks "what is available": list collections.

    line 22
  3. Very specific:

    If a collection name and --bbox are provided: search for items.

    line 23
  4. Very specific:

    If --download is present: download items after searching.

    line 24
  5. Distinctive:

    If the user provided a filter keyword, pass it:

    line 36
  6. Very specific:

    If time_range was not specified, omit it or pass None.

    line 74
  7. Distinctive:

    If the user asks about available assets or bands for a specific item:

    line 78
  8. Very specific:

    Default output directory: ./stac_data/

    line 118

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

You are helping the user search and download satellite imagery from the Planetary Computer STAC catalog using geoai.

Input: $@

Follow these steps in order.

Step 1 -- Determine the action

Parse $@ to identify what the user wants:

  • If the input is list, collections, or asks "what is available": list collections.
  • If a collection name and --bbox are provided: search for items.
  • If --download is present: download items after searching.

Step 2 -- List collections (if requested)

python3 -c "
import geoai
df = geoai.pc_collection_list()
print(df.to_string())
"

If the user provided a filter keyword, pass it:

python3 -c "
import geoai
df = geoai.pc_collection_list(filter_by='FILTER')
print(df.to_string())
"

Report the available collections and stop (unless the user also specified a search).

Step 3 -- Search for items

Parse the collection name, bounding box (--bbox), and optional datetime range (--datetime).

The datetime range should be in the format YYYY-MM-DD/YYYY-MM-DD (start/end).

python3 -c "
import geoai

items = geoai.pc_stac_search(
    collection='COLLECTION',
    bbox=[MINX, MINY, MAXX, MAXY],
    time_range='TIME_RANGE',
    limit=LIMIT,
)
print(f'Found {len(items)} items')
print('---')
for item in items[:20]:
    assets = list(item.assets.keys())
    print(f'  {item.id}: {item.datetime} - assets: {assets}')
"

Replace COLLECTION, MINX, MINY, MAXX, MAXY, TIME_RANGE, and LIMIT with actual values. Use limit=10 by default.

If time_range was not specified, omit it or pass None.

Step 4 -- List assets for an item (optional)

If the user asks about available assets or bands for a specific item:

python3 -c "
import geoai
assets = geoai.pc_item_asset_list(item_id='ITEM_ID', collection='COLLECTION')
for name, info in assets.items():
    print(f'  {name}: {info}')
"

Step 5 -- Download items (if --download flag or user confirms)

python3 -c "
import geoai, os

items = geoai.pc_stac_search(
    collection='COLLECTION',
    bbox=[MINX, MINY, MAXX, MAXY],
    time_range='TIME_RANGE',
    limit=LIMIT,
)

output_dir = 'OUTPUT_DIR'
os.makedirs(output_dir, exist_ok=True)

result = geoai.pc_stac_download(
    items,
    output_dir=output_dir,
)
print(f'Downloaded to: {output_dir}')
for f in os.listdir(output_dir):
    fpath = os.path.join(output_dir, f)
    if os.path.isfile(fpath):
        size_mb = os.path.getsize(fpath) / (1024 * 1024)
        print(f'  {f} ({size_mb:.1f} MB)')
"

Default output directory: ./stac_data/

Step 6 -- Report and suggest follow-ups

Summarize the search or download results. Then suggest:

  • "Use the gdal skill to examine any downloaded files."
  • "Use the gdal skill to clip or mosaic the imagery."

Error handling

  • import geoai fails -> suggest pip install geoai-py.
  • Invalid collection name -> list available collections and suggest the closest match.
  • No items found -> suggest expanding the bbox, adjusting the date range, or trying a different collection.
  • Download failure -> report the error and suggest retrying with fewer items.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.