AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Nasa Firms Fire Fetch

skill-tiangong-ai-agent-skills-nasa-firms-fire-fetch · by tiangong-ai

Retrieve bounded NASA FIRMS satellite active-fire and thermal-anomaly point detections through the Tiangong CLI for one reviewed source, known bounding box, and short UTC date window. Use for hotspot screening or candidate fire-location context; do not use for fire perimeters, burned area, confirmed wildfire incidents, cause attribution, emergency alerts, recurring monitoring, or multi-source fus…

— No reviews yet
0 installs
0 views
— view→install

Install

$ agentstack add skill-tiangong-ai-agent-skills-nasa-firms-fire-fetch

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • ✓ Prompt-injection patterns
  • ✓ Secret / credential exfiltration
  • ✓ Dangerous shell & filesystem operations
  • ✓ Untrusted network calls
  • ✓ Known-malicious package signatures

What it can access

  • ✓ Network access No
  • ✓ Filesystem access No
  • ✓ Shell / process execution No
  • ✓ Environment & secrets No
  • ✓ Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-tiangong-ai-agent-skills-nasa-firms-fire-fetch)

Reliability & compatibility

✓ Security review passed
0 installs to date
— no reviews yet
● 12d ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Nasa Firms Fire Fetch? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

NASA FIRMS Active Fire

Use the CLI-owned nasa-firms.active-fire capability. This Skill supplies intent routing and result-use boundaries only; the CLI owns source discovery, input/output schemas, MAP_KEY injection, chunking, limits, validation, and receipts.

Before running

  1. Read references/tiangong-data-requirement.json.
  2. Use the caller- or workspace-resolved stable CLI. The requirement declares

compatible capability and operation contract majors; it does not select a package build.

  1. Run data describe with that same CLI. Continue only when the capability

ID and required contract majors match, and copy the exact current capability/operation versions from that response into the run request.

  1. Ensure NASA_FIRMS_MAP_KEY is present in the CLI process environment, then

run the default static doctor. Never place the key in argv, the request JSON, a Skill-local config file, logs, or output.

tiangong-ai data describe nasa-firms.active-fire --json
tiangong-ai data doctor nasa-firms.active-fire --json

Use the returned Discovery Metadata to confirm current source availability, coverage, granularity, NRT or Standard Processing semantics, citation guidance, quota, provides, and doesNotProvide. Do not substitute facts remembered from an older Skill revision. A blocked static doctor means the required logical credential is unavailable; stop instead of bypassing the CLI.

Prepare the request

Build a tiangong.data.run-request.v1 envelope and replace the two version placeholders with the exact versions from the same data describe response. Use one source and one known WGS84 bounding box that does not cross the antimeridian. The inclusive UTC date window may contain at most 31 dates; the CLI performs provider-compliant five-day chunking and enforces transaction and record limits.

{
  "schemaVersion": "tiangong.data.run-request.v1",
  "capabilityId": "nasa-firms.active-fire",
  "capabilityVersion": "",
  "operationId": "fetch-area",
  "operationVersion": "",
  "input": {
    "source": "VIIRS_NOAA20_NRT",
    "boundingBox": {
      "west": 115.8,
      "south": -8.9,
      "east": 116.3,
      "north": -8.3
    },
    "startDate": "2026-03-01",
    "endDate": "2026-03-07",
    "checkAvailability": true
  }
}

Use the operation input schema returned by the same data describe response for the current source enum and limits. Select NRT only when timeliness is material and its provisional status can be retained; select the matching Standard Processing source for consistent historical work when available. Set checkAvailability when the source's historical window is uncertain, accepting the extra provider request. Do not silently widen the box, switch sources, geocode place names, cross the antimeridian, or fan out across areas.

Run

tiangong-ai data run nasa-firms.active-fire fetch-area \
  --input /absolute/path/to/request.json --json

The command emits a tiangong.data.run-result.v1 envelope. Preserve its contract, warnings, errors, and receipt with data when handing the result to another workflow.

Result boundaries

  • Treat each record as a satellite thermal-anomaly or active-fire detection,

not a fire perimeter, burned-area estimate, incident identity, or proof of a wildfire or ignition cause.

  • Preserve source, acquisition time, satellite/instrument, confidence,

day/night, version, and sensor measurements with every downstream use.

  • Preserve NRT provisional warnings and the exact selected dataset in citations.

Do not merge NRT and Standard Processing records without an explicit method.

  • Treat partial as incomplete chunk or row coverage. Report missing chunks

and invalid paths together with the usable detections.

  • Preserve duplicate/inconsistent-header and row-validation issues. Rows with

invalid required coordinates or acquisition timestamps are omitted, while a duplicate optional header or malformed optional measurement does not discard an otherwise usable detection.

  • Treat blocked as no usable business result. Surface credential, request,

availability, endpoint, quota, or provider errors instead of bypassing limits or switching endpoints.

  • Report record-limit truncation and transaction estimates; a truncated result

is not exhaustive evidence of hotspot absence or presence.

  • Confirm operationally important detections with incident, perimeter, imagery,

or local-authority sources. This capability supplies no alert, evacuation, severity, containment, smoke, emissions, weather, or hydrology decision.

  • Recurring monitoring, multi-area or multi-source fan-out, duplicate-event

resolution, statistical inference, and research evidence admission belong to the caller or Auto Research, not this atomic Skill.

  • This execution contract does not expose the source script's standalone

MAP_KEY-status probe, arbitrary sensor-specific raw columns, or raw JSON/log artifact output. Use the static doctor plus an explicit bounded operation; add any future live quota diagnostic as a separately reviewed CLI contract.

Reference

  • references/tiangong-data-requirement.json: stable capability requirement; it is not a package lock.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Versions

  • v0.1.0 Imported from the upstream source.