BirdWeather PUC

Access BirdWeather PUC station data — species detections, sensor readings (AQI, temperature, humidity, pressure, eCO₂, sound dB), and historical trends. Use...

Security Scan

The skill's code, instructions, and resource access match its description: it reads public BirdWeather station APIs and optionally logs data to a user-specified SQLite DB — nothing in the package requests unrelated credentials, hidden endpoints, or unexpected permissions.

Purpose & Capability

Name/description (BirdWeather PUC data access) aligns with required actions: HTTP GETs to app.birdweather.com and optional local SQLite logging. No unrelated credentials, binaries, or config paths are requested.

Instruction Scope

SKILL.md instructs only to fetch station endpoints, run the included Python script, and optionally write to a user-specified DB. It does not instruct reading other system files, secrets, or sending data to third-party endpoints.

Install Mechanism

Instruction-only skill with one included Python script; there is no install spec or external downloads. Uses standard library urllib and sqlite3 — no additional packages or remote installers.

Credentials

No required environment variables or credentials are declared. The SKILL.md suggests an optional public station token (read-only) which is consistent with the API docs; no unrelated secrets or multiple credentials are requested.

Persistence & Privilege

Skill is not always-enabled and does not request system-wide persistence. It only writes to an explicit DB path provided by the user (no hidden persistence or modifications to other skills).

Assessment

This skill appears to do exactly what it claims: read public BirdWeather station endpoints and optionally log data to a local SQLite DB. Before installing, ensure you: 1) pass a DB path you control (don't write to shared/system locations), 2) understand that storing logs locally will retain detection and sensor history, and 3) review the included script if you require extra assurance — it uses only standard Python libs and contacts app.birdweather.com. If you plan to enable autonomous invocation, be aware the agent could poll the station or update the DB without interactive approval (the skill itself does not request broad credentials).

Fetch bird detections, species lists, and environmental sensor data from a BirdWeather PUC station.

Setup

BirdWeather tokens are public (no auth required for read access). Find yours at: app.birdweather.com → Station Settings → Token

Store token in environment or pass directly:

export BIRDWEATHER_TOKEN=your_token_here

Core Script

Use scripts/birdweather.py for all data access:

# Daily summary — detections, species count, top birds, sensors
python3 scripts/birdweather.py summary --token TOKEN

# Recent detections (last N, default 10)
python3 scripts/birdweather.py detections --token TOKEN --limit 20

# Top species for a time period
python3 scripts/birdweather.py species --token TOKEN --period week

# Current sensor readings (AQI, temp, humidity, pressure, eCO₂, sound dB)
python3 scripts/birdweather.py sensors --token TOKEN

# Log sensor snapshot to SQLite (for history/trends)
python3 scripts/birdweather.py log --token TOKEN --db PATH_TO_DB

# Check for new species (first-ever detections vs. known catalog)
python3 scripts/birdweather.py new-species --token TOKEN --db PATH_TO_DB

All commands output JSON. Parse with json.loads() or pipe to jq.

Workflows

New Species Alert

1. Run new-species — compares live species list against DB catalog
2. If new species found: alert user with common name, scientific name, confidence, timestamp
3. Update DB with log command

Daily Summary

1. Run summary for today's counts and top birds
2. Run sensors for current environmental readings
3. Combine into a brief — detections, species count, top 3-5 birds, AQI/temp

Sensor Trend Analysis

1. Log regularly with log --db (add to cron/heartbeat)
2. Query SQLite birdweather_sensor_history table for trends
3. Look for AQI spikes, temperature patterns, sound level changes

SQLite Schema

When using --db, two tables are maintained:

birdweather_species — cumulative species catalog:

species_id INTEGER, common_name TEXT, scientific_name TEXT,
color TEXT, thumbnail_url TEXT, first_detected_at TEXT,
detection_count INTEGER

birdweather_sensor_history — time-series sensor log:

id INTEGER PRIMARY KEY, recorded_at TEXT,
temp_f REAL, humidity REAL, pressure REAL,
aqi REAL, eco2 REAL, sound_db REAL, voc REAL

API Reference

See references/api.md for full endpoint documentation.

System Access

• Network: app.birdweather.com/api/v1/stations/{token}/* (read-only, no auth)
• Disk: SQLite DB at user-specified path (optional, only with --db)
• No credentials stored — token is passed per-invocation