agentleFS
DeiblerDeibler/edmund-harness/skills/fishing/SKILL.md

fishing

Skill24 starsChanged 2 months agoMITView on GitHub

Ground any PA, MD, NJ, or DE fishing question in the local fishing dataset—waters, bass and other species, stocking, catches, boat access, motor rules, depth, gages, observed conditions, charts, or maps. Use fishing_query and fishing_viz before relying on memory or general web results.

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 4 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use the local platform as the primary source for fishing questions in PA, MD, NJ, and DE.

    line 8
  2. Distinctive:

    Use a targeted endpoint only for detail the summary does not contain.

    line 21
  3. Distinctive:

    Keep evidence types separate.

    line 42
  4. Very specific:

    Call fishing_query on /viz/schema before composing visualization params.

    line 50
  5. Distinctive:

    Prefer source URLs, survey years, and observation times returned by the API.

    line 65
  6. Very specific:

    If a data call fails, query /meta/health.

    line 67

≈ “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

Mid-Atlantic fishing data

Use the local platform as the primary source for fishing questions in PA, MD, NJ, and DE. It joins waterbodies, species presence, public catch occurrences, stocking, regulations, access points, monitoring gages, depth, and survey links.

Answer a water-specific question

  1. Resolve the water with fishing_query at /waterbodies, usually with {q:"<name>", state:"PA"}. Do not invent an id. If near-duplicates come back, prefer the exact named water with the richer survey/source record, or inspect both summaries when that distinction matters.
  2. Query /waterbodies/{id}/summary. This is the join hub and often answers the question in one call: species, access, gages, stocking, catches, regulations, motor restrictions, depth, and biologist reports.
  3. Use a targeted endpoint only for detail the summary does not contain.

Useful endpoints:

  • /fisheries — species composition by water; filters include water, species, and state.
  • /analytics/best-waters — compare waters by species, state, and propulsion restriction.
  • /regulations — special regulations and motor_restriction such as electric_only, no_motor, or hp_limit.
  • /stocking, /catches, /access-points, /gages, /species — focused records with spatial and ordinary filters.
  • /gages/{site_no}/observations — observed flow, stage, temperature, or other measurements when that gage exposes them.
  • /meta/stats and /meta/connectors — dataset coverage and source freshness.

Common spatial params are near:"lon,lat,radius_m" and bbox:"west,south,east,north". Pagination uses limit and offset.

Current conditions and forecasts

Keep evidence types separate. Fishing gages provide observed water conditions; they do not provide a weather forecast. For a question like “how will Blue Marsh fish tonight,” use the fishing data for the water/species/access facts and RadarOmega for current weather, radar, or forecast timing. Say which conclusion comes from which source.

Charts and maps

Call fishing_query on /viz/schema before composing visualization params; it is the live contract for entities, dimensions, measures, filters, and kinds. Then call fishing_viz with /viz/chart or /viz/map. The tool saves a PNG and returns its path. Deliver that path with send_attachment; a filesystem path in message text is not a delivered image.

For underlying numbers instead of a PNG, call fishing_query on the same viz path with fmt:"json".

Interpret honestly

  • Species-presence data proves presence, not today’s bite quality or abundance.
  • Catch records are open-licensed GBIF/iNaturalist occurrences, not private angler-app logs. A heatmap is sampling density, not a guaranteed hotspot.
  • Zero records means “none in this dataset,” not “none exist.”
  • Prefer source URLs, survey years, and observation times returned by the API; do not turn an old survey into a current claim.
  • If a data call fails, query /meta/health. A listening API with a failed database is unavailable; report that plainly instead of silently replacing the local dataset with generic web search.

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.