agentleFS
c-monganc-mongan/ireland-mcp/skills/irish-area-report/SKILL.md

irish-area-report

Skill2 starsChanged 20 days agoMITView on GitHub

Builds a cited one-page profile of an Irish county, town or point (population from the CSO census, administrative boundaries from Tailte Éireann GeoHive, recent house sale prices from the Property Price Register, and the Met Éireann forecast and warnings) using the Ireland MCP server. Use when someone asks "what is X like", wants an area overview before moving, visiting or writing about a place in Ireland, or needs the county, constituency or electoral division for a location.

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 3 are distinctive, and 4 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.

  • 4

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    If an argument shape is unclear, call ireland_describe with { "source", "operation" } first.

    line 23
  2. Distinctive:

    If the snapshot says the place is not found, ask for a nearby town or coordinates.

    line 35
  3. Very specific:

    Population: Call cso/cso_area_profile with { "area": "<county>", "years": ["2016", "2022"] } to show change between censuses (Dublin may be …

    line 36
  4. Very specific:

    House prices: Call ppr/ppr_price_stats with { "county": "<county>", "from": "<12 months ago>" }.

    line 42
  5. Very specific:

    Weather: Use the forecast and warnings from step 1, or met-eireann/met_get_forecast and met-eireann/met_get_warnings.

    line 45
  6. Distinctive:

    Follow ../_shared/citations.md: every number has its period and source.

    line 73
  7. Distinctive:

    No advice on whether to buy, rent or move.

    line 75

≈ “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

Irish area report

Produce a short, sourced profile of one place in Ireland.

Related projects: Civgraph (Scott Moore). Not affiliated; see ../_shared/inspirations.md.

Calling the tools

Steps name each operation as source/operation (e.g. ppr/ppr_price_stats), using the typed tool name as the operation. On the default surface, run it with ireland_call, for example:

{ "source": "cross", "operation": "ireland_snapshot", "args": { "place": "Athlone" } }

If an argument shape is unclear, call ireland_describe with { "source", "operation" } first; it returns the schema and an example. search, fetch and nearby are top-level tools. If the server was added with ?toolsets=<ids> or ?toolsets=all, the typed tool (e.g. ireland_snapshot) can be called directly with the same args.

Steps

  1. Resolve the place.
    • County or large town: call cross/ireland_snapshot with { "place": "Athlone" }. It returns county, census population, boundaries, forecast and national warnings in one call.
    • Exact point (lat/lon, or the place is not in the built-in list): call cross/nearby with { "lat": 53.27, "lon": -9.05 }, or geohive/geohive_boundaries_at_point for boundaries only.
    • If the snapshot says the place is not found, ask for a nearby town or coordinates. Do not guess.
  2. Population. Call cso/cso_area_profile with { "area": "<county>", "years": ["2016", "2022"] } to show change between censuses (Dublin may be split; use the label returned). For a town, pass { "area": "<town>" } to get Census 2022 town figures (F1015, no change); say which level you used.
  3. Boundaries. Report county, local authority, Dáil constituency, electoral division and small area from the GeoHive block. For other layers, use geohive/geohive_list_layers then geohive/geohive_query_layer.
  4. House prices. Call ppr/ppr_price_stats with { "county": "<county>", "from": "<12 months ago>" }. Narrow with address (a town word) or eircode (routing key such as "H91"). Keep from–to within 3 years. See the house-price-check skill for caveats.
  5. Weather. Use the forecast and warnings from step 1, or met-eireann/met_get_forecast and met-eireann/met_get_warnings.
  6. Optional extras, only if asked: TDs for the constituency via oireachtas/oireachtas_search_members with { "constituency": "<name>" }; transport via the commute-weather skill.

Output format

Illustrative layout; the values are examples, not data.

## <Place>, Co. <County>
| Topic | Figure | Period | Source |
|---|---|---|---|
| Population | 84,447 | Census 2022 | CSO F1001 |
| Change since 2016 | +5.1% | 2016–2022 | CSO F1001 |
| Median sale price | €315,000 (n=1,204) | Oct 2025–Sep 2026 | PPR, data as of DATE |
| Constituency | Galway West | current boundaries | GeoHive |
| Weather next 6h | 12°C, showers | issued TIME | Met Éireann |
| Active warnings | Yellow wind (Galway) | until TIME | Met Éireann |

<2–4 sentence plain-English summary>

Sources
- ...

Rules

  • Follow ../_shared/citations.md: every number has its period and source.
  • Say "not available" for a failed section and keep the rest. Never fill gaps from memory.
  • No advice on whether to buy, rent or move. Describe the data only.
  • Field notes and example values: references/fields.md.

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.