agentleFS
c-monganc-mongan/ireland-mcp/skills/compare-two-areas/SKILL.md

compare-two-areas

Skill2 starsChanged 19 days agoMITView on GitHub

Compares two Irish places side by side (census population and change, Pobal deprivation by electoral division, recent Property Price Register sale prices, RTB average rents and local boundaries) using the Ireland MCP server, with every figure cited. Use when someone asks "how does X compare with Y", wants Ballymun versus Tallaght, Galway versus Limerick, or two counties, towns or electoral divisions put side by side.

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. Very specific:

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

    line 25
  2. Very specific:

    Population: Call cso/cso_area_profile with { "area": "<county or town>", "years": ["2016", "2022"] }.

    line 38
  3. Very specific:

    Deprivation: Call pobal/pobal_deprivation_search with { "query": "<ED code>" } (the code from step 1 matches Pobal's ed_id) for each ED …

    line 40
  4. Very specific:

    Sale prices: Call ppr/ppr_price_stats for each place over the same 12 months, e.g.

    line 43
  5. Very specific:

    Rents (optional): Call cso/cso_get_table_metadata with { "table_code": "RIQ02" } to find the Location codes, then cso/cso_get_data with

    line 46
  6. Distinctive:

    Compute differences: only from returned values (absolute and %), and show the arithmetic.

    line 50
  7. Distinctive:

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

    line 70
  8. Distinctive:

    Use the same period and level for both places.

    line 71

≈ “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

Compare two areas

Build a side-by-side, sourced comparison of two places in Ireland. Use irish-area-report instead for a single place, and where-to-live-shortlist when the user wants to rank three or more places.

Related projects: IrelandInsights (IrelandInsights), Civgraph (Scott Moore), Ireland Property Price Atlas (Ireland Property Price Atlas). Not affiliated; see ../_shared/inspirations.md.

Calling the tools

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

{ "source": "pobal", "operation": "pobal_deprivation_search", "args": { "query": "Ballymun" } }

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

Steps

  1. Pin both places to the same level. Compare like with like: county with county, council with council, LEA with LEA, electoral division (ED) with ED. Call ireland_resolve_place with { "place": "Tallaght" } for each place. It returns place.level and every code: county, local authority, LEA, Dáil constituency, NUTS3 and the ED code (six digits, e.g. "268018"). For an area, add "list": "ed" to get all of its EDs. A town name falls back to its gazetteer point, which is flagged approximate. If the levels differ, tell the user and pick the closest common level.
  2. Population. Call cso/cso_area_profile with { "area": "<county or town>", "years": ["2016", "2022"] }. Counties give change between censuses; towns give Census 2022 only.
  3. Deprivation. Call pobal/pobal_deprivation_search with { "query": "<ED code>" } (the code from step 1 matches Pobal's ed_id) for each ED from step 1. A name can match several EDs (Ballymun A–F); list each or give a population-weighted average, and say which.
  4. Sale prices. Call ppr/ppr_price_stats for each place over the same 12 months, e.g. { "county": "Dublin", "address": "tallaght", "from": "<12 months ago>" } or an Eircode routing key ("eircode": "D24"). Report median, count and quartiles.
  5. Rents (optional). Call cso/cso_get_table_metadata with { "table_code": "RIQ02" } to find the Location codes, then cso/cso_get_data with { "table_code": "RIQ02", "filters": { "C03004V03625": ["<loc>"], "C02970V03592": ["-"], "C02969V03591": ["-"], "TLIST(Q1)": ["<latest quarter>"] } }. RTB locations are counties, towns and Dublin postal districts (e.g. "Dublin 24"); say if a place has no RTB row.
  6. Compute differences only from returned values (absolute and %), and show the arithmetic.

Output format

Illustrative layout; the values are examples, not data.

## Tallaght vs Ballymun
| Measure | Tallaght | Ballymun | Period | Source |
|---|---|---|---|---|
| Electoral divisions | Tallaght-Jobstown, ... | Ballymun A–F | 2022 boundaries | CSO / Tailte Éireann |
| Pobal relative index | -8.1 (Disadvantaged) | -21.6 to -9.3 | 2022 | Pobal HP Index |
| Median sale price | €365,000 (n=410) | €310,000 (n=96) | Oct 2025–Sep 2026 | PPR, data as of DATE |
| RTB average rent | €1,950 | €1,880 | 2025Q4 | RTB via CSO RIQ02 |
Sources
- ...

Rules

  • Follow ../_shared/citations.md: every number has its period and source.
  • Use the same period and level for both places; flag any mismatch in the table.
  • No "better" or "worse" verdicts and no advice on where to live. Describe differences only.
  • Pobal scores are relative to the national mean (0); negative means more disadvantaged than average.
  • Small PPR counts (under 20 sales) are unstable; say so next to the median.

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.