agentleFS
c-monganc-mongan/ireland-mcp/skills/safety-stats/SKILL.md

safety-stats

Skill2 starsChanged 19 days agoMITView on GitHub

Reports official road-safety and recorded-crime statistics for Ireland by county, Garda division or Garda station and year or quarter - persons killed and injured on roads (RSA tables published via the CSO) and recorded crime incidents by offence type (CSO) - with population rates from the census, via the Ireland MCP server. Use when someone asks how many people died on roads in a county, how recorded crime changed in a Garda division, or wants road deaths or crime compared between areas or years.

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 2 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    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:

    Get codes: Call cso/cso_get_table_metadata with { "table_code": "ROA15" } (or the crime table).

    line 45
  3. Very specific:

    Fetch: Call cso/cso_get_data with filters for every dimension you need, e.g.

    line 48
  4. Distinctive:

    Compare periods: Use full years or the same quarters year on year.

    line 55
  5. Distinctive:

    No safety advice, no area labels like "dangerous", and no claims about causes.

    line 78

≈ “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

Safety stats

Cited counts and rates for road casualties and recorded crime. These are official statistics, not a measure of how safe a particular street or person is.

Related projects: Ireland Road Deaths (RSA), Crime Stats IE (Brian Fox). Not affiliated; see ../_shared/inspirations.md.

Calling the tools

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

{ "source": "cso", "operation": "cso_get_data", "args": { "table_code": "ROA15", "filters": { "TLIST(A1)": ["2023", "2024"] } } }

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 can be called directly with the same args.

Tables

TopicTableGeographyTime
Persons killed and injuredROA15CountyYear
Collisions and casualtiesROA27CountyYear
Casualties by road user, age, sexROA16StateYear
Recorded crime by offenceCJQ06Garda division (old model; archived June 2026)Quarter
Recorded crime by offenceCJQ10Garda division (new operating model)Quarter
Recorded crime by offenceCJA07 / CJA11Garda station (old / new model)Year

Confirm a table is current with cso/cso_search_tables ("road deaths", "recorded crime") if a call fails.

Steps

  1. Get codes. Call cso/cso_get_table_metadata with { "table_code": "ROA15" } (or the crime table). Note the dimension codes (e.g. "C03867V04617" County, "C02481V03160" Garda Division) and the category code for each place, offence and period.
  2. Fetch. Call cso/cso_get_data with filters for every dimension you need, e.g. ROA15 { "TLIST(A1)": ["2023","2024"], "C03867V04617": ["<county code>"] }. Keep results under 500 rows. For crime, filter TLIST(Q1) (codes like "20251") and the Garda Division; pick headline offence groups (two-digit category codes such as "01"; their labels end in "(01)") rather than every sub-offence. Prefer CJQ10 for recent quarters.
  3. Rates (optional). Divide by population from cso/cso_area_profile (county) and show per 100,000 with the census year. Garda divisions do not match counties exactly; say so.
  4. Compare periods. Use full years or the same quarters year on year; quarterly crime is seasonal.
  5. Null values mean not yet published; never treat them as zero.

Output format

Illustrative layout; the values are examples, not data.

## Road casualties, Co. Galway
| Year | Killed | Injured | Killed per 100k (Census 2022) |
|---|---|---|---|
| 2023 | 12 | 391 | 4.4 |
| 2024 | 5 | not yet published | 1.8 |
Sources
- Road Safety Authority, table ROA15 via CSO PxStat (CC BY 4.0), retrieved <date>

Rules

  • Follow ../_shared/citations.md.
  • Recorded-crime figures can be revised, and fraud (offence group 09) figures before and after 2023Q3 are not comparable; say so when either applies.
  • Recorded crime reflects reporting and recording, not all crime. Small counts swing year to year.
  • No safety advice, no area labels like "dangerous", and no claims about causes.

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.