agentleFS
c-monganc-mongan/ireland-mcp/skills/local-election-brief/SKILL.md

local-election-brief

Skill2 starsChanged 20 days agoMITView on GitHub

Prepares a neutral, cited brief for a Dáil constituency or an address before an election or a meeting with local representatives, combining GeoHive boundaries (constituency, local electoral area), the sitting TDs from the Oireachtas, each TD's recent parliamentary questions, local census population and change, deprivation and recent house prices, via the Ireland MCP server. Use when someone asks "who are my TDs", "what is happening in my constituency", or wants a local briefing pack before voting or canvassing.

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 1 is distinctive, and 4 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    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 25
  2. Very specific:

    Find the constituency: Call ireland_resolve_place with the town, LEA, council or lat/lon.

    line 32
  3. Very specific:

    Keep codes.constituency (with seats), codes.lea and codes.county.

    line 33
  4. Very specific:

    Sitting TDs: Call oireachtas/oireachtas_search_members with { "constituency": "<name>" }.

    line 36
  5. Distinctive:

    Do not include personal contact details beyond the official Oireachtas record links.

    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

Local election brief

A one-page, even-handed picture of a constituency: who represents it, what they have raised in the Dáil, and what the local data shows. Use td-briefing for a deep dive on one member.

Related projects: Contact Your Local TD (Unknown), Constituent (Owen Connor), Oireachtas Connect (Oireachtas Connect). Not affiliated; see ../_shared/inspirations.md.

Calling the tools

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

{ "source": "oireachtas", "operation": "oireachtas_search_members", "args": { "constituency": "Galway West" } }

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.

Steps

  1. Find the constituency. Call ireland_resolve_place with the town, LEA, council or lat/lon. Keep codes.constituency (with seats), codes.lea and codes.county. An LEA or council can overlap several constituencies; each comes with its share of residents, so name them all. From a constituency name, pass "list": "lea" to get its LEAs, then go to step 2.
  2. Sitting TDs. Call oireachtas/oireachtas_search_members with { "constituency": "<name>" }. List every member returned, in the API's order or alphabetically; never by party preference.
  3. What each TD raised. For each member_code, call oireachtas/oireachtas_search_questions with { "member_code", "date_from": "<3 months ago>", "limit": 50 }. Count questions and group them by the minister or department addressed. Apply the same window and limit to every member.
  4. Local context. cso/cso_area_profile for the county (2016 vs 2022 population); ppr/ppr_price_stats for the county or a main town over the last 12 months; optionally pobal/pobal_deprivation_search for named electoral divisions.
  5. Recent Dáil votes (optional). oireachtas/oireachtas_get_votes with { "chamber": "dail", "date_from" } gives division tallies, not individual votes; do not attribute a vote to a TD from tallies.

Output format

Illustrative layout; the values are examples, not data.

## <Constituency> (<seats> seats) — brief as of <date>
**Sitting TDs:** <Name> (<Party>), ... (34th Dáil, Oireachtas Open Data)
| TD | Questions (<window>) | Most-addressed departments |
|---|---|---|
**Local data:** population <n> (Census 2022, change since 2016 <x%>); median sale <€> (PPR, <period>)
Sources
- ...

Rules

  • Follow ../_shared/citations.md.
  • Strict neutrality: same queries, windows and table columns for every member; no adjectives, ratings, predictions or claims about motives or effectiveness.
  • Question counts measure activity in one channel only; say so. Ministers do not ask questions.
  • Do not include personal contact details beyond the official Oireachtas record links.
  • Constituency boundaries changed in 2023; data from before the 34th Dáil may use old boundaries.

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.