agentleFS
c-monganc-mongan/ireland-mcp/skills/lobbying-watch/SKILL.md

lobbying-watch

Skill2 starsChanged 20 days agoMITView on GitHub

Summarises published returns on the Register of Lobbying (Lobbying.ie, Standards in Public Office Commission) for a topic, organisation or designated public official, and links them to Oireachtas members and to related bills, via the Ireland MCP server. Use when someone asks who lobbied on housing, which organisations contacted a Minister or TD, or what lobbying surrounded a bill.

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 26
  2. Very specific:

    Search returns: Call lobbying/lobbying_search_returns with one of query (topic words), lobbyist (organisation) or official (a designated …

    line 33
  3. Very specific:

    Page through: Use page until possibly_more is false or you reach a stated cap (e.g.

    line 36
  4. Very specific:

    Link to legislation (optional): If returns name a bill, call oireachtas/oireachtas_search_bills with title words to show its current stage …

    line 43
  5. Distinctive:

    Do not add private contact details.

    line 68

≈ “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

Lobbying watch

Find and summarise lobbying returns, then connect them to the people and legislation they name. The register records declared activity; it does not show influence or outcomes.

Related projects: Lobbyieng (Robert McElhinney), Dáil Tracker (peweet), Oireachtas Connect (Oireachtas Connect). Not affiliated; see ../_shared/inspirations.md.

Calling the tools

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

{ "source": "lobbying", "operation": "lobbying_search_returns", "args": { "query": "housing", "date_from": "2026-01-01", "date_to": "2026-06-30", "limit": 50 } }

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. Search returns. Call lobbying/lobbying_search_returns with one of query (topic words), lobbyist (organisation) or official (a designated public official's name), plus date_from and date_to. Windows are limited to one year; split longer periods into yearly calls.
  2. Page through. Use page until possibly_more is false or you reach a stated cap (e.g. 200 returns). Report total and how many you read.
  3. Summarise. Count returns by lobbyist, public_policy_area_name and subject_matter_name, and list the officials named. Quote the intended_results_text briefly with the return url. Skip obvious test or placeholder returns (e.g. text "TEST") and say how many you skipped.
  4. Link officials to members. For an official who is a TD or Senator, call oireachtas/oireachtas_search_members with { "name": "<surname>" } to confirm party and constituency.
  5. Link to legislation (optional). If returns name a bill, call oireachtas/oireachtas_search_bills with title words to show its current stage and dates beside the lobbying dates.
  6. Company context (optional). cro/cro_search_datasets points to CRO open data for a registered company; describe only what it contains.

Output format

Illustrative layout; the values are examples, not data.

## Lobbying on "housing", 1 Jan–30 Jun 2026 (Register of Lobbying)
Returns found: 916 (read 200). Test/placeholder returns skipped: 3.
| Lobbyist | Returns | Policy areas | Officials named |
|---|---|---|---|
Selected returns: <date> <lobbyist> — "<intended result, short quote>" (<url>)
Sources
- Register of Lobbying, © Standards in Public Office Commission, Lobbying.ie (PSI General Licence), retrieved <date>

Rules

  • Follow ../_shared/citations.md.
  • A return is a declaration of activity, not a meeting count and not evidence of influence or wrongdoing. Never imply either.
  • Same layout for every organisation and official; no adjectives about lobbyists or officials.
  • Do not add private contact details; the adapter already omits them.

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.