agentleFS
c-monganc-mongan/ireland-mcp/skills/pay-gap-compare/SKILL.md

pay-gap-compare

Skill2 starsChanged 19 days agoMITView on GitHub

Compares employer gender pay gap reports filed under the Gender Pay Gap Information Act 2021 (mean and median hourly gaps, bonus gaps, quartile shares) across companies, years or a NACE industry using the PayGap.ie dataset, and adds CSO national earnings by sex for context, via the Ireland MCP server. Use when someone asks what a company's gender pay gap is, how banks or tech firms compare, how an employer's gap changed between years, or how employer reports relate to national figures.

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 3 are distinctive, and 3 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.

  • 3

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Put employer-reported gender pay gap figures side by side and keep them distinct from national statistics.

    line 9
  2. Very specific:

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

    line 24
  3. Very specific:

    Find reports: Call paygap/paygap_search_reports with company (name fragment), year and/or industry (words such as "Financial" match the …

    line 31
  4. Very specific:

    Fallback notice: If the response shows fallback: true, state that the publisher's dated GitHub snapshot was used and annotation flags are …

    line 44
  5. Distinctive:

    Follow ../_shared/citations.md.

    line 62
  6. Distinctive:

    No rankings of "best" or "worst" employers and no claims about employer conduct.

    line 65

≈ “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

Pay gap compare

Put employer-reported gender pay gap figures side by side and keep them distinct from national statistics.

Related projects: PayGap.ie (Jennifer Keane). Not affiliated; see ../_shared/inspirations.md.

Calling the tools

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

{ "source": "paygap", "operation": "paygap_search_reports", "args": { "industry": "Financial", "year": 2024, "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. Find reports. Call paygap/paygap_search_reports with company (name fragment), year and/or industry (words such as "Financial" match the nace_section label). NACE letters follow the dataset's own coding (finance is "L" in its labels), so check nace_section before relying on a letter. Page with offset.
  2. Check identity. Several employers can share a name fragment, and one employer can file more than one report a year. Show the full name and keep duplicates separate.
  3. Compare. Tabulate mean and median hourly gap, bonus gaps and the share of women in each pay quartile where present. Blank metrics stay "not reported"; zero and negative values are real.
  4. Trend (optional). Repeat for each available year (dataset.available_years) for the same employer.
  5. Industry spread (optional). For an industry, report the count, median and range of the median hourly gap across returned reports; do not average means.
  6. National context (optional). cso/cso_search_tables with "earnings sex" (e.g. SES16 or EHA tables) and cso/cso_get_data for national figures. Cite separately; they use different methods.
  7. Fallback notice. If the response shows fallback: true, state that the publisher's dated GitHub snapshot was used and annotation flags are unavailable.

Output format

Illustrative layout; the values are examples, not data.

## Gender pay gap: financial and insurance activities, 2024 reports
| Employer | Mean hourly gap | Median hourly gap | Mean bonus gap | Women in top quartile | Report |
|---|---|---|---|---|---|
Reports found: 90. Industry median of median hourly gaps: x% (range a%–b%).
Sources
- Irish Gender Pay Gap Portal (PayGap.ie), dataset CC0 1.0; original employer reports linked per row

Rules

  • Follow ../_shared/citations.md; credit PayGap.ie and link each employer report.
  • A gender pay gap is not a measure of unequal pay for equal work. Say so once.
  • Employer reports are self-reported and not a representative sample of all workers.
  • No rankings of "best" or "worst" employers and no claims about employer conduct.

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.