L’interface est localisée ; les présentations et documents des Skills sont traduits automatiquement par IA dans votre langue. Le code, les commandes, chemins et termes techniques restent en version originale, et le document de l’auteur fait foi.
Explorer les Skills
Productivité · SKILL.md

social-insurance-statistics

social-insurance-statistics

Query Social Insurance Board statistical publications for benefits, social protection services, and caseload trends.

Independent GitHub snapshot · Automated classification · Original documentation governs

Documentation de la Skill

GitHub

name: social-insurance-statistics description: Query Social Insurance Board statistical publications for benefits, social protection services, and caseload trends.

Social Insurance Statistics

Use when

  • You need Social Insurance Board caseload/benefit statistics.
  • You need social-protection service trend context.

Avoid when

  • You only need unemployment service data.

Inputs

  • Benefit/service type, period, and region/group.

Outputs

  • Social-insurance statistics dataset with period metadata.

Primary endpoints

Workflow

  1. Locate relevant publication/table on statistics page.
  2. Extract indicators by period/group.
  3. Normalize metric definitions and units.
  4. Return analysis-ready dataset with caveats.

Human setup (when needed)

  • If data is offered in document downloads only, walk user through downloads and continue from supplied files.

Quality checks

  • Preserve source terminology for benefits/services.
  • Separate counts, rates, and monetary values.

Access reality

Request contract

  • Use the listed primary endpoints as authoritative entry points.
  • If API/query parameters are only visible in-browser, preserve exact request URL, params, and headers in output metadata.
  • If endpoint is UI-only, document click path and extraction method used.

Output schema expectations

  • Keep at least: source URL, retrieval timestamp, publication/update date (if available), title/record label, and extracted governance-relevant fields.
  • Preserve original field names when present in downloadable/API output.

Limits and caveats

  • Confirm whether data is open-download, UI-only, or authenticated before claiming full access.
  • Separate narrative/guidance text from measurable records.

Verification hooks

  • Validate endpoint reachability and content type before extraction.
  • Validate that each extracted claim is linked to a concrete source URL.
Skills enregistrées