agentleFS
SafetyMPSafetyMP/HR-ERP/.cursor/skills/hr-regulated-domain/SKILL.md

hr-regulated-domain

Skill1 starsChanged 6 months agoApache-2.0View on GitHub

HR ERP regulated domains: wage/hour compliance, payroll calculation kernel, employment AI governance, MLOps/inference routing. Use for pay/time APIs, packages/payroll-calc, docs/compliance, lib/governance, screening/scoring.

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Collaboration plane: Do not invoke until phase 6 (revalidationConfirmed in plan/handoff).

    line 15

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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

HR regulated domain

Collaboration plane: Do not invoke until phase 6 (revalidationConfirmed in plan/handoff). Use @hr-human-collaboration for phases 1–5.

Use this skill when

  • Pay, time, earnings, jurisdiction matrices, COMPLIANCE_* errors
  • packages/payroll-calc/, fingerprints, gross-to-net replay
  • ML screening, scoring, governance APIs, docs/ai-governance/
  • Product MCP / inference paths with employment impact — co-load @hr-product-mcp-governance and references/product-mcp.md when lib/copilot/** changes

Do not use this skill when

  • Non-pay UI with no compliance or AI scoring surface
  • T1/T2 work with no regulated path triggers

Instructions

  1. Load the relevant L3 reference(s) below — one domain at a time.
  2. Compliance + payroll kernel: read both when pay math executes.
  3. AI governance + MLOps: co-load when inference and scoring both change.
  4. Legal checklist → specs/templates/legal-checklist.md; counsel confirms interpretation.

Resources

  • references/compliance.md
  • references/payroll-kernel.md
  • references/ai-governance.md
  • references/mlops.md
  • references/product-mcp.md — in-app copilot MCP (use @hr-product-mcp-governance for catalog/transport)

Limitations

  • Engineering controls only — not legal advice
  • Product runtime MCP still follows docs/security/agent-mcp-threat-model.md

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.