agentleFS
SafetyMPSafetyMP/HR-ERP/.cursor/skills/hr-governance-learning/SKILL.md

hr-governance-learning

Skill1 starsChanged 6 months agoApache-2.0View on GitHub

Adaptation plane — learning ledger, reflect/promote L0-L3, DMAIC/PDCA, CTQ snapshots, router hints. Human-invoked for RGF workflows.

The file

Files
SKILL.md

HR governance learning (Adaptation plane)

Reflective Governance Fabric (RGF) + DMAIC/PDCA (ADR 0018, ADR 0019). Human invokes; agents do not self-promote policy.

When

  • Running governance:reflect (includes ctqSnapshot)
  • Opening DMAIC project or PDCA loop
  • Promoting L1/L2/L3 with gates below

PDCA checklist (weekly)

  • Plan: reflect report + stub
  • Do: shadow router hint or L1 trial
  • Check: improve measure --ctq … vs baseline
  • Act: promote or reject with principal

DMAIC checklist (project)

  • Define — --ctq or --brief required on improve define
  • Measure — baseline + optional --ctq metric
  • Analyze — RCA stub
  • Improve — promote L1/L2/L3
  • Control — control plan (L2 required)

Learning tiers

TierMutatesGate
L0LedgerAutomatic
L1Skill references/learning/*.mdPO + CI
L2adaptation.skillRouterHintsControl plan
L3additionalPathTriggersCounsel + ADR + sync-check

Evidence (ADR 0019)

  • T3+ handoffs: evidenceBundlePath + lane sign-offs
  • Collect: npm run governance:evidence:collect
  • Verify: npm run governance:evidence

Do not

  • L2 without control plan; L3 without --adr
  • Define DMAIC without CTQ or brief
  • Weaken non-learnable invariants

References

  • governance-continuous-learning.md
  • product-value-ctq-tree.yaml
  • ADR 0019

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.