agentleFS
SafetyMPSafetyMP/HR-ERP/.cursor/skills/hr-orchestration-lanes/SKILL.md

hr-orchestration-lanes

Skill1 starsChanged 6 months agoApache-2.0View on GitHub

HR ERP function-lane recipes: payroll T3 counsel, migration custodian isolation, security sentinel SLA, parallel scout+architect greenfield. Use with manifest v4 and ADR 0011 / 0016.

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 0 are distinctive, and 5 are 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.

  • 5

    Very specific

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

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

    Run npm run governance:lint — note Required lanes and Suggested lanes.

    line 27
  2. Very specific:

    Run npm run governance:plan — use regulatedGraph + delegatedTaskPlan + collaborationPlan for /multitask.

    line 28
  3. Very specific:

    Payroll/compliance (T3): add readonly counsel; load @hr-regulated-domain after revalidation (max 3 bodies with product-gate).

    line 34
  4. Very specific:

    AI governance paths: add readonly ai_governance_reviewer (docs/ai-governance/, lib/governance/, threat model doc).

    line 35
  5. Very specific:

    MLOps inference only (docs/ml/, services/ml-serving/): add mlops_reviewer readonly Task.

    line 37

≈ “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 orchestration lanes

Use when

  • Orchestrating HR ERP features in Cursor (tier ≥ T1)
  • Diff touches pay, compliance, AI governance, migrations, or security plane

Instructions

Phase 2 — Strategy options (HOTL)

Present ≥2 lane DAG alternatives with risk, reward, rollback, and deferred specialized skills. Use collaboration-plan.md.

Phases 4–7 — Execution

  1. Run npm run governance:lint — note Required lanes and Suggested lanes.
  2. Run npm run governance:plan — use regulatedGraph + delegatedTaskPlan + collaborationPlan for /multitask.
  3. Plan Mode bridge: save .cursor/plans/*.md → human revalidation → governance:plan → /multitask (phase 6+ only).
  4. Greenfield T1: parallel scout + architect → builder → parallel sentinel + verifier.
  5. DDL (T2+): /worktree + worktrees.json; architect readonly → custodian → builder.
  6. Ops / CI / deploy (T2+): release_ops after architect when .github/workflows, vercel.json, docs/operations/** change; load @devops-product-lifecycle + @hr-devops-lifecycle.
  7. Security plane: sentinel mandatory before merge (middleware.ts, lib/security/**).
  8. Payroll/compliance (T3): add readonly counsel; load @hr-regulated-domain after revalidation (max 3 bodies with product-gate).
  9. AI governance paths: add readonly ai_governance_reviewer (docs/ai-governance/, lib/governance/, threat model doc).
  10. Product MCP (lib/copilot/**): ai_governance_reviewer + sentinel after builder; load @hr-product-mcp-governance after revalidation.
  11. MLOps inference only (docs/ml/, services/ml-serving/): add mlops_reviewer readonly Task.
  12. T4 ≥2 Tasks: finops_coordinator + @hr-swarm-governance FinOps note.

Resources

  • ADR 0011
  • cursor-3-native-runtime.md
  • hook-rollout-schedule.md
  • governance-manifest.yaml
  • Promoted learning: references/learning/6f436872-80bd-42b9-9d49-20da21203d33.md (lane_gap harness_foundation)

Limitations

  • Archived hr-erp-* skill names are invalid in new handoffs — use consolidated hr-* skills only

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.