원클릭으로 Manus에서 모든 스킬 실행

hr-orchestration-lanes

스타1

포크0

업데이트2026년 5월 31일 03:11

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.

설치

Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.

Manus에서 실행

출처

SafetyMP

SafetyMP/HR-ERP

GitHub 저장소 열기 Creator 저장소 보기

다운로드

Manus에서 실행

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

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

이 저장소의 다른 Skills

같은 저장소

hr-contributor-handoff

SafetyMP/HR-ERP

Community PR/issue triage, appreciative contributor review, docs sync, and orchestrator handoff JSON. T1 advocate lane — not FinOps/swarm. Co-load lint-and-validate and security review when diff warrants.

2026-05-311

hr-data-custody

SafetyMP/HR-ERP

HR ERP database migrations and packaging: Prisma/SQL surfaces, expand-migrate-contract, RLS-safe seeds, db:verify, distroless/GHCR supply chain. Use for DDL, backfills, dual-write cutovers, Dockerfile, or publish-ghcr workflows.

2026-05-311

hr-devops-lifecycle

SafetyMP/HR-ERP

HR ERP DevOps overlay: Vercel git deploy, GHA quality gate, Redis workers, Phase 1 topology. Co-loads @devops-product-lifecycle. Use for ops paths in this repo.

2026-05-311

hr-foundation-governance

SafetyMP/HR-ERP

Agent harness foundation — manifest v4, hooks, lint, ALARP, Cursor native unlock, Phase 2 evidence. Use for .cursor/**, governance scripts, and meta docs.

2026-05-311

hr-governance-learning

SafetyMP/HR-ERP

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

2026-05-311

hr-human-collaboration

SafetyMP/HR-ERP

Collaboration plane (Harness HITL) — seven-phase human-agent loop: proposal, options, human tradeoffs, execute, revalidate, specialized tools, output review. Use at T1+ before specialized skills; load routing portion automatically at orchestration.

2026-05-311

name	hr-orchestration-lanes
description	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.
risk	medium
minRiskTier	T1
source	project
disable-model-invocation	true

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

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