zhongwei/gh-gtmagents-gtm-agents-plugins-loyalty-lifecycle-orchestration
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Initial commit

Browse Source
This commit is contained in:
Zhongwei Li
2025-11-29 18:30:55 +08:00
commit fba50997cc
12 changed files with 422 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

49
commands/configure-rewards.md Normal file
View File

@@ -0,0 +1,49 @@
---
name: configure-rewards
description: Orchestrates reward catalog setup, fulfillment workflows, and QA before launch.
usage: /loyalty-lifecycle-orchestration:configure-rewards --program "Tiered Loyalty" --catalog drive://loyalty --launch-date 2026-01-15
---
# Command: configure-rewards
## Inputs
- **program** – reference name/ID for the loyalty initiative.
- **catalog** – storage location or doc with reward definitions.
- **launch-date** – target go-live date.
- **regions** – optional localization list for compliance and fulfillment.
- **approvers** – optional stakeholders (legal, finance, partner, ops).
### GTM Agents Pattern & Plan Checklist
> Mirrors GTM Agents orchestrator blueprint @puerto/plugins/orchestrator/README.md#112-325.
- **Pattern selection**: Reward configuration usually runs **pipeline** (catalog intake → fulfillment design → compliance QA → launch packet). If QA + compliance run in parallel, document a **diamond** block with merge gate in the plan header.
- **Plan schema**: Save `.claude/plans/plan-<timestamp>.json` capturing catalog source, fulfillment automations, dependency graph (legal, finance, ops, vendors), error handling, and success metrics (SLA, redemption accuracy, fraud rate).
- **Tool hooks**: Reference `docs/gtm-essentials.md` stack—Serena for catalog diffs, Context7 for compliance/billing SOPs, Sequential Thinking for QA retros, Playwright for redemption form testing.
- **Guardrails**: Default retry limit = 2 for failed catalog loads or QA runs; escalation ladder = Reward Ops → Finance/Legal → Exec sponsor.
- **Review**: Run `docs/usage-guide.md#orchestration-best-practices-puerto-parity` before launch to confirm dependencies + approvals.
## Workflow
1. **Catalog Intake** – load reward definitions (cost, eligibility, inventory) plus vendor details.
2. **Fulfillment Design** – define earning/redemption automations, notification flows, and SLA tracking.
3. **Compliance & Risk** – validate tax regulations, export controls, and fraud safeguards.
4. **QA Checklist** – run test transactions across tiers, currencies, devices, and failure scenarios.
5. **Launch Packet** – produce runbook, escalation plan, and monitoring dashboard references.
## Outputs
- Reward configuration checklist with owner + status.
- QA evidence (screenshots, logs, test cases) stored with catalog.
- Fulfillment runbook (SLA, webhook IDs, contact points) for ops + support teams.
- Plan JSON entry stored/updated in `.claude/plans` for audit trail.
## Agent/Skill Invocations
- `reward-operations` – leads fulfillment + QA steps.
- `loyalty-strategist` – approves benefit alignment with goals.
- `reward-ops` skill – enforces operational standards.
- `loyalty-modeling` skill – confirms economics after final catalog changes.
## GTM Agents Safeguards
- **Fallback agents**: document substitutes (e.g., Reward Ops covering Strategist) when approvers unavailable.
- **Escalation triggers**: escalate if QA fails twice or compliance issues surface; follow GTM Agents rip-cord and log remediation inside plan JSON.
- **Plan maintenance**: update plan JSON/change log whenever catalog, vendors, or launch dates shift for audit parity.
---

48
commands/monitor-loyalty.md Normal file
View File

@@ -0,0 +1,48 @@
---
name: monitor-loyalty
description: Evaluates loyalty program performance, member health, and experiment impact.
usage: /loyalty-lifecycle-orchestration:monitor-loyalty --window 30d --detail full --dimensions "tier,region"
---
# Command: monitor-loyalty
## Inputs
- **window** – time range (7d, 30d, quarter) for analysis.
- **detail** – summary | full report depth.
- **dimensions** – optional breakdowns (tier, cohort, region, channel).
- **experiments** – optional list of campaigns/tests to review.
- **alert_threshold** – optional KPI threshold for escalations.
### GTM Agents Pattern & Plan Checklist
> Mirrors GTM Agents orchestrator blueprint @puerto/plugins/orchestrator/README.md#112-325.
- **Pattern selection**: Monitoring typically runs **pipeline** (data → diagnostics → experiments → action plan). If diagnostics and experiment review can run in parallel, document a **diamond** segment with merge gate in the plan header.
- **Plan schema**: Save `.claude/plans/plan-<timestamp>.json` capturing window, feeds, task IDs, dependency graph (BI, CRM, experimentation), error handling, and success metrics (retention, liability, engagement lift, alert remediation time).
- **Tool hooks**: Reference `docs/gtm-essentials.md` stack—Serena for metric definition diffs, Context7 for SOPs/dashboards, Sequential Thinking for retro cadence, Playwright for verifying embedded dashboards.
- **Guardrails**: Default retry limit = 2 for failed data pulls or chart renders; escalation ladder = Member Insights Analyst → Loyalty Strategist → Exec sponsor.
- **Review**: Run `docs/usage-guide.md#orchestration-best-practices-puerto-parity` before distributing outputs to ensure dependencies + approvals captured.
## Workflow
1. **Data Pull** – collect enrollment, engagement, redemption, CSAT, and revenue metrics by selected window.
2. **Health Diagnostics** – evaluate tier mix, churn risk, point liability, and reward breakage.
3. **Member Insights** – surface segments needing nudges, upgrade opportunities, or win-back plays.
4. **Experiment Review** – summarize test results with lift, guardrails, and recommendations.
5. **Action Plan** – produce prioritized backlog (journey tweaks, rewards refresh, messaging updates).
## Outputs
- Dashboard snapshot with KPI trends and drilldowns.
- Risk/Opportunity list referencing data points and owners.
- Experiment readouts plus next-test suggestions.
- Plan JSON entry stored/updated in `.claude/plans` for audit trail.
## Agent/Skill Invocations
- `member-insights-analyst` – owns analysis + insights.
- `loyalty-strategist` – validates roadmap adjustments.
- `member-insights` skill – ensures segmentation + reporting standards.
## GTM Agents Safeguards
- **Fallback agents**: document substitutes (e.g., Loyalty Strategist covering Analyst) when analysts unavailable.
- **Escalation triggers**: if alert_threshold is breached twice or liability spikes, trigger GTM Agents rip-cord escalation and record remediation in plan JSON.
- **Plan maintenance**: update plan JSON/change log when metrics, thresholds, or tooling stack shift to keep audit history accurate.
---

48
commands/plan-loyalty.md Normal file
View File

@@ -0,0 +1,48 @@
---
name: plan-loyalty
description: Produces loyalty program blueprint with tiers, benefits, and lifecycle triggers.
usage: /loyalty-lifecycle-orchestration:plan-loyalty --goal retention --tiers 3 --budget 50000
---
# Command: plan-loyalty
## Inputs
- **goal** – retention | expansion | engagement | advocacy.
- **tiers** – number of tiers or type (points-only, hybrid, missions).
- **budget** – monthly/quarterly reward pool.
- **personas** – optional comma-separated member segments.
- **constraints** – optional compliance or platform notes.
### GTM Agents Pattern & Plan Checklist
> Mirrors GTM Agents orchestrator blueprint @puerto/plugins/orchestrator/README.md#112-325.
- **Pattern selection**: Loyalty design generally follows a **diamond** (research ↔ modeling in parallel, converge into governance) or **pipeline** if run sequentially; document choice in the plan header.
- **Plan schema**: Save `.claude/plans/plan-<timestamp>.json` capturing tiers, benefit assumptions, financial guardrails, dependency graph (legal, finance, ops), error handling, and success criteria (retention, NRR, cost/point).
- **Tool hooks**: Reference `docs/gtm-essentials.md` stack—Serena for catalog/tier diffs, Context7 for compliance docs, Sequential Thinking for scenario modeling, Playwright for testing redemption flows.
- **Guardrails**: Default retry limit = 2 for data pulls or modeling errors; escalation ladder = Loyalty Strategist → Finance/Legal → Exec sponsor.
- **Review**: Run `docs/usage-guide.md#orchestration-best-practices-puerto-parity` before publishing to ensure dependencies, approvals, and deliverables are logged.
## Workflow
1. **Signal Review** – pull churn metrics, cohort revenue, product usage, and VOC insights.
2. **Tier & Benefit Design** – outline requirements per tier (earn rules, benefits, surprise moments).
3. **Lifecycle Mapping** – embed loyalty triggers into onboarding, adoption, upsell, and renewal stages.
4. **Economic Modeling** – estimate cost per point, breakage, and projected ROI.
5. **Governance Packet** – assign owners, cadences, and KPIs for launch.
## Outputs
- Program blueprint deck/table (tiers, requirements, benefits, KPIs).
- Lifecycle trigger matrix (event → loyalty action → channel → owner).
- Financial model summary (cost, expected lift, break-even timeline).
- Plan JSON entry stored/updated in `.claude/plans` for audit trail.
## Agent/Skill Invocations
- `loyalty-strategist` – leads architecture.
- `loyalty-modeling` skill – calculates economics and guardrails.
- `member-insights-analyst` – validates segment assumptions.
## GTM Agents Safeguards
- **Fallback agents**: document substitutes (e.g., loyalty-ops covering strategist) when key approvers unavailable.
- **Escalation triggers**: escalate if modeling shows negative ROI twice or compliance blockers arise; follow GTM Agents rip-cord path and log in plan JSON.
- **Plan maintenance**: update plan JSON/change log whenever tiers, budgets, or guardrails shift so audit reviewers see history.
---