zhongwei/gh-gtmagents-gtm-agents-plugins-lead-nurture-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 18:30:53 +08:00
commit 5b26b773ff
12 changed files with 421 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

48
commands/configure-branches.md Normal file
View File

@@ -0,0 +1,48 @@
---
name: configure-branches
description: Generates implementation instructions for nurture branching logic, personalization rules, and automations.
usage: /lead-nurture-orchestration:configure-branches --journey "MM Onboarding" --platform marketo --qa true
---
# Command: configure-branches
## Inputs
- **journey** – reference name or existing blueprint ID.
- **platform** – MAP/CRM platform (Marketo, HubSpot, Braze, Iterable, Pardot, Customer.io, SF Automations).
- **qa** – include QA + evidence steps (default true).
- **assets** – optional asset list to wire.
- **webhooks** – optional external integrations to include.
### GTM Agents Pattern & Plan Checklist
> Lifted from GTM Agents orchestrator practices @puerto/plugins/orchestrator/README.md#112-325.
- **Pattern selection**: Most branching config is a **pipeline** continuation of design-nurture. If QA + personalization can run parallel, explicitly log a **diamond** segment and define merge points.
- **Plan schema**: Update `.claude/plans/plan-<timestamp>.json` (or create if standalone) with branch IDs, step references, tokens, webhook payloads, QA scenarios, and error handling. Note dependencies (assets, webhooks) and success criteria (activation %, latency).
- **Tool hooks**: Use `docs/gtm-essentials.md` stack—Serena for MAP diffs, Context7 for platform docs, Sequential Thinking for post-flight retro, Playwright for landing/app QA.
- **Guardrails**: Default retry limit = 2 per failed automation. Escalate Marketing Ops Partner → Nurture Architect → RevOps if QA evidence fails or compliance issues appear.
- **Review**: Run `docs/usage-guide.md#orchestration-best-practices-puerto-parity` before publishing to ensure agents, dependencies, and deliverables are confirmed.
## Workflow
1. **Blueprint Sync** – pull journey diagram, triggers, suppression, personalization tokens.
2. **Branch Mapping** – translate logic into platform-specific steps (smart lists, decision splits, wait steps, webhook calls).
3. **Personalization Wiring** – define tokens, dynamic content blocks, conditional logic.
4. **QA & Evidence** – build test plan (seed profiles, edge cases, fallback paths) with screenshots/logs.
5. **Documentation** – produce build guide, change log, rollback plan.
## Outputs
- Implementation checklist with step-by-step instructions.
- QA/evidence matrix (test profile, scenario, expected result, status).
- Change log template + rollback notes.
- Plan JSON entry stored/updated in `.claude/plans` for traceability.
## Agent/Skill Invocations
- `marketing-ops-partner` – executes platform build.
- `personalization-logic` skill – ensures conditional content is accurate.
- `nurture-testing` skill – enforces QA rigor.
## GTM Agents Safeguards
- **Fallback agents**: document substitutes (e.g., Marketing Ops Partner covering testing) if specialists unavailable.
- **Escalation triggers**: if unsubscribe/spam complaints or latency guardrails breach twice in 48h, trigger lifecycle rip-cord and notify Marketing + Sales leadership.
- **Plan maintenance**: each branching change requires updating plan JSON + change log; reference in status packets to keep audit trail aligned with GTM Agents standards.
---

48
commands/design-nurture.md Normal file
View File

@@ -0,0 +1,48 @@
---
name: design-nurture
description: Produces a multi-stage nurture journey blueprint with segmentation, triggers, and content plan.
usage: /lead-nurture-orchestration:design-nurture --goal pipeline --segments "mid-market,enterprise" --length 6
---
# Command: design-nurture
## Inputs
- **goal** – pipeline, expansion, adoption, education, reactivation.
- **segments** – comma-separated audiences.
- **length** – desired number of steps/stages.
- **channels** – optional list (email, in-app, ads, SDR assist).
- **constraints** – optional compliance/brand limitations.
### GTM Agents Pattern & Plan Checklist
> Derived from GTM Agents orchestrator blueprint @puerto/plugins/orchestrator/README.md#112-325.
- **Pattern selection**: Most nurture builds follow a **pipeline** (brief → architecture → content → branching → measurement). Switch to **diamond** when content mapping and personalization work can run in parallel. Document the pattern in the plan header.
- **Plan schema**: Save `.claude/plans/plan-<timestamp>.json` with objective, stages, task IDs, parallel groups, context passing (e.g., audience segments), error handling, and success criteria (activation, SQL lift, etc.).
- **Tool hooks**: Reference `docs/gtm-essentials.md` (Serena for MAP/CRM automation patches, Context7 for platform docs, Sequential Thinking for retros, Playwright for landing/in-app QA).
- **Guardrails**: Set retry limits (default 2) and escalation flow (Nurture Architect → Marketing Ops Lead → RevOps) if automation validation fails.
- **Review**: Use `docs/usage-guide.md#orchestration-best-practices-puerto-parity` checklist before execution to confirm agents, dependencies, deliverables.
## Workflow
1. **Brief Alignment** – confirm ICP, lifecycle stage, KPIs, and signal availability.
2. **Stage Architecture** – define entry criteria, triggers, and suppression per segment.
3. **Content Mapping** – outline assets, offers, personalization tokens per touch.
4. **Branching & Fail-safes** – specify conditional logic, fallback steps, exit rules.
5. **Measurement Plan** – KPIs per stage, alerting, retro cadence, experiment backlog.
## Outputs
- Journey table (step, trigger, channel, asset, CTA, owner).
- Mermaid-style diagram or pseudo-code for automation teams.
- Asset + data requirements list with due dates and owners.
- Plan JSON entry stored/updated in `.claude/plans` for audit trail.
## Agent/Skill Invocations
- `nurture-architect` – leads design.
- `lifecycle-cadence` skill – validates pacing + suppression.
- `personalization-logic` skill – ensures tailored content blocks.
## GTM Agents Safeguards
- **Fallback agents**: note substitutions (e.g., Marketing Ops Partner covering Personalization) if a specialist is unavailable.
- **Escalation triggers**: if guardrails (drop-off %, unsubscribe, latency) breach twice within 48h, escalate per lifecycle rip-cord (Marketing Director + Sales Director).
- **Plan maintenance**: When segments, owners, or branching logic change, update the saved plan and reference change log in status packets.
---

48
commands/optimize-nurture.md Normal file
View File

@@ -0,0 +1,48 @@
---
name: optimize-nurture
description: Builds a nurture optimization plan with insights, experiments, and remediation tasks.
usage: /lead-nurture-orchestration:optimize-nurture --window 30d --kpis "activation,pipeline" --segments "enterprise"
---
# Command: optimize-nurture
## Inputs
- **window** – reporting period (7d, 14d, 30d, quarter).
- **kpis** – comma-separated metrics (opens, clicks, conversion, pipeline, velocity, unsub).
- **segments** – optional audience filters.
- **experiments** – optional list of running tests to review.
- **alerts** – optional thresholds for escalations.
### GTM Agents Pattern & Plan Checklist
> Based on GTM Agents orchestrator blueprint @puerto/plugins/orchestrator/README.md#112-325.
- **Pattern selection**: Optimization usually runs **pipeline** (data → insights → experiments → action plan → governance). If insights and experiment analysis can proceed in parallel, log a **diamond** segment + merge gate.
- **Plan schema**: Update `.claude/plans/plan-<timestamp>.json` with data sources, query/metric owners, experiment IDs, remediation tasks, risk guardrails, error handling, and success targets (activation %, pipeline lift, unsub ceiling).
- **Tool hooks**: Reference `docs/gtm-essentials.md` (Serena for pipeline diffs + data pulls, Context7 for platform docs, Sequential Thinking for retrospection, Playwright for QA of revised assets).
- **Guardrails**: Define retry limit (default 2) for automation fixes; escalation ladder = Nurture Analytics Partner → Marketing Ops Partner → Revenue Operations if alerts breach thresholds.
- **Review**: Run `docs/usage-guide.md#orchestration-best-practices-puerto-parity` before sharing to ensure agent coverage + deliverables are complete.
## Workflow
1. **Data Consolidation** – MAP stats, CRM pipeline, product usage, SDR assist metrics.
2. **Insight Detection** – highlight stages with drop-offs, fatigue, or high unsub rates.
3. **Experiment Analysis** – summarize test results, significance, and rollout recommendations.
4. **Action Plan** – propose new tests, content refresh, audience refinements, or sequencing changes.
5. **Governance** – log owners, deadlines, and dependencies for each recommendation.
## Outputs
- Optimization brief (insights, impact, recommended action, owner, due date).
- Updated experiment tracker with verdicts and next tests.
- Alert + SLA tracker for segments needing fast intervention.
- Plan JSON entry stored/updated in `.claude/plans` for auditability.
## Agent/Skill Invocations
- `nurture-analytics-partner` – leads analysis.
- `nurture-testing` skill – validates experiment rigor.
- `lifecycle-cadence` skill – checks pacing vs fatigue thresholds.
## GTM Agents Safeguards
- **Fallback agents**: record substitutes (e.g., Lifecycle Cadence covering analytics) when primary owners unavailable.
- **Escalation triggers**: if activation/pipeline KPIs fall below guardrail for two consecutive windows, invoke lifecycle rip-cord and notify Marketing + Sales leadership.
- **Plan maintenance**: every optimization cycle must append results + changes to the plan JSON and status packets, matching GTM Agents audit expectations.
---