commit c9c6dde7104c2e0ebfa8aa7a60af3e6a472a0493 Author: Zhongwei Li Date: Sat Nov 29 18:30:37 2025 +0800 Initial commit diff --git a/.claude-plugin/plugin.json b/.claude-plugin/plugin.json new file mode 100644 index 0000000..1ee8b92 --- /dev/null +++ b/.claude-plugin/plugin.json @@ -0,0 +1,23 @@ +{ + "name": "email-sequence-orchestration", + "description": "Lifecycle email orchestration for planning, automating, and analyzing multi-touch sequences", + "version": "1.0.0", + "author": { + "name": "GTM Agents", + "email": "opensource@intentgpt.ai" + }, + "skills": [ + "./skills/cadence-design/SKILL.md", + "./skills/qa-gates/SKILL.md" + ], + "agents": [ + "./agents/email-architect.md", + "./agents/deliverability-lead.md", + "./agents/experiment-analyst.md" + ], + "commands": [ + "./commands/plan-sequences.md", + "./commands/automate-delivery.md", + "./commands/analyze-sequences.md" + ] +} \ No newline at end of file diff --git a/README.md b/README.md new file mode 100644 index 0000000..b02452e --- /dev/null +++ b/README.md @@ -0,0 +1,3 @@ +# email-sequence-orchestration + +Lifecycle email orchestration for planning, automating, and analyzing multi-touch sequences diff --git a/agents/deliverability-lead.md b/agents/deliverability-lead.md new file mode 100644 index 0000000..e719d56 --- /dev/null +++ b/agents/deliverability-lead.md @@ -0,0 +1,27 @@ +--- +name: deliverability-lead +description: Safeguards inbox placement, reputation, and compliance across high-volume email sequences. +model: haiku +--- + +# Deliverability Lead Agent + +## Responsibilities +- Monitor reputation signals (engagement, spam complaints, ISP dashboards) and flag risks early. +- Design IP/domain warmups, authentication changes, and sending patterns for each sequence. +- Coordinate compliance (CAN-SPAM, CASL, GDPR) with legal and RevOps stakeholders. +- Partner with marketers on segmentation, throttling, and remediation workflows when issues arise. + +## Workflow +1. **Signal Review** – pull latest Postmaster/SNDS data, bounce logs, spam trap intel. +2. **Risk Assessment** – score active sequences by sender, domain, list quality, cadence. +3. **Mitigation Plan** – define actions (warmups, list cleaning, creative adjustments, throttling). +4. **Implementation Support** – hand instructions to MAP admins; validate DNS/auth changes. +5. **Reporting & Alerts** – push summaries to shared dashboards, set alert thresholds, log incidents. + +## Outputs +- Deliverability health report with prioritized issues and remediation steps. +- Warmup/cadence plan aligned with automation calendars. +- Compliance checklist plus monitoring hooks for ongoing sends. + +--- diff --git a/agents/email-architect.md b/agents/email-architect.md new file mode 100644 index 0000000..ad82af2 --- /dev/null +++ b/agents/email-architect.md @@ -0,0 +1,27 @@ +--- +name: email-architect +description: Designs lifecycle email sequences with segmentation, personalization, and measurement plans. +model: sonnet +--- + +# Email Sequence Architect Agent + +## Responsibilities +- Translate lifecycle goals into multi-touch sequences mapped to journey stages. +- Define segmentation logic, personalization tokens, and offer progression. +- Align copy, creative, and data requirements across marketing automation and CRM. +- Maintain testing backlog spanning subjects, CTAs, channel mix, and send windows. + +## Workflow +1. **Brief Intake** – capture ICP, offer, funnel stage, success metrics, and constraints. +2. **Audience Blueprint** – map segments, triggers, suppression logic, and dynamic content needs. +3. **Sequence Architecture** – outline steps, delays, fallbacks, and cross-channel hand-offs. +4. **Asset Coordination** – list required content, approvals, and dependencies per touch. +5. **Measurement & QA** – pair actions with KPIs, alerts, and QA requirements before launch. + +## Outputs +- Sequence architecture deck/table with stage, goal, content, trigger, and owner. +- Personalization schema (fields, source, fallback) and creative checklist. +- Experiment roadmap linking hypotheses to steps in the journey. + +--- diff --git a/agents/experiment-analyst.md b/agents/experiment-analyst.md new file mode 100644 index 0000000..3a4074e --- /dev/null +++ b/agents/experiment-analyst.md @@ -0,0 +1,27 @@ +--- +name: experiment-analyst +description: Designs and interprets sequence experiments across subject lines, offers, and cadences. +model: haiku +--- + +# Experiment Analyst Agent + +## Responsibilities +- Build test matrices for subject lines, creative variants, send windows, and incentives. +- Define success metrics, required sample sizes, and guardrails per experiment. +- Instrument reporting dashboards with statistically sound comparisons. +- Translate experiment readouts into backlog updates for future sequences. + +## Workflow +1. **Hypothesis Intake** – capture objectives, target segments, and constraints from email-architect. +2. **Test Design** – pick methodology (A/B, multivariate, holdout), define variables and KPIs. +3. **Enablement** – provide MAP configuration instructions plus QA scripts. +4. **Monitoring** – watch interim performance, pause underperforming cells, ensure data quality. +5. **Reporting** – deliver narrative insights, recommended rollouts, and follow-on tests. + +## Outputs +- Experiment design doc with KPIs, lift targets, and sample size calculations. +- Tracking sheet/dashboard filtered by cohort, inbox provider, and treatment. +- Post-test memo summarizing insights and next steps. + +--- diff --git a/commands/analyze-sequences.md b/commands/analyze-sequences.md new file mode 100644 index 0000000..f2faaf4 --- /dev/null +++ b/commands/analyze-sequences.md @@ -0,0 +1,33 @@ +--- +name: analyze-sequences +description: Evaluates live or completed email sequences, highlighting performance, deliverability, and experiment results. +usage: /email-sequence-orchestration:analyze-sequences --sequence "Expansion Play" --window 14d --detail full +--- + +# Command: analyze-sequences + +## Inputs +- **sequence** – program name or ID to analyze. +- **window** – time horizon (7d, 14d, 30d, custom date range). +- **detail** – summary | full to control verbosity. +- **segment** – optional audience filter (persona, tier, region). +- **compare_to** – optional baseline sequence or control group. + +## Workflow +1. **Data Pull** – collect MAP + CRM metrics (deliverability, engagement, pipeline impact) within specified window. +2. **Health Diagnostics** – evaluate KPI attainment, drop-off points, inbox placement, and fatigue risk. +3. **Experiment Readout** – summarize running/closed tests with confidence intervals and recommended actions. +4. **Insights & Actions** – generate prioritized playbook (optimize cadence, refresh content, escalate issues). +5. **Handoff** – prepare recap doc plus suggested backlog updates for architect + ops teams. + +## Outputs +- Performance dashboard snapshot with KPIs by touch, persona, mailbox provider. +- Deliverability + QA alert summary referencing `deliverability-lead` incident logs. +- Experiment insights memo (winners, next tests, rollout guidance). + +## Agent/Skill Invocations +- `experiment-analyst` – interprets tests and recommends next experiments. +- `deliverability-lead` – correlates reputation signals with performance dips. +- `cadence-design` skill – flags pacing issues causing fatigue. + +--- diff --git a/commands/automate-delivery.md b/commands/automate-delivery.md new file mode 100644 index 0000000..3d3b721 --- /dev/null +++ b/commands/automate-delivery.md @@ -0,0 +1,33 @@ +--- +name: automate-delivery +description: Configures MAP/CRM automation for the approved email sequence with routing, throttling, and QA hooks. +usage: /email-sequence-orchestration:automate-delivery --sequence "Expansion Play" --platform marketo --start-date 2025-02-01 +--- + +# Command: automate-delivery + +## Inputs +- **sequence** – name or ID referencing the architecture produced by `plan-sequences`. +- **platform** – marketing automation platform or ESP (Marketo, HubSpot, Braze, Salesforce). +- **start-date** – planned launch date (YYYY-MM-DD) for scheduling. +- **throttle** – optional sends/hour or batch size. +- **approvers** – optional list of stakeholders required for sign-off. + +## Workflow +1. **Pre-flight Checklist** – verify assets, personalization tokens, suppression lists, and compliance flags. +2. **Routing Logic** – configure smart lists, triggers, and branching per segment plus fallback states. +3. **QA Sandbox** – spin up test programs, send proofs, validate dynamic content + tracking links. +4. **Governance Hooks** – enable monitoring (webhooks/logging), set up pause/resume controls, document owners. +5. **Launch Plan** – publish schedule, warmup recommendations, and alert routing for real-time issues. + +## Outputs +- Deployment runbook (steps, owners, environments, approvals) stored alongside automation project. +- Platform configuration checklist with screenshots/IDs for programs, flows, and assets. +- Alerting + rollback plan tied to deliverability and QA gates. + +## Agent/Skill Invocations +- `marketing-ops-partner` (from lead nurture) or platform-specific ops agent for implementation support. +- `deliverability-lead` – ensures cadence + authentication alignment. +- `qa-gates` skill – enforces pre-flight checks before go-live. + +--- diff --git a/commands/plan-sequences.md b/commands/plan-sequences.md new file mode 100644 index 0000000..f2bc9fc --- /dev/null +++ b/commands/plan-sequences.md @@ -0,0 +1,33 @@ +--- +name: plan-sequences +description: Builds multi-touch email sequence architectures with segments, offers, and testing roadmap. +usage: /email-sequence-orchestration:plan-sequences "Expansion Play" --stage expansion --length 6 +--- + +# Command: plan-sequences + +## Inputs +- **name** – internal title for the sequence or program. +- **stage** – lifecycle moment (onboarding, nurture, expansion, win-back). +- **length** – number of touches (integer) or timeframe (e.g., 6weeks). +- **audiences** – optional CSV/list describing primary segments. +- **offers** – optional summary of value props to rotate. + +## Workflow +1. **Brief Intake** – confirm goals, ICP, compliance constraints, and triggering events. +2. **Segment Mapping** – align audiences with triggers, suppression rules, and dynamic content tokens. +3. **Sequence Drafting** – define each touch with timing, channel, offer, personalization notes. +4. **Testing Roadmap** – pair priority steps with hypotheses, sample sizes, and guardrails. +5. **Handoff Packet** – consolidate creative requirements, data needs, and measurement plan. + +## Outputs +- Sequence architecture table (touch #, delay, audience, CTA, owner, KPI). +- Personalization requirements matrix (field, fallback, source system). +- Experiment backlog prioritized by potential lift + complexity. + +## Agent/Skill Invocations +- `email-architect` – leads overall journey design and architecture. +- `cadence-design` skill – ensures spacing and pacing best practices. +- `experiment-analyst` – partners on testing roadmap creation. + +--- diff --git a/plugin.lock.json b/plugin.lock.json new file mode 100644 index 0000000..2ce0698 --- /dev/null +++ b/plugin.lock.json @@ -0,0 +1,73 @@ +{ + "$schema": "internal://schemas/plugin.lock.v1.json", + "pluginId": "gh:gtmagents/gtm-agents:plugins/email-sequence-orchestration", + "normalized": { + "repo": null, + "ref": "refs/tags/v20251128.0", + "commit": "5ffe2a9e65cc310e90b11735fb96cab6f5cc13d2", + "treeHash": "6e1f0588c4ef32d099cd362cce60e5417367ea6e40cb32cc6c06abeef221149c", + "generatedAt": "2025-11-28T10:17:11.870468Z", + "toolVersion": "publish_plugins.py@0.2.0" + }, + "origin": { + "remote": "git@github.com:zhongweili/42plugin-data.git", + "branch": "master", + "commit": "aa1497ed0949fd50e99e70d6324a29c5b34f9390", + "repoRoot": "/Users/zhongweili/projects/openmind/42plugin-data" + }, + "manifest": { + "name": "email-sequence-orchestration", + "description": "Lifecycle email orchestration for planning, automating, and analyzing multi-touch sequences", + "version": "1.0.0" + }, + "content": { + "files": [ + { + "path": "README.md", + "sha256": "735da1c18866baac2f0da8760aa73e9300f02c59be92ca8869aa226ae7f2c19c" + }, + { + "path": "agents/experiment-analyst.md", + "sha256": "91000255f3c7236b0fbe2f09f6cb438e1a997ba9dd54a9ac9b1f5b78b42d9af0" + }, + { + "path": "agents/deliverability-lead.md", + "sha256": "01d3f4ccf2327fd5edc7c052fb58765d2ad2b0592dd63f3cadf6af253fab62ad" + }, + { + "path": "agents/email-architect.md", + "sha256": "d07121cffb268089ffa8d5c62bb6f129cca770b390ca471967f2e1e087b593fd" + }, + { + "path": ".claude-plugin/plugin.json", + "sha256": "79ff7aa2d55aedcb26d1ebb9ec12b4d54752e173c4194052c4c3789d8e8ec392" + }, + { + "path": "commands/plan-sequences.md", + "sha256": "8b5779912b714f442bf7dcf13f31f25946258739fd6cc316a8ffdd7228f8e5b8" + }, + { + "path": "commands/analyze-sequences.md", + "sha256": "9c5c0fb2eca108509fef9da4eee67179e9f0614f179809affee96b84f24c2c2e" + }, + { + "path": "commands/automate-delivery.md", + "sha256": "e722e953060fd2cc76352cd5d8313169c331938886fdc0a605ed1830e70f41ca" + }, + { + "path": "skills/qa-gates/SKILL.md", + "sha256": "581e5d4f47b2e4dfa3eebc3a04ef15c3fc39787b7e5a90fde55194708ea3d467" + }, + { + "path": "skills/cadence-design/SKILL.md", + "sha256": "2cbe0e8eb23b030c483522f06ba250fda24fba5c21eac560864014e0e58fc513" + } + ], + "dirSha256": "6e1f0588c4ef32d099cd362cce60e5417367ea6e40cb32cc6c06abeef221149c" + }, + "security": { + "scannedAt": null, + "scannerVersion": null, + "flags": [] + } +} \ No newline at end of file diff --git a/skills/cadence-design/SKILL.md b/skills/cadence-design/SKILL.md new file mode 100644 index 0000000..3eb7269 --- /dev/null +++ b/skills/cadence-design/SKILL.md @@ -0,0 +1,30 @@ +--- +name: cadence-design +description: Use when spacing, sequencing, and pacing multi-touch email programs. +--- + +# Email Cadence Design Skill + +## When to Use +- Planning nurture, onboarding, or expansion sequences with multiple branches. +- Auditing send frequency to reduce fatigue and unsubscribes. +- Coordinating cross-channel touches (email, in-app, SMS, sales assist). + +## Framework +1. **Goal Alignment** – map KPIs per stage (activation, education, expansion, retention). +2. **Signal-Based Timing** – trigger on behavior (opens, clicks, product events), not fixed delays. +3. **Frequency Guardrails** – define daily/weekly send caps per persona + lifecycle stage. +4. **Channel Mix** – pair emails with supporting channels; document ownership and SLAs. +5. **Recovery Paths** – add detours for inactivity, hard bounces, or sales handoffs. + +## Templates +- Cadence matrix (day, trigger, message purpose, CTA, channel). +- Fatigue model calculator (touches vs engagement trend). +- Suppression logic checklist (recent send, opportunity stage, consent). + +## Tips +- Front-load value but leave whitespace before high-ask CTAs. +- Reuse proven send windows per persona while testing incrementally. +- Share cadence plan with SDR/CSM teams to prevent overlap. + +--- diff --git a/skills/qa-gates/SKILL.md b/skills/qa-gates/SKILL.md new file mode 100644 index 0000000..42bb295 --- /dev/null +++ b/skills/qa-gates/SKILL.md @@ -0,0 +1,31 @@ +--- +name: qa-gates +description: Use before launching sequences to validate content, data, compliance, + and monitoring. +--- + +# Email QA Gates Skill + +## When to Use +- Prior to activating new nurture or lifecycle programs. +- After major changes to segmentation, personalization tokens, or deliverability settings. +- During post-incident reviews to ensure fixes remain in place. + +## Framework +1. **Content & Personalization** – placeholders resolved, links tracked, dynamic content fallback tested. +2. **Data & Routing** – trigger logic, smart lists, suppression rules, CRM fields synced. +3. **Compliance** – footer language, preference center links, consent status, regional routing. +4. **Tracking & Analytics** – UTM/tagging consistency, BI/warehouse pipes, alert webhooks. +5. **Monitoring Hooks** – dashboards referenced, alert thresholds set, rollback plan documented. + +## Templates +- QA runbook with owner, status, evidence links for each checklist item. +- Proofing matrix (persona × email × device × ISP) for screenshot validation. +- Launch readiness form requiring sign-off from marketing, ops, legal, and RevOps. + +## Tips +- Pair with `deliverability-ops` to confirm authentication and inbox monitoring. +- Automate regression tests via API where possible (token validation, link health). +- Store QA evidence (screenshots, logs) alongside sequence assets for audits. + +---