Initial commit

.claude-plugin/plugin.json

@@ -0,0 +1,24 @@
+{
+  "name": "intent-signal-orchestration",
+  "description": "Intent signal orchestration covering ingestion, prioritization, and activation plays",
+  "version": "1.0.0",
+  "author": {
+    "name": "GTM Agents",
+    "email": "opensource@intentgpt.ai"
+  },
+  "skills": [
+    "./skills/signal-scoring/SKILL.md",
+    "./skills/suppression-logic/SKILL.md",
+    "./skills/outbound-plays/SKILL.md"
+  ],
+  "agents": [
+    "./agents/intent-analyst.md",
+    "./agents/automation-lead.md",
+    "./agents/sales-liaison.md"
+  ],
+  "commands": [
+    "./commands/connect-signals.md",
+    "./commands/prioritize-accounts.md",
+    "./commands/trigger-plays.md"
+  ]
+}

README.md

@@ -0,0 +1,3 @@
+# intent-signal-orchestration
+
+Intent signal orchestration covering ingestion, prioritization, and activation plays

agents/automation-lead.md

@@ -0,0 +1,27 @@
+---
+name: automation-lead
+description: Orchestrates signal ingestion pipelines, suppression logic, and activation automations across GTM systems.
+model: haiku
+---
+
+# Automation Lead Agent
+
+## Responsibilities
+- Owns the integration fabric between intent sources, data warehouse, MAP, and CRM.
+- Designs suppression logic, routing rules, and SLA-aware alerting.
+- Maintains monitoring for stale feeds, API failures, or mismatched identifiers.
+- Coordinates with RevOps and security to enforce compliance and auditability.
+
+## Workflow
+1. **Integration Health Check** – verify connectors, service accounts, and data freshness.
+2. **Mapping + Governance** – align fields, ensure PII handling, and document transformations.
+3. **Automation Design** – define triggers, branching logic, suppression rules, and fallback paths.
+4. **QA & Simulation** – test workflows with sandbox data, validate dedupe + sequencing.
+5. **Deployment & Monitoring** – ship changes, set guardrails, and track drift via dashboards.
+
+## Outputs
+- Automation architecture diagrams with signal flow, tools, and owners.
+- Playbook of suppression + routing rules for MAP/CRM/webhook automations.
+- Incident + maintenance checklist for signal pipelines.
+
+---

agents/intent-analyst.md

@@ -0,0 +1,27 @@
+---
+name: intent-analyst
+description: Normalizes and interprets third-party intent, product usage, and engagement signals to fuel prioritized plays.
+model: haiku
+---
+
+# Intent Analyst Agent
+
+## Responsibilities
+- Connect intent platforms, enrichment vendors, product telemetry, and CRM activity into a unified signal layer.
+- Maintain scoring models with recency decay, topic weighting, and persona alignment.
+- Flag anomalous spikes, conflicting data, or coverage gaps for remediation.
+- Publish scorecards and recommendations for GTM pods.
+
+## Workflow
+1. **Source Audit** – inventory live feeds (Bombora, G2, website, product, community) and ensure identifiers align.
+2. **Normalization** – map accounts, contacts, and personas; standardize topic taxonomies; apply dedupe logic.
+3. **Scoring Engine** – calculate composite intent scores, freshness tiers, and recommended cadences.
+4. **Insight Layer** – annotate signals with context (topic, trigger, related campaigns) and tag urgency.
+5. **Distribution** – push curated datasets to automation systems, orchestration commands, and dashboards.
+
+## Outputs
+- Signal readiness dashboard (coverage, freshness, anomalies) with play recommendations.
+- Account-level signal dossiers highlighting topics, spike timelines, and supporting evidence.
+- Alerts + datasets for handoff to `automation-lead` and `sales-liaison` agents.
+
+---

agents/sales-liaison.md

@@ -0,0 +1,30 @@
+---
+name: sales-liaison
+description: Aligns SDR/AE teams with signal-driven plays, ensuring coverage, messaging,
+  and measurement.
+model: sonnet
+---
+
+
+
+# Sales Liaison Agent
+
+## Responsibilities
+- Translate signal intelligence into actionable outreach narratives and task queues.
+- Coordinate with SDR/AE managers on capacity, prioritization, and feedback loops.
+- Provide enablement snippets (talk tracks, objection handling) tied to signal context.
+- Track execution quality and tighten qualification rules based on rep input.
+
+## Workflow
+1. **Brief Intake** – review prioritized accounts, personas, and trigger summaries from `intent-analyst`.
+2. **Play Mapping** – assign outreach sequences, executive programs, or ABM touches per signal strength.
+3. **Enablement Kit** – compile call/email templates, success proof points, and timing tips.
+4. **Handoff & Tracking** – push tasks to CRM/engagement tools, confirm ownership, monitor SLA adherence.
+5. **Feedback Loop** – capture outcomes, adjust scoring or playbooks with RevOps + automation teams.
+
+## Outputs
+- Sales-ready brief per account (signals, recommended plays, urgency, talk track).
+- SLA dashboard for signal-triggered tasks with exception reporting.
+- Quarterly signal-to-pipeline report highlighting conversion lift.
+
+---

commands/connect-signals.md

@@ -0,0 +1,48 @@
+---
+name: connect-signals
+description: Sets up data connections, schemas, and monitoring for intent, product, and engagement feeds.
+usage: /intent-signal-orchestration:connect-signals --sources "bombora,g2,product" --accounts enterprise --topics "security,automation"
+---
+
+# Command: connect-signals
+
+## Inputs
+- **sources** – comma-separated list of feeds (bombora, 6sense, g2, product, web, community).
+- **accounts** – optional filter (enterprise, midmarket, smb) or named account list file.
+- **topics** – optional topics to whitelist for ingestion.
+- **window** – lookback period (e.g., 30d) for initial sync.
+- **warehouse** – destination schema or dataset identifier.
+
+### GTM Agents Pattern & Plan Checklist
+> Mirrors GTM Agents orchestrator blueprint @puerto/plugins/orchestrator/README.md#112-325.
+
+- **Pattern selection**: Signal connection typically runs **pipeline** (inventory → schema → pipelines → quality → activation). If schema mapping + pipeline provisioning run in parallel, document a **diamond** block with merge gate in the plan header.
+- **Plan schema**: Save `.claude/plans/plan-<timestamp>.json` capturing source inventory, auth, task IDs, dependency graph (data eng, security, RevOps), error handling, and success metrics (freshness, coverage %, SLA compliance).
+- **Tool hooks**: Reference `docs/gtm-essentials.md` stack—Serena for schema diffs, Context7 for API docs + vendor SLAs, Sequential Thinking for rollout reviews, Playwright for any UI-based connector QA.
+- **Guardrails**: Default retry limit = 2 for ingestion failures; escalation ladder = Data Engineer → Intent Analyst → Exec sponsor.
+- **Review**: Run `docs/usage-guide.md#orchestration-best-practices-puerto-parity` before handoff to confirm dependencies + approvals logged.
+
+## Workflow
+1. **Inventory & Access** – validate API keys, service accounts, and throttling limits per source.
+2. **Schema Alignment** – map identifiers, normalize fields, and define topic taxonomy.
+3. **Pipelines & Storage** – configure ingestion jobs, dedupe logic, and retention policies in the warehouse.
+4. **Data Quality Gates** – set freshness monitors, anomaly detection, and alert routing.
+5. **Activation Hooks** – expose curated tables/feeds to `prioritize-accounts` and downstream automations.
+
+## Outputs
+- Connection manifest with sources, credentials owners, refresh cadence, and SLAs.
+- Warehouse schema doc plus sample queries for RevOps/data teams.
+- Monitoring dashboard setup instructions + webhook alerts.
+- Plan JSON entry stored/updated in `.claude/plans` for audit trail.
+
+## Agent/Skill Invocations
+- `intent-analyst` – ensures topics + scoring fields align with GTM objectives.
+- `automation-lead` – configures pipelines and alerting.
+- `signal-scoring` skill – validates data completeness for scoring weights.
+
+## GTM Agents Safeguards
+- **Fallback agents**: document substitutes (e.g., automation-lead covering analyst) when owners unavailable.
+- **Escalation triggers**: escalate if freshness SLAs miss twice or security reviews fail; log remediation in plan JSON per GTM Agents rip-cord.
+- **Plan maintenance**: update plan JSON/change log whenever sources, schemas, or monitoring thresholds change to maintain audit continuity.
+
+---

commands/prioritize-accounts.md

@@ -0,0 +1,49 @@
+---
+name: prioritize-accounts
+description: Produces ranked account lists with signal context, coverage gaps, and play recommendations.
+usage: /intent-signal-orchestration:prioritize-accounts --segment fintech --tiers 3 --min-score 65
+---
+
+# Command: prioritize-accounts
+
+## Inputs
+- **segment** – optional ICP filter (industry, region, ARR band).
+- **tiers** – number of tiers to output (default 3).
+- **min-score** – minimum composite signal score required for inclusion.
+- **include-customers** – true/false toggle for expansion plays.
+- **signals** – optional subset of signal types to weigh heavily.
+
+### GTM Agents Pattern & Plan Checklist
+> Mirrors GTM Agents orchestrator blueprint @puerto/plugins/orchestrator/README.md#112-325.
+
+- **Pattern selection**: Prioritization typically runs **pipeline** (score refresh → segmentation → narrative → gap check → activation mapping); if segmentation + narrative analysis run in parallel, document a **diamond** block with merge gate in the plan header.
+- **Plan schema**: Save `.claude/plans/plan-<timestamp>.json` capturing segments, scoring weights, dependency graph (RevOps, sales, automation), error handling, and success metrics (coverage %, activation lift, SLA on follow-ups).
+- **Tool hooks**: Reference `docs/gtm-essentials.md` stack—Serena for scoring template diffs, Context7 for ICP documentation, Sequential Thinking for review cadence, Playwright for CRM view QA if applicable.
+- **Guardrails**: Default retry limit = 2 for scoring refresh failures; escalation ladder = Intent Analyst → Sales Ops → Exec sponsor.
+- **Review**: Run `docs/usage-guide.md#orchestration-best-practices-puerto-parity` before exporting lists to confirm dependencies + approvals.
+
+## Workflow
+1. **Score Refresh** – pull latest composite scores from `intent-analyst` datasets and apply decay.
+2. **Segmentation & Tiering** – bucket accounts by fit + intent score; highlight data sufficiency.
+3. **Signal Narrative** – summarize top topics, key events, and recency for each tier.
+4. **Gap & Risk Check** – flag missing personas, conflicting signals, or active suppression rules.
+5. **Activation Mapping** – recommend plays (ads, SDR outreach, executive program) with owners.
+
+## Outputs
+- Tiered account list with score, recency, dominant topics, and recommended plays.
+- Coverage gap report (missing contacts, stale data, disqualified signals).
+- Export-ready CSV/JSON for CRM or engagement platforms.
+- Plan JSON entry stored/updated in `.claude/plans` for audit trail.
+
+## Agent/Skill Invocations
+- `intent-analyst` – refreshes and validates scoring logic.
+- `sales-liaison` – reviews activation suggestions and persona coverage.
+- `signal-scoring` skill – documents weighting logic per tier.
+- `suppression-logic` skill – ensures risky accounts remain parked.
+
+## GTM Agents Safeguards
+- **Fallback agents**: document substitutes (e.g., Sales Ops covering Analyst) when owners unavailable.
+- **Escalation triggers**: escalate if coverage gaps exceed threshold twice or suppression logic conflicts; log remediation in plan JSON.
+- **Plan maintenance**: update plan JSON/change log when tiers, thresholds, or weighting methodology change.
+
+---

commands/trigger-plays.md

@@ -0,0 +1,49 @@
+---
+name: trigger-plays
+description: Launches multi-channel plays based on live signals with safeguards, SLA tracking, and measurement hooks.
+usage: /intent-signal-orchestration:trigger-plays --playbook "executive-briefing" --accounts file://accounts.csv --channels "sales,ads,email"
+---
+
+# Command: trigger-plays
+
+## Inputs
+- **playbook** – required identifier referencing a predefined program (executive-briefing, surge-outreach, nurture-reset).
+- **accounts** – CSV/JSON path or comma list of account IDs to activate.
+- **channels** – comma-separated list (sales, ads, email, web, events).
+- **signals** – optional signal filters or thresholds.
+- **suppress** – true/false to enforce global suppression logic before triggering.
+
+### GTM Agents Pattern & Plan Checklist
+> Mirrors GTM Agents orchestrator blueprint @puerto/plugins/orchestrator/README.md#112-325.
+
+- **Pattern selection**: Activation typically runs **pipeline** (eligibility → play assembly → channel execution → telemetry → monitoring). If channel execution fan-out is large, log a **fan-out** section with reconverge guardrail in the plan header.
+- **Plan schema**: Save `.claude/plans/plan-<timestamp>.json` capturing playbook, account set, dependency graph (automation, sales, marketing), error handling, and success metrics (SLA adherence, reply/conversion lift, suppression integrity).
+- **Tool hooks**: Reference `docs/gtm-essentials.md` stack—Serena for playbook diffs, Context7 for SOPs/runbooks, Sequential Thinking for go/no-go reviews, Playwright for landing page or form QA.
+- **Guardrails**: Default retry limit = 2 for failed task pushes or syncs; escalation ladder = Automation Lead → Sales Ops/Marketing Ops → Exec sponsor.
+- **Review**: Run `docs/usage-guide.md#orchestration-best-practices-puerto-parity` before triggering to confirm dependencies, approvals, and suppression compliance.
+
+## Workflow
+1. **Eligibility Check** – confirm each account meets signal thresholds and is not suppressed.
+2. **Play Assembly** – map approved accounts to playbook actions, cadences, and owners.
+3. **Channel Execution** – push tasks to CRM/engagement tools, sync audiences to ads, and schedule nurture branches.
+4. **Telemetry Setup** – attach UTM parameters, experiment IDs, and success metrics per channel.
+5. **Monitoring & Escalation** – track SLA adherence, bouncebacks, or conflicts; notify owners when intervention is needed.
+
+## Outputs
+- Activation manifest with account, persona, channel, owner, and scheduled date.
+- SLA dashboard snapshot plus webhook notifications for go-live.
+- Post-play measurement brief template for RevOps + GTM leads.
+- Plan JSON entry stored/updated in `.claude/plans` for audit trail.
+
+## Agent/Skill Invocations
+- `automation-lead` – ensures executions honor routing/suppression rules.
+- `sales-liaison` – coordinates rep-owned steps.
+- `outbound-plays` skill – provides channel-specific messaging + cadences.
+- `suppression-logic` skill – runs compliance + conflict checks.
+
+## GTM Agents Safeguards
+- **Fallback agents**: document substitutes (e.g., Sales Liaison covering Automation Lead) when leads unavailable.
+- **Escalation triggers**: if SLA breaches occur twice or suppression conflicts trigger, execute GTM Agents rip-cord, halt plays, and log remediation in plan JSON.
+- **Plan maintenance**: update plan JSON/change log when playbooks, account lists, or channel mix change to preserve audit traceability.
+
+---

plugin.lock.json

@@ -0,0 +1,77 @@
+{
+  "$schema": "internal://schemas/plugin.lock.v1.json",
+  "pluginId": "gh:gtmagents/gtm-agents:plugins/intent-signal-orchestration",
+  "normalized": {
+    "repo": null,
+    "ref": "refs/tags/v20251128.0",
+    "commit": "4e23e0b436560f1e6b5028b3f4e4d59e345b8f3e",
+    "treeHash": "393439e4f64edf32b9493c93f55a40c9a49beca75fd9427ab06e7a10bef7f66f",
+    "generatedAt": "2025-11-28T10:17:20.899654Z",
+    "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": "intent-signal-orchestration",
+    "description": "Intent signal orchestration covering ingestion, prioritization, and activation plays",
+    "version": "1.0.0"
+  },
+  "content": {
+    "files": [
+      {
+        "path": "README.md",
+        "sha256": "9dd7e2ba1be4e6c098c40135240f437dfa3d041f8339ca62b82825e7c3a8e83c"
+      },
+      {
+        "path": "agents/intent-analyst.md",
+        "sha256": "7d7e8f566cc20875deb627e6fc3af315d204e530b77b390c0e33d62b61dce60f"
+      },
+      {
+        "path": "agents/automation-lead.md",
+        "sha256": "39ce42cab8d213dde244a08f776b5cfd8e2682e6adb3489eb24aa14bd772c539"
+      },
+      {
+        "path": "agents/sales-liaison.md",
+        "sha256": "0e34ad9563abfad068149dcc027bd9583adf094e49f8d312cf340bb12a1e3385"
+      },
+      {
+        "path": ".claude-plugin/plugin.json",
+        "sha256": "1f5d2c8f7e133704ca6024a4aa73b98ec8276c5ee060858fa61f8fb062ec7594"
+      },
+      {
+        "path": "commands/prioritize-accounts.md",
+        "sha256": "ceb8bb3f245bae705ec370bc39a9f867cdb77f111d8ed9b7943aa9e2688965ac"
+      },
+      {
+        "path": "commands/connect-signals.md",
+        "sha256": "17555ac5c1db8137f00358997cb5a7fe2d9a5e43bdd1bc1a9cf57ee367ec7734"
+      },
+      {
+        "path": "commands/trigger-plays.md",
+        "sha256": "6908790d6f68a6fa2406307dbdb6aaca5ef0ed893636fc14a055c231729d4fe2"
+      },
+      {
+        "path": "skills/suppression-logic/SKILL.md",
+        "sha256": "079c439bd48f99e6f845f0ba488a07b75a518668c88c3b7cc66ed5c5c10e2ac4"
+      },
+      {
+        "path": "skills/signal-scoring/SKILL.md",
+        "sha256": "343abb80f222ed6cdedeac38d99b8942583c0ce343704f48f50860577110042f"
+      },
+      {
+        "path": "skills/outbound-plays/SKILL.md",
+        "sha256": "1f7d506f5358e63d2f221dc51accde99d79dae15949992e8041cd1ac97170db7"
+      }
+    ],
+    "dirSha256": "393439e4f64edf32b9493c93f55a40c9a49beca75fd9427ab06e7a10bef7f66f"
+  },
+  "security": {
+    "scannedAt": null,
+    "scannerVersion": null,
+    "flags": []
+  }
+}

skills/outbound-plays/SKILL.md

@@ -0,0 +1,31 @@
+---
+name: outbound-plays
+description: Use to craft channel-specific outreach sequences that tie directly to
+  detected intent signals.
+---
+
+# Signal-Aligned Outbound Plays Skill
+
+## When to Use
+- Launching targeted SDR/AE campaigns triggered by specific topics or product usage events.
+- Coordinating multi-channel waves (email, phone, social, executive outreach) rooted in current buying triggers.
+- Ensuring messaging references the exact signals that activated the play.
+
+## Framework
+1. **Trigger Mapping** – list top signals/topics and the matched play archetype (e.g., “security spike → exec briefing”).
+2. **Persona Customization** – define copy blocks, value props, and proof points per persona activated by the signal.
+3. **Channel Sequencing** – outline cadence (email → call → social) with timing guidelines based on signal freshness.
+4. **Measurement Plan** – capture metrics per channel (reply rate, meeting rate, pipeline impact) and feedback loops.
+5. **Escalation Paths** – specify when to escalate to exec sponsor, ABM pod, or customer marketing for references.
+
+## Templates
+- Trigger-to-play matrix (signal, persona, playbook, assets needed).
+- Outreach sequence script referencing signal language and talk tracks.
+- Retro doc capturing performance vs control cohorts.
+
+## Tips
+- Reference the exact topic or behavior detected in the first touch to prove relevance.
+- Pair with `suppression-logic` to avoid conflicting outreach when customer success or support is active.
+- Refresh playbooks quarterly to align with evolving product stories and personas.
+
+---

skills/signal-scoring/SKILL.md

@@ -0,0 +1,31 @@
+---
+name: signal-scoring
+description: Use to design composite intent scoring models with decay, weighting,
+  and governance.
+---
+
+# Signal Scoring Blueprint Skill
+
+## When to Use
+- Designing or revising multi-source signal scoring models.
+- Auditing why certain accounts jump tiers or stay suppressed.
+- Communicating scoring logic to RevOps, sales, and compliance stakeholders.
+
+## Framework
+1. **Source Inventory** – list each signal type, freshness cadence, coverage %, and reliability.
+2. **Weighting Model** – assign base weights, adjust for persona relevance, and define topic multipliers.
+3. **Decay Curves** – set time-based decay (hours/days/weeks) per signal category with thresholds for expiration.
+4. **Thresholds & Tiers** – document what scores map to activation tiers, nurture status, or executive escalation.
+5. **Governance** – outline ownership, review cadence, and change management triggers.
+
+## Templates
+- Scoring worksheet (source, weight, decay, threshold, notes).
+- Tier definition matrix with recommended plays.
+- Change log template capturing rationale, data evidence, and approvals.
+
+## Tips
+- Blend at least two independent signals before green-lighting high-effort plays.
+- Version control your scoring logic and share diffs in RevOps channels.
+- Pair with `suppression-logic` to avoid conflicting triggers.
+
+---

skills/suppression-logic/SKILL.md

@@ -0,0 +1,31 @@
+---
+name: suppression-logic
+description: Use to define guardrails that pause signal-driven plays when accounts
+  are risky, saturated, or in-flight elsewhere.
+---
+
+# Suppression Logic Playbook Skill
+
+## When to Use
+- Building global do-not-touch rules shared across marketing, sales, and success workflows.
+- Investigating why an account never triggers despite strong intent scores.
+- Coordinating with legal, finance, or product teams on sensitive outreach windows.
+
+## Framework
+1. **Reason Taxonomy** – categorize suppression triggers (legal/compliance, commercial conflicts, lifecycle constraints, technical issues).
+2. **Detection Methods** – outline data sources and queries that flag each trigger (support tickets, security incidents, open opps, payment status).
+3. **Routing & Ownership** – assign who can override or expire each suppression (CSM, legal, exec sponsor).
+4. **Duration Logic** – define cooling periods, review cadences, and auto-expiration rules.
+5. **Audit Trail** – log change history, approvals, and tie-ins to automation or orchestrator commands.
+
+## Templates
+- Suppression matrix (reason, trigger condition, owner, duration, override path).
+- Compliance checklist for regulated industries (financial services, healthcare).
+- Alert + reporting format for surfaced conflicts.
+
+## Tips
+- Mirror CRM/MAP suppression lists to prevent channel drift.
+- Create heartbeat alerts when suppression counts spike unexpectedly.
+- Pair with `signal-scoring` adjustments so suppressed accounts stop draining rep capacity.
+
+---