zhongwei/gh-gtmagents-gtm-agents-plugins-intent-signal-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 18:30:50 +08:00
commit f35582cbf8
12 changed files with 427 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

48
commands/connect-signals.md Normal file
View File

@@ -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.
---

49
commands/prioritize-accounts.md Normal file
View File

@@ -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.
---

49
commands/trigger-plays.md Normal file
View File

@@ -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.
---