zhongwei/gh-gtmagents-gtm-agents-plugins-community-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 18:29:57 +08:00
commit 28cbddad71
12 changed files with 423 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

48
commands/measure-engagement.md Normal file
View File

@@ -0,0 +1,48 @@
---
name: measure-engagement
description: Reviews community health metrics, sentiment, and experiment impact with recommended actions.
usage: /community-orchestration:measure-engagement --window 30d --detail full --dimensions "channel,persona"
---
# Command: measure-engagement
## Inputs
- **window** – time horizon (7d, 30d, 90d) for analysis.
- **detail** – summary | full report depth.
- **dimensions** – optional breakdown (channel, persona, program, cohort).
- **experiments** – optional list of programs to analyze.
- **alert_threshold** – optional metric threshold for escalations.
### GTM Agents Pattern & Plan Checklist
> Mirrors GTM Agents orchestrator blueprint @puerto/plugins/orchestrator/README.md#112-325.
- **Pattern selection**: Engagement measurement typically runs **pipeline** (data → diagnostics → sentiment → experiment readouts → actions). If diagnostics + experiment analysis can run in parallel, log a **diamond** segment with merge gate in the plan header.
- **Plan schema**: Save `.claude/plans/plan-<timestamp>.json` capturing window, data feeds, task IDs, dependency graph (analytics, CRM, sentiment tools), error handling, and success metrics (engagement %, advocacy, risk volume).
- **Tool hooks**: Reference `docs/gtm-essentials.md` stack—Serena for schema diffs, Context7 for platform documentation/conversation exports, Sequential Thinking for insights review cadence, Playwright for verifying dashboard/report embeds.
- **Guardrails**: Default retry limit = 2 for failed data pulls or sentiment processing; escalation ladder = Community Analyst → Community Lead → CS/Product leadership.
- **Review**: Run `docs/usage-guide.md#orchestration-best-practices-puerto-parity` before execution to confirm inputs, dependencies, deliverables.
## Workflow
1. **Data Pull** – aggregate platform analytics, CRM attribution, sentiment scores, and support signals.
2. **Health Diagnostics** – compute growth, activation, engagement, retention, and advocacy metrics by dimension.
3. **Sentiment Review** – scan community conversations, surveys, and NPS for emerging themes.
4. **Experiment Readouts** – evaluate running pilots against guardrails + KPIs.
5. **Action Recommendations** – produce prioritized playbook (content tweaks, ambassador outreach, escalations).
## Outputs
- Community health dashboard snapshot with annotated insights.
- Sentiment + risk report referencing `sentiment-analysis` findings.
- Recommended action list with owners, deadlines, and expected impact.
- Plan JSON entry stored/updated in `.claude/plans` for audit trail.
## Agent/Skill Invocations
- `community-analyst` – leads data aggregation and insights.
- `sentiment-analysis` skill – interprets qualitative signals and escalation needs.
- `community-lead` – receives action plan and drives follow-through.
## GTM Agents Safeguards
- **Fallback agents**: document substitutes (e.g., Community Lead covering Analyst) when analysts unavailable.
- **Escalation triggers**: if engagement drops below alert_threshold twice or sentiment exposes severe risks, escalate via GTM Agents rip-cord to cross-functional leadership.
- **Plan maintenance**: update plan JSON/change log when data sources, thresholds, or reporting cadences change to maintain GTM Agents audit parity.
---

48
commands/plan-community-calendar.md Normal file
View File

@@ -0,0 +1,48 @@
---
name: plan-community-calendar
description: Builds a rolling community programming calendar with themes, formats, and owners.
usage: /community-orchestration:plan-community-calendar --window 8weeks --channels "forum,events,slack" --themes "product,customer-stories"
---
# Command: plan-community-calendar
## Inputs
- **window** – planning horizon (e.g., 8weeks, quarter).
- **channels** – comma-separated community surfaces (forum, Slack, Discord, events, webinar, newsletter).
- **themes** – optional list of focus themes or series.
- **audiences** – optional persona/segment filters.
- **dependencies** – optional notes on launches, campaigns, or partner tie-ins.
### GTM Agents Pattern & Plan Checklist
> Mirrors GTM Agents orchestrator blueprint @puerto/plugins/orchestrator/README.md#112-325.
- **Pattern selection**: Community calendar planning typically runs **pipeline** (signals → themes → programming → resources → publishing). If programming segments (e.g., events vs async drops) run in parallel, capture a **diamond** segment with merge gate in the plan header.
- **Plan schema**: Save `.claude/plans/plan-<timestamp>.json` capturing window, channels, task IDs, dependency graph (hosts, moderators, asset teams), error handling, and success metrics (attendance, engagement %, advocacy contributions).
- **Tool hooks**: Reference `docs/gtm-essentials.md` stack—Serena for asset/promo diffs, Context7 for playbooks/guidelines, Sequential Thinking for governance/check-in cadence, Playwright for testing community microsites or forms if needed.
- **Guardrails**: Default retry limit = 2 for resource shortages or tooling failures; escalation ladder = Community Lead → Marketing/CS leadership → Exec sponsor.
- **Review**: Run `docs/usage-guide.md#orchestration-best-practices-puerto-parity` before execution to confirm owners, dependencies, deliverables.
## Workflow
1. **Signal Review** – pull engagement data, VOC insights, and upcoming GTM milestones.
2. **Theme Mapping** – align themes to goals (activation, adoption, advocacy) and persona interests.
3. **Programming Mix** – schedule events, AMAs, content drops, and spotlights with owners + formats.
4. **Resource Checklist** – detail required assets, hosts, moderators, and promo timelines.
5. **Publishing Packet** – output calendar plus reminders/automation hooks for each touch.
## Outputs
- Calendar table (date, theme, channel, format, owner, CTA, dependencies).
- Asset + promotion checklist with due dates.
- Risk log flagging capacity or approval gaps.
- Plan JSON entry stored/updated in `.claude/plans` for audit trail.
## Agent/Skill Invocations
- `community-lead` – sets strategy and approvals.
- `community-ops` skill – ensures workflows and tooling readiness.
- `community-analyst` – provides data context for theme prioritization.
## GTM Agents Safeguards
- **Fallback agents**: document substitutes (e.g., Community Ops covering Community Lead) when decision-makers unavailable.
- **Escalation triggers**: if capacity gaps or moderation risks appear twice in planning reviews, escalate to cross-functional steering committee per GTM Agents rip-cord.
- **Plan maintenance**: update plan JSON/change log when themes, channels, or dependencies change so audit trail matches GTM Agents standards.
---

50
commands/run-community-event.md Normal file
View File

@@ -0,0 +1,50 @@
---
name: run-community-event
description: Generates run of show, moderation plan, and follow-up tasks for community events or live sessions.
usage: /community-orchestration:run-community-event --event "Product AMA" --date 2025-12-05 --hosts "PM,CSM" --format livestream
---
# Command: run-community-event
## Inputs
- **event** – name or theme of the session.
- **date** – scheduled date/time (ISO or natural language).
- **hosts** – comma-separated speakers/moderators.
- **format** – webinar | livestream | roundtable | in-person | async.
- **audience** – optional persona/community segment.
- **goals** – optional KPIs (registrations, NPS, product adoption prompt).
### GTM Agents Pattern & Plan Checklist
> Mirrors GTM Agents orchestrator blueprint @puerto/plugins/orchestrator/README.md#112-325.
- **Pattern selection**: Live event orchestration generally runs **pipeline** (brief → run-of-show → moderation → promotion → follow-up). If moderation + promotion can run in parallel, document a **diamond** segment with merge gate in the plan header.
- **Plan schema**: Save `.claude/plans/plan-<timestamp>.json` capturing event details, task IDs, dependency graph (hosts, ops, tooling, accessibility), error handling, and success metrics (attendance, engagement rate, CSAT/NPS).
- **Tool hooks**: Reference `docs/gtm-essentials.md` stack—Serena for script/asset diffs, Context7 for event SOPs, Sequential Thinking for pre/post-mortem cadence, Playwright for registration/stream QA if needed.
- **Guardrails**: Default retry limit = 2 for tooling failures or host changes; escalation ladder = Community Lead → Marketing/CS leadership → Exec sponsor.
- **Review**: Run `docs/usage-guide.md#orchestration-best-practices-puerto-parity` before execution to confirm owners, dependencies, deliverables.
## Workflow
1. **Brief Assembly** – capture objectives, audience, and success metrics; pull relevant insights/content.
2. **Run of Show** – outline agenda, time stamps, speaker prompts, engagement moments, and CTAs.
3. **Moderation & Ops** – assign backstage roles, chat moderation guidelines, accessibility needs, and failovers.
4. **Promotion & Reminders** – auto-generate promo copy, schedule reminders, and update community calendar.
5. **Follow-up Plan** – create recap checklist (recording, notes, action items, support cases) and measurement hooks.
## Outputs
- Event runbook (agenda, host responsibilities, tech setup, contingency plan).
- Moderation worksheet with escalation triggers and response templates.
- Follow-up task list tied to owners and due dates.
- Plan JSON entry stored/updated in `.claude/plans` for audit trail.
## Agent/Skill Invocations
- `community-lead` – approves agenda + goals.
- `community-moderator` – executes moderation plan.
- `community-ops` skill – ensures tooling + workflows are ready.
- `escalation` skill – provides incident handling guidance.
## GTM Agents Safeguards
- **Fallback agents**: document substitutes (e.g., Moderator covering Community Lead) when hosts unavailable.
- **Escalation triggers**: if incidents breach guardrails (e.g., harassment, platform failure) escalate immediately per GTM Agents rip-cord; log remediation in plan JSON.
- **Plan maintenance**: update plan JSON/change log when hosts, formats, or tooling stack change so audit trail mirrors GTM Agents procedures.
---