zhongwei/gh-gtmagents-gtm-agents-plugins-customer-feedback-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 18:30:14 +08:00
commit bd4e235b9b
12 changed files with 428 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

49
commands/route-insights.md Normal file
View File

@@ -0,0 +1,49 @@
---
name: route-insights
description: Operationalizes feedback themes by assigning owners, communication plans, and tracking loops.
usage: /customer-feedback-orchestration:route-insights --themes file://themes.json --cadence monthly --channels "product,cs,marketing"
---
# Command: route-insights
## Inputs
- **themes** – JSON/CSV file or inline JSON containing prioritized themes from `synthesize-feedback`.
- **cadence** – meeting or reporting cadence (weekly, biweekly, monthly).
- **channels** – comma-separated functional audiences (product, cs, marketing, exec, community).
- **broadcast** – true/false toggle to auto-generate comms templates for customers.
- **tracking** – project tool identifier (asana, jira, notion) for action logging.
### GTM Agents Pattern & Plan Checklist
> Mirrors GTM Agents orchestrator blueprint @puerto/plugins/orchestrator/README.md#112-325.
- **Pattern selection**: Insight routing generally runs **pipeline** (theme intake → owner mapping → action serialization → communications → feedback loop). If action serialization + comms can run in parallel, document a **diamond** block with merge gate in the plan header.
- **Plan schema**: Save `.claude/plans/plan-<timestamp>.json` capturing theme set, DRIs, dependency graph (product, CS, marketing, exec), error handling, and success metrics (resolution rate, time-to-close, comms completion).
- **Tool hooks**: Reference `docs/gtm-essentials.md` stack—Serena for workflow automation diffs, Context7 for past retros + roadmap docs, Sequential Thinking for follow-up cadence, Playwright for portal/comms QA if needed.
- **Guardrails**: Default retry limit = 2 for task routing/comms failures; escalation ladder = Product Liaison → CX Leadership → Exec sponsor.
- **Review**: Run `docs/usage-guide.md#orchestration-best-practices-puerto-parity` before publishing to confirm dependencies, approvals, deliverables.
## Workflow
1. **Theme Intake** – validate scoring, persona coverage, and urgency tags.
2. **Owner Mapping** – assign DRIs per functional area, define success metrics, and set deadlines.
3. **Action Serialization** – create tasks/epics with references to supporting data and customer quotes.
4. **Communication Plan** – craft internal/external messaging, executive summaries, and customer follow-ups.
5. **Feedback Loop Setup** – configure progress dashboards, reminders, and close-the-loop alerts.
## Outputs
- Routing table (theme, owner, due date, metric, status).
- Internal + external comms templates referencing impact and next steps.
- Action tracker ready for import into chosen project tool.
- Plan JSON entry stored/updated in `.claude/plans` for audit trail.
## Agent/Skill Invocations
- `product-liaison` – ensures roadmap alignment and executive visibility.
- `cs-analyst` – verifies metrics + datasets tied to each action.
- `stakeholder-ops` skill – governs approvals, cadences, and comms.
- `insight-synthesis` skill – keeps narratives consistent with source data.
## GTM Agents Safeguards
- **Fallback agents**: document substitutes (e.g., CX Ops covering Product Liaison) when stakeholders unavailable.
- **Escalation triggers**: if SLAs for close-the-loop breaching twice or roadmap owners reject actions repeatedly, escalate via GTM Agents rip-cord and log remediation inside plan JSON.
- **Plan maintenance**: update plan JSON/change log when owners, cadences, or tracking tools change to maintain audit parity.
---

50
commands/run-survey.md Normal file
View File

@@ -0,0 +1,50 @@
---
name: run-survey
description: Launches customer surveys with sampling plans, question sets, and automation hooks.
usage: /customer-feedback-orchestration:run-survey --audience "admins" --goal adoption --channels "email,in-app" --deadline 2025-12-15
---
# Command: run-survey
## Inputs
- **audience** – persona or segment target (admins, champions, exec sponsors).
- **goal** – objective (adoption, roadmap validation, satisfaction, messaging test).
- **channels** – comma-separated distribution methods (email, in-app, community, CS-led).
- **deadline** – fielding end date or fixed duration.
- **incentive** – optional reward description or budget.
- **sample_size** – desired number of responses (numeric).
### GTM Agents Pattern & Plan Checklist
> Mirrors GTM Agents orchestrator blueprint @puerto/plugins/orchestrator/README.md#112-325.
- **Pattern selection**: Survey orchestration typically runs **pipeline** (brief → question design → sampling → monitoring → handoff). If question design + sampling prep run in parallel, note a **diamond** block with merge gate in the plan header.
- **Plan schema**: Save `.claude/plans/plan-<timestamp>.json` capturing audience, goals, sampling logic, dependency graph (legal, CS, research ops), error handling, and success metrics (response rate, completion %, demographic balance).
- **Tool hooks**: Reference `docs/gtm-essentials.md` stack—Serena for MAP automation diffs, Context7 for research SOPs + historic surveys, Sequential Thinking for pre/post-readouts, Playwright for survey QA.
- **Guardrails**: Default retry limit = 2 for distribution/QA failures; escalation ladder = Research Lead → Customer Marketing → Exec sponsor.
- **Review**: Run `docs/usage-guide.md#orchestration-best-practices-puerto-parity` before launch to confirm dependencies, approvals, deliverables.
## Workflow
1. **Brief Assembly** – capture goals, personas, hypotheses, and stakeholder approvals.
2. **Question Design** – generate question bank with logic, scales, and branching recommendations.
3. **Sampling & Distribution** – build target lists, dedupe suppression lists, schedule sends.
4. **Monitoring** – track response rates, data quality, and audience balance; trigger boosts if needed.
5. **Handoff** – package clean dataset + metadata for `synthesize-feedback` command.
## Outputs
- Survey plan (audience, sample, channels, incentive, timeline).
- Question set with logic map and translation/localization notes.
- Distribution checklist + automation steps for MAP/CS tooling.
- Plan JSON entry stored/updated in `.claude/plans` for audit trail.
## Agent/Skill Invocations
- `research-lead` – validates methodology and question quality.
- `cs-analyst` – ensures sampling + data integrity.
- `survey-design` skill – provides templates and guardrails.
- `stakeholder-ops` skill – outlines approvals + comms.
## GTM Agents Safeguards
- **Fallback agents**: document substitutes (e.g., CS Analyst covering Research Lead) when leads unavailable.
- **Escalation triggers**: if response rate misses guardrail twice or sampling bias detected, escalate via GTM Agents rip-cord and log corrective actions in plan JSON.
- **Plan maintenance**: update plan JSON/change log when audiences, question sets, or tooling stacks change to preserve audit parity.
---

49
commands/synthesize-feedback.md Normal file
View File

@@ -0,0 +1,49 @@
---
name: synthesize-feedback
description: Consolidates quantitative and qualitative signals into prioritized themes with opportunity sizing.
usage: /customer-feedback-orchestration:synthesize-feedback --window 60d --personas "admins,execs" --detail workshop
---
# Command: synthesize-feedback
## Inputs
- **window** – analysis horizon (30d, 60d, quarter) pulling data from surveys, support, usage, community.
- **personas** – optional filter for personas or segments to highlight.
- **detail** – summary | workshop controls depth of deliverables.
- **include-voice** – true/false to embed verbatim quotes.
- **impact-lens** – arr | adoption | satisfaction to drive prioritization lens.
### GTM Agents Pattern & Plan Checklist
> Mirrors GTM Agents orchestrator blueprint @puerto/plugins/orchestrator/README.md#112-325.
- **Pattern selection**: Feedback synthesis typically runs **pipeline** (aggregation → tagging → impact modeling → opportunity framing → narrative). If tagging + modeling can run in parallel, record a **diamond** block with merge gate in the plan header.
- **Plan schema**: Save `.claude/plans/plan-<timestamp>.json` capturing window, data feeds, dependency graph (CS, product, research, analytics), error handling, and success metrics (theme confidence, coverage %, time-to-synthesize).
- **Tool hooks**: Reference `docs/gtm-essentials.md` stack—Serena for taxonomy updates, Context7 for historic studies, Sequential Thinking for workshop prep, Playwright for dashboard QA when embedding outputs.
- **Guardrails**: Default retry limit = 2 for data pulls/tagging jobs; escalation ladder = Research Lead → CX Leadership → Exec sponsor.
- **Review**: Run `docs/usage-guide.md#orchestration-best-practices-puerto-parity` before workshops to confirm dependencies + deliverables.
## Workflow
1. **Data Aggregation** – collect structured/unstructured feedback from connected systems.
2. **Tagging & Clustering** – apply taxonomy, detect emerging topics, score severity + frequency.
3. **Impact Modeling** – quantify ARR, usage, or sentiment impact with supporting metrics.
4. **Opportunity Framing** – craft problem statements, desired outcomes, and proposed motions.
5. **Narrative Packaging** – produce decks/notes for PM, CS, marketing, and exec consumption.
## Outputs
- Theme matrix with impact, personas, confidence, and owner recommendations.
- Quote bank + evidence appendix tied to each theme.
- Action backlog seeds for `route-insights` command.
- Plan JSON entry stored/updated in `.claude/plans` for audit trail.
## Agent/Skill Invocations
- `cs-analyst` – leads data prep + scoring.
- `research-lead` – ensures insights align with study goals.
- `insight-synthesis` skill – provides framing templates and storytelling patterns.
- `survey-design` skill – highlights methodology caveats.
## GTM Agents Safeguards
- **Fallback agents**: document substitutes (e.g., CS Analyst covering Research Lead) when leads unavailable.
- **Escalation triggers**: if data completeness or confidence metrics miss thresholds twice, escalate via GTM Agents rip-cord and log remediation in plan JSON.
- **Plan maintenance**: update plan JSON/change log when data sources, personas, or impact lenses change to preserve audit history.
---