/prd-v09-feedback-loop-setup

name: prd-v09-feedback-loop-setup
description: >
  Establish channels and processes for capturing and processing post-launch feedback during PRD v0.9 Go-to-Market.
  Triggers on requests to set up feedback systems, capture user input, or when user asks "how do we collect feedback?",
  "feedback loop", "user research", "post-launch feedback", "customer feedback", "NPS", "voice of customer".
  Outputs CFD- entries specialized for post-launch feedback capture.
context: fork
allowed-tools:
  - Read
  - Write
  - Edit
  - Glob
  - Grep
  - WebSearch
  - WebFetch

execution_modes:
  default: standard
  supports: [quick, standard, deep]

Feedback Loop Setup

Position in workflow: v0.9 Launch Metrics → **v0.9 Feedback Loop Setup** → v1.0 Market Adoption

Execution Mode

Default is **standard**. See [`.claude/rules/08-skill-execution-modes.md`](../../rules/08-skill-execution-modes.md) for selection logic.

| Mode | What this skill produces | |------|--------------------------| | **quick** | 1–2 channels (in-app + support); basic triage workflow | | **standard** | 3–4 channels; full processing workflow + sentiment tracking + SLAs | | **deep** | All channels + closed-loop tracking + voice-of-customer synthesis + escalation rules |

Consumes

This skill requires prior work from v0.9 Launch Metrics and v0.1-v0.8:

• **GTM-\* launch channels** (from v0.9 GTM Strategy) — Active launch channels (Product Hunt, email, paid ads, etc.) become feedback sources; GTM- messaging and channels inform where feedback will arrive
• **MON-\* monitoring dashboards and alerts** (from v0.8 Monitoring Setup) — MON- thresholds (latency, error rate, performance) define what qualifies as critical feedback; monitoring alerts can trigger deep-dive user research
• **KPI-\* launch targets and baselines** (from v0.9 Launch Metrics) — KPI- thresholds (Day 1/7/30/90 targets) inform feedback urgency and trigger investigation when below target; baseline performance metrics (p95 latency, error rate, conversion rate) provide context for performance feedback
• **CFD-\* baseline entries** (from v0.1-v0.4) — Baseline customer feedback hypotheses (user pain points, value propositions, competitive alternatives) become validation targets post-launch; feedback loop confirms or contradicts CFD- assumptions
• **PER-\* personas** (from v0.4 Persona Definition) — Persona segments (PER-001 Startup Founder, PER-002 Team Lead) enable feedback categorization by user type and prioritization by persona importance

This skill assumes v0.9 Launch Metrics is live with KPI- thresholds established, GTM- channels are active, and MON- dashboards are displaying baseline metrics.

Produces

This skill creates/updates:

• **CFD-\* post-launch feedback entries** (feedback capture specifications, channel/type-based) — Every piece of user feedback becomes a CFD- entry with source, sentiment, impact, and action taken; traced to GTM- channels and user personas
• **Feedback processing workflow/matrix** — Triage → Categorization → Prioritization → Action mapping showing how feedback flows from capture to ID updates (CFD- → FEA-/BR-/RISK- → EPIC-)
• **CFD-\* update entries** — CFD- entries updated with resolution status, outcome, and follow-up evidence, enabling confidence progression (initial feedback → validated pattern → implemented action → confirmed outcome)

All CFD-* post-launch entries are **evidential feedback records**, not confidence-based themselves but supporting confidence scoring on OTHER IDs:

• **Timestamped** (when feedback was received, to track trends and velocity)
• **Sourced** (channel, user segment, user ID if available for follow-up)
• **Categorized** (UX | Performance | Feature Gap | Bug | Praise | Confusion for trend analysis)
• **Prioritized** (Critical/High/Medium/Low with impact justification)
• **Actionable** (every CFD- either triggers ID creation/update or documents "won't fix" decision)
• **Closed-loop** (user receives response and can verify resolution)

Example CFD- post-launch entries:

CFD-101: "Can't figure out how to export my data"
Type: Support Ticket
Source: Intercom (GTM-002 email → user support request)
Date: 2025-01-15
User Segment: PER-001 (Startup Founder)

Verbatim: "I've been using the tool for a week and I can't find any way to export my work."

Processed:
  Category: Feature Gap
  Sentiment: Frustrated
  Priority: High
  Frequency: Repeated (3rd request this week)

Impact Assessment:
  Users Affected: ~50 (based on support volume)
  KPI Impact: KPI-104 (D7 Retention) — export needed for team use case
  Revenue Risk: High — multiple users mentioned "dealbreaker"

Action:
  Response: "Thanks for reaching out! Export is on our roadmap."
  Internal Action: Escalated to product team, added to backlog
  Linked IDs: FEA-025 (Export Feature) created, EPIC-05 updated
  Status: In Progress

Resolution:
  Outcome: FEA-025 shipped in v1.2
  Date: 2025-02-01
  Follow-up: Emailed user with release notes

Linked IDs: GTM-002 (email channel source), PER-001 (persona), KPI-104 (affected metric), FEA-025 (action taken), EPIC-05 (implementation)

---

CFD-102: NPS Detractor Response
Type: NPS Response
Source: In-App Survey (MON-005 trigger)
Date: 2025-01-18
User Segment: PER-002 (Team Lead)

Verbatim: "Score: 4. Too slow. Takes forever to load projects and I give up waiting."

Processed:
  Category: Performance
  Sentiment: Negative
  Priority: Critical
  Frequency: Trending (NPS dropped 10 points this week)

Impact Assessment:
  Users Affected: ~200 (20% of NPS responses mention speed)
  KPI Impact: KPI-103 (Activation), KPI-104 (Retention) — both trending down
  Revenue Risk: High — performance is activation blocker

Action:
  Response: N/A (anonymous survey)
  Internal Action: Performance spike investigation started (MON-001 latency breach detected)
  Linked IDs: RISK-012 (Performance Degradation) escalated, EPIC-06 prioritized for optimization
  Status: In Progress

Resolution:
  Outcome: Database query o