- Home
- Skills
- Product Management
- Journey Designer
Journey Designer
Turn Capabilities into end-to-end user journeys and derive Features from real pain points, with a traceable Pain Point → Opportunity → Feature chain and embedded Mermaid diagrams.
$5
Works with the AI Agents you already use
Journey Designer
Example session with this skill installed
I've finished product framing. Let's design the journeys for C1 Real-Time Vehicle Monitoring.
- Read your context and instructions
- Compiled the journey designer
The skill loads C1 and persona P1 (Fleet Manager). It proposes merging ~S1 Daily Monitoring and ~S2 Vehicle Detail into one journey, "J1 Daily Vehicle Status Monitoring", with three phases: Overview → Filter → Detail. It enriches each phase step by step and finds 7 pain points, for example "can only search by plate number" (High/Fatal). It then derives F1 Unified Monitoring Dashboard, F2 Smart Vehicle Filter, F3 Real-Time Data Push and F4 Vehicle Detail Page, each traced to a pain point. It saves J1-daily-monitoring.md (with emotion map, derivation chain and priority quadrant diagrams) and F1–F4 feature files.
Connects securely to your tools. The creator never sees your data.
About this skill
Journey Designer
The middle layer of the Harness Skills product-management pipeline: Capability → Journeys → Features.
Journey Designer takes the Capabilities produced by Product Framer (with conceptual scenes ~S and feature candidates ~F). It walks you through each user journey, one question at a time, the way a senior BA would. It discovers pain points inside the steps users actually take, then derives Features from those pain points. It never invents them.
What it does
- Journey scoping: groups conceptual scenes into end-to-end journeys using merge rules (same persona + sequential/causal trigger).
- Phase-by-phase enrichment: steps, problems, touchpoints and emotion tags, all anchored to Persona data.
- Three-layer display (Service Blueprint style): User Actions / System Touchpoints / Product Support. This stops you mixing up what users do with what your product should do.
- Moments of Truth: rates each pain point for Severity and Criticality (Fatal / Important / Minor), with a two-gate boundary check.
- Traceable Feature derivation: Pain Point → Opportunity → Feature Candidate →
~Fcross-check → Feature. Every upstream~Fgets an explicit disposition. - Two-way gap analysis: Phase ↔ Feature coverage.
- Mermaid diagrams embedded in each journey file:
- Journey Emotion Map (always)
- Feature Derivation Chain (always)
- Service Blueprint (when there are 3+ touchpoints)
- Pain Point Priority quadrant (when there are 5+ pain points)
Output
product-management/
journeys/J{n}-{name}.md
features/F{n}-{name}.md
The files are structured markdown written for two readers: human BA/PM teams and downstream coding agents. The next step is User Story.
Methodology
The skill draws on Customer Journey Mapping, Shostack's Service Blueprint, Design Thinking (Define → Ideate), Carlzon's Moments of Truth and Contextual Inquiry. README.md includes a concept-to-source traceability table.
Package
SKILL.md, README.md, 5 reference files (enrichment protocol, feature derivation rules, diagram generation, state panels, a full worked example) and 2 templates (journey, feature).
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Product Management.
Prompts, state panels and examples are mostly in Simplified Chinese; the methodology docs are in English. Works best with Product Framer output (Capability files with ~S/~F and Persona files) in product-management/. It describes as-is journeys only; to-be behaviour is expressed as Features. It does not write user stories or acceptance criteria (use User Story for that). Diagrams are Mermaid and need a Mermaid-capable renderer.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 3 days ago
Requires
Nothing to install.
Permissions
File Scopes
No network access. Never modifies upstream product-framer files.