- Home
- Skills
- Business & Operations
- Product Framer
Product Framer
Frame a product's Vision, Personas and Capabilities through Design Thinking elicitation — a senior-BA-style conversation that outputs structured, agent-readable artifacts.
$5
Works with the AI Agents you already use
Product Framer
Example session with this skill installed
I want to plan a fleet-management product. Our fleet managers switch between three systems to monitor vehicles and react too slowly to incidents.
- Read your context and instructions
- Compiled the product framer
After a one-question-per-turn elicitation with state panels and calibration checkpoints, the agent writes product-management/vision.md (problems, values, differentiation, success metrics, non-goals, constraints, assumptions), personas/P1-fleet-manager.md and P2-safety-auditor.md, capabilities.yaml, and capabilities/C1-vehicle-monitoring.md, C2-incident-handling.md, C3-safety-analytics.md — each with scope, priority, dependencies, conceptual scenes (~S) and feature candidates (~F).
Connects securely to your tools. The creator never sees your data.
About this skill
Frame a product's Vision, Personas, and Capabilities through a Design Thinking-driven conversation that works like talking to a senior business analyst, not filling out a form.
How it works
- Elicitation, not extraction: opens with the business story and listens for roles, problems, current state and desired state. It asks one question per turn and shows a state panel before each one.
- Explicit sufficiency gate: a Dimension Coverage Gate (Who / Problem / As-Is / To-Be) decides when enough is known to move on.
- Answer-drift handling: four drift types (off-topic, solution-instead-of-problem, information dump, evasion) are handled explicitly. Tangents go to a Parking Lot so nothing the user says is lost.
- Calibration: checks its understanding with the user after every 2-3 key inputs.
- Lean Value Tree personas: goals are written as business outcomes, not feature descriptions. Includes review roles (security, compliance, reliability) so agents don't optimize only for functional correctness.
- Collaborative decomposition: the user picks the decomposition dimension. Capabilities are MECE and user-perceptible, each with conceptual Scenes (~S) and Feature Candidates (~F).
- Reverse mode: feed it an existing feature list, backlog or PRD and it derives the Vision and Capabilities bottom-up. It also resumes from existing outputs.
Output (written to product-management/):
vision.md: problems, values, differentiation, success metrics, non-goals, constraints, assumptionspersonas/P{n}-{name}.mdcapabilities.yaml: a lightweight indexcapabilities/C{n}-{name}.md
This is the entry point of a pipeline: product-framer → journey-designer → user-story → event-storming. Every artifact is structured so downstream skills and coding agents can consume it directly.
Stops at Vision → Personas → Capabilities; journeys, formal features and user stories are handled by the companion skills (journey-designer, user-story). Example phrasings, state panels and templates are largely in Simplified Chinese.
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 any payment.
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
Permissions
File Scopes
Reads any materials the user shares (feature lists, PRDs) and writes Vision/Persona/Capability markdown files.