- Home
- Skills
- Product Management
- User Story
User Story
Write INVEST-compliant user stories with Given/When/Then acceptance criteria through collaborative dialogue, traced back to Feature → Journey pain points, with optional mockup calibration to catch missing UI states.
$5
Works with the AI Agents you already use
User Story
Example session with this skill installed
Write user stories for F2 Smart Vehicle Filter.
- Read your context and instructions
- Compiled the user story
The skill reads F2, the J1 pain points and persona P1. It asks 2-3 clarifying questions (filter combinations, empty results, scale). It then produces stories such as "US-1: Filter vehicles by status", where Source is F2 → J1 Phase 2 Pain Point #5 and the persona is the Fleet Manager. Each story comes with happy-path and empty-result scenarios, an INVEST table, size S and a P0 suggestion (Fatal pain point). After an optional mockup pass adds Loading and Overflow scenarios, it saves US1–US4 files and vehicle-filter.yaml.
Connects securely to your tools. The creator never sees your data.
About this skill
User Story
The task layer of the Harness Skills product-management pipeline: Feature + Journey → User Stories.
User Story writes well-structured, INVEST-compliant stories through collaborative dialogue. It never dumps output on thin context. A hard gate requires at least 2-3 clarifying questions before any story is generated.
What it does
- Two modes: Create (new stories for a feature or epic) and Refine (evaluate, rewrite and split existing stories).
- Upstream context absorption: reads
product-management/(personas, journeys, features, vision) and your codebase so you don't repeat yourself.- Vision Non-Goals become boundary checks.
- Constraints are injected into the acceptance criteria.
- The full package for every story:
- As a / I want / So that
- Given/When/Then acceptance criteria covering the happy path and edge/error paths
- An INVEST check table
- A T-shirt sizing hint
- A priority suggestion drawn from upstream pain-point severity
- Source traceability:
F-ID → J-ID Phase N Pain Point #M, so a coding agent knows why each ticket matters. - Non-human actors (services, devices, scheduled jobs) and review-role stories (security, compliance, reliability).
- Six splitting strategies: by workflow step, business rule, user role, data variation, happy/unhappy path and CRUD.
- Mockup calibration (optional, UI stories only): a low-fi layout walkthrough with a 6-State Checklist (Loading / Empty / Error / Overflow / Partial / Permission) that surfaces missing acceptance criteria.
Output
product-management/
user-stories/US{n}-{name}.md
user-stories/{feature-name}.yaml # lightweight index
mockups/{feature-name}-layout.md # optional
There is one story per file, so each one works as a ready-to-use ticket for a human team or an AI coding agent.
Works standalone
You don't need the rest of the pipeline. Without upstream files, the skill gathers context through its own questions and leaves out the Source field. It never fabricates traceability.
Package
SKILL.md, README.md (methodology: 3 C's, INVEST, Harness Engineering), 2 references (output format, mockup calibration) and a story template.
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.
The core instructions are in English, but some prompts and the mockup checklist are in Simplified Chinese. It does not estimate in story points or push stories to Jira or Linear; output is local markdown and YAML. Path A of mockup calibration needs the Superpowers brainstorming Visual Companion; otherwise it falls back to text. It is not a UI design tool.
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
- Software
Git
Permissions
File Scopes
No network access. Never modifies upstream artifacts.