tapd-product-discovery

Manages pre-PRD product discovery workflows with TAPD parent stories, prototypes, and role-based child tickets.

840|261|Updated Apr 18, 2019
One-click install
npx skills add https://github.com/TencentBlueKing/bk-bcs --skill tapd-product-discovery
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: tapd-product-discovery
Source: https://github.com/TencentBlueKing/bk-bcs/tree/main/.agents/skills/tapd-product-discovery
Command: npx skills add https://github.com/TencentBlueKing/bk-bcs --skill tapd-product-discovery

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

It handles the messy phase before a complete PRD exists, turning raw ideas, boss requests, user feedback, or competitor observations into structured TAPD parent stories, PRDs, prototypes, and role-split child tickets.

Core Features & Use Cases

  • Product Parent Story Management: Creates or reuses TAPD parent stories and drives them through backlog, doing, for approve, approved, and done states.
  • Research and PRD Authoring: Guides user research, competitor analysis, and business analysis, then consolidates findings into a PRD saved under docs/reqs/product/.
  • Prototype Generation: Produces page prototype Specs and BKUI-based static HTML prototypes for product, design, and frontend review before ticket splitting.
  • Role-Based Ticket Splitting: After product approval, creates design, frontend, and backend child stories only when actually needed, recording skip reasons in the parent story.
  • Use Case: Your boss suggests adding a risk trend view to cluster inspection. Use this Skill to create a TAPD parent story, run research, draft the PRD, generate a BKUI HTML prototype, and split design/frontend/backend child tickets after approval.

Quick Start

Ask the assistant to start the product discovery flow for a new idea, providing your TAPD workspace_id and a short description of the requirement source.

Frequently Asked Questions about tapd-product-discovery

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I start a TAPD requirement when I only have an idea and no PRD?

Start the product discovery flow by providing the idea source and your TAPD workspace_id. The Skill creates or locates a product parent story in backlog state, then guides research, PRD drafting, and prototype review before any engineering tickets exist.

How do I split a TAPD parent story into design, frontend, and backend child tickets?

After the parent story reaches approved state, the Skill evaluates whether each role is actually needed based on interaction, page, and API/data criteria. It creates only the necessary child stories under the parent and records skip reasons for the rest.

When should I use product discovery instead of the story pipeline skill?

Use product discovery when no complete PRD exists yet, such as raw ideas, research needs, or prototype review. If the PRD, design, and API docs are already confirmed, hand the work to tapd-story-pipeline for engineering implementation instead.

Can I skip the HTML prototype for backend-only changes?

Yes. Pure backend tasks, configuration changes, script jobs, and text-only edits can skip the prototype Spec and BKUI HTML prototype. The Skill records the skip reason in the TAPD parent story before continuing to product review.

What happens if the TAPD MCP service is unavailable?

The Skill stops all TAPD write operations and instead outputs the local product documents plus the manual ticket creation fields. No stories_create or stories_update calls are made without MCP availability and explicit user confirmation.

What status flow does a TAPD product parent story follow?

The parent story moves through backlog, doing, for approve, approved, and done. The done state only means product-side work is complete; release status continues to be tracked by the frontend and backend child stories.