xby-generate-prd-prompt
Run the following command in DeepSeek Harness:
dsh plugin install xby-skill/xby-generate-prd-prompt
Paste the following prompt into your AI chat to install this plugin:
Run dsh plugin install xby-skill/xby-generate-prd-prompt in your DeepSeek Harness terminal to install the plugin; the source repository is available at https://github.com/xby-skill/xby-generate-prd-prompt .
About this plugin
Writing a solid product requirements document, running a thorough codebase review, or dissecting a nasty bug often takes longer than the thinking itself because you keep reshaping the prompt structure by hand. xby-generate-prd-prompt hands that job to a modular template engine: pick your technology stacks and analysis focus areas, and it assembles a fully structured prompt covering all 14 PRD sections, 12 codebase-analysis sections, or 8 bug-analysis sections automatically.
It supports free combination across 31 technology stacks and 10 analysis dimensions, composed from 34 swappable template parts. Whether the project is a full-stack front end or a backend microservice mesh, the generated prompt adjusts its emphasis to match. Bug analysis additionally accepts a severity-level parameter so the depth of investigation aligns with the criticality of the issue.
Built for engineers and teams that regularly ask an AI assistant to draft PRDs, review codebases, or break down faults. If you want consistent document structure, complete sections, and precise technical focus every time instead of hand-writing a long prompt from scratch, this plugin automates the assembly step out of the way.
Use Cases
- Auto-assemble a 14-section standard PRD prompt tuned to your tech stack
- Generate a 12-section deep codebase analysis prompt on demand
- Build a structured bug triage prompt keyed to a severity level
Best For
- Engineers who regularly ask an AI assistant to draft and refine PRDs
- Small-to-mid teams that expect consistent, fully-structured document output
- Architects who want prompt emphasis to shift precisely with the tech stack
Related Plugins
A unified suite combining hot runtime injection, task-aware thinking-mode routing, and a graded session protocol with red-team gates to sustain model diligence across long-horizon inference.
ModLens is a vision plugin for DeepSeek Harness that gives text-only models sight by reading images pasted directly into chat, with zero-config setup and multiple vision engines.
On-demand vision for text-only DeepSeek Harness agents: built-in free keyless vision chain and 14 vision tools, routing image turns as tool calls to vision models with pixel fidelity, no Python needed, one-command install.
Give text-only models in DeepSeek Harness eyes, enabling image Q&A, long-screenshot OCR, UI restoration, and GUI visual tasks.