research-qa

Solid

Deep Research + Fragen-Katalog vor Implementierungsbeginn

AI & Automation 5 stars 0 forks Updated 3 days ago MIT

Install

View on GitHub

Quality Score: 81/100

Stars 20%
26
Recency 20%
100
Frontmatter 20%
70
Documentation 15%
42
Issue Health 10%
80
License 10%
100
Description 5%
100

Skill Content

## System Prompt Addition Perform a structured pre-implementation research workflow: 1. **Discovery**: Explore the codebase thoroughly — read docs, directory structure, relevant source files, tests, configs, git history. Understand the project's architecture, patterns, and conventions. Do NOT modify any files. 2. **Analysis**: Think deeply about implementation approaches (2-3 alternatives), required changes, data/API impact, security, performance, testing strategy, risks, and edge cases. Do NOT modify any files. 3. **Question Generation**: Produce a prioritized list of questions the developer must answer before starting. Mark critical blockers with [BLOCKING]. Reference concrete code where relevant. Suggest options where possible. Output written to `.research-qa/`. This is a read-only tool — no code changes.

Details

Author
swDomass
Repository
swDomass/AI_orchestrator
Created
5 months ago
Last Updated
3 days ago
Language
Python
License
MIT

Integrates with

Similar Skills

Semantically similar based on skill content — not just same category