flow-qa

Files behavioral bug reports into the configured issue tracker through conversational QA intake.

Updated Jun 28, 2026
One-click install
npx skills add https://github.com/AO-HyS/aohys.com --skill flow-qa-ao-hys
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: flow-qa
Source: https://github.com/AO-HyS/aohys.com/tree/main/.agents/skills/flow-qa
Command: npx skills add https://github.com/AO-HyS/aohys.com --skill flow-qa-ao-hys

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Turning informal bug reports into well-structured, durable issues is tedious and often produces vague tickets that lack reproduction steps or expected behavior. This Skill runs a conversational QA intake that captures the essential behavioral details and files clean issues into the repository's configured tracker. ## Core Features & Use Cases - Conversational Intake: Asks at most three targeted questions to capture expected behavior, actual behavior, reproduction steps, and frequency. - Tracker-Aware Filing: Reads the repository's issue-tracker configuration and files issues through the native integration rather than assuming GitHub. - Dependency-Aware Splitting: Separates genuinely independent failure modes, files blockers first, and records blocking relationships. - Use Case: A user reports that the dashboard publish flow intermittently fails. The Skill asks clarifying questions, inspects the relevant code for domain language, and files a concise user-facing issue with numbered reproduction steps and a blocking relationship to a related defect. ## Quick Start Ask the assistant to run a QA intake and file an issue for the bug you just observed, describing what happened and what you expected.

Frequently Asked Questions about flow-qa

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

FAQPage Schema
How do I file a bug report from a conversation with an AI assistant?▼

Describe what happened and what you expected, and the Skill runs a QA intake that asks up to three clarifying questions about reproduction and frequency. It then files a concise issue with numbered reproduction steps into the repository's configured tracker.

What information should a good bug report include?▼

A good bug report states what happened, what was expected, numbered reproduction steps, relevant inputs or state, and frequency. The Skill captures exactly these fields and avoids implementation paths or line numbers that become stale.

Does this Skill only work with GitHub Issues?▼

No. It reads the repository's issue-tracker documentation and uses the configured tracker and its native integration, explicitly avoiding the assumption of GitHub. If no tracker is configured, it loads a setup Skill first.

Can the Skill split one bug report into multiple issues?▼

Yes, but only for genuinely independent failure modes. It preserves honest dependencies, files blocker issues first, and records the blocking relationship so downstream work is correctly ordered.

Will the Skill diagnose or fix the bug during intake?▼

No. Intake is limited to capturing behavior and filing the issue. It may inspect code read-only for domain language, but diagnosis and fixes only happen when separately requested.