Quick Flow

Quick Flow is an AI Engineering skill for Claude Code, published by a5c-ai in babysitter.

1.7K stars98 forkson a5c-ai/babysitterAdded 2026/07/20+1% in starsRepository updated 2026/08/11

agent-orchestrationagent-skillsagentic-aiagentic-workflowai-agentsai-automationbabysitterclaude-codeclaude-code-skillsclaude-code-workflowsclaude-skillsclaude-workflowscodex-plugincodex-skillscodex-workflowhermes-pluginpi-extensiontrustworthy-aivibe-coding

Install in seconds

Install Quick Flow

Copy Quick Flow into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.

terminal

npx degit https://github.com/a5c-ai/babysitter/tree/main/library/methodologies/bmad-method/skills/quick-flow ~/.claude/skills/quick-flow

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/a5c-ai/babysitter.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file: library/methodologies/bmad-method/skills/quick-flow/SKILL.md in a5c-ai/babysitter
Installs to: ~/.claude/skills/quick-flow
Collection: One of 36 skills cataloged from this repository
Category: AI Engineering — 3670 skills

What Quick Flow does

Move a small project from a quick technical specification through story-by-story implementation, tests, and scored code review with BMAD Quick Flow.

Quick Flow is cataloged under AI Engineering on DirSkills. Quick Flow comes from a repository tagged agent-orchestration, agent-skills, agentic-ai, agentic-workflow and ai-agents.

Reviewed 2026-08-04

DirSkills review

This is the BMAD Quick Flow workflow for Barry, the Solo Dev agent, rather than a generic Babysitter page. It links a quick specification to per-story implementation and a final multi-dimensional review.

Inputs include project name and requirements, with an optional technology stack and a story count that defaults to five.
Outputs cover architecture decisions, implementation results for each story, a 0-100 review score, and a stakeholder summary; project-specific acceptance tests still define whether the work is done.

Documentation

README

From the original repository

Quick Spec: Create technical specification with stories
Quick Dev: Implement each story with tests
Code Review: Multi-dimensional quality assessment

Inputs

projectName - Project name
projectDescription - Project requirements
techStack - Preferred technology stack (optional)
storyCount - Number of stories (default: 5)

Outputs

Technical specification with architecture decisions
Implementation results per story
Multi-dimensional code review with 0-100 score
Summary for stakeholder communication

Process Files

bmad-quick-flow.js - Complete Quick Flow lifecycle

Frequently asked about Quick Flow

What else does a5c-ai publish alongside Quick Flow?
Quick Flow is one of 36 skills that DirSkills catalogs from a5c-ai/babysitter, the repository it ships in. Its siblings there include Agent Dispatch, Architecture Design and Architecture Patterns. Each one is a separate skill with its own page in this directory, installs the same way Quick Flow does, and is maintained by a5c-ai in that same repository. The rest of the collection is listed on the a5c-ai/babysitter page.
How does Quick Flow compare to other AI Engineering skills?
Quick Flow ranks #946 by stars among the 3670 AI Engineering skills in this catalog. The most-starred ones next to it are Architecture Decision Records, AI-First Engineering and Agentic OS. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Quick Flow against them. Open each page to compare what they document and how they install.