Flow Interview

Flow Interview is an AI Engineering skill for Claude Code, published by gmickel in flow-next.

685 stars54 forkson gmickel/flow-nextAdded 2026/08/23Repository updated 2026/08/22

agentic-workflowai-agentai-workflowanthropicautonomous-agentclaude-codeclaude-code-pluginclicode-reviewcodexexecutionfactory-droidmarketplaceopenai-codexplanningpluginralph-modesdlcspec-driven-developmentworkflow

Install in seconds

Install Flow Interview

Copy Flow Interview 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/gmickel/flow-next/tree/main/plugins/flow-next/skills/flow-next-interview ~/.claude/skills/flow-next-interview

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/gmickel/flow-next.git

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

In this catalog

Source file: plugins/flow-next/skills/flow-next-interview/SKILL.md in gmickel/flow-next
Installs to: ~/.claude/skills/flow-next-interview
Collection: One of 25 skills cataloged from this repository
Category: AI Engineering — 2451 skills

What Flow Interview does

Flow Interview conducts a thorough interview about a task, spec, or spec file to capture unresolved implementation details. Use it before building when requirements need refinement or clarification.

Flow Interview is cataloged under AI Engineering on DirSkills. Flow Interview comes from a repository tagged agentic-workflow, ai-agent, ai-workflow, anthropic and autonomous-agent.

Documentation

README

Excerpt

Flow interview

Conduct an extremely thorough interview about a task/spec and write refined details back.

.flow/ is the only task tracker. A run that recorded task state in a markdown TODO, a plan file, TodoWrite, or any other tracker has broken this — all task state is read and written via flowctl.

Chart boundary (fn-135)

Existing-spec clarification stays primary. Interview refines a valid spec with unresolved judgment questions. Do not reopen discovery as /flow-next:chart unless the answers reveal that the effort itself is not yet specifiable - only then route backward to chart. Clear work that never needed a chart stays out of chart. Unsure of the hop: /flow-next:guide.

Preamble

This is the opening of the README. Read the full README on GitHub.

Frequently asked about Flow Interview

What else does gmickel publish alongside Flow Interview?
Flow Interview is one of 25 skills that DirSkills catalogs from gmickel/flow-next, the repository it ships in. Its siblings there include Codebase Feature Map, Export Context and Flow Interview. Each one is a separate skill with its own page in this directory, installs the same way Flow Interview does, and is maintained by gmickel in that same repository. The rest of the collection is listed on the gmickel/flow-next page.
How does Flow Interview compare to other AI Engineering skills?
Flow Interview ranks #1751 by stars among the 2451 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 Flow Interview against them. Open each page to compare what they document and how they install.