Human-First Visual Digest

Human-First Visual Digest is a Writing 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 Human-First Visual Digest

Copy Human-First Visual Digest 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/.flow/specs ~/.claude/skills/specs

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: .flow/specs/fn-189-human-first-visual-digest-skill.md in gmickel/flow-next
Installs to: ~/.claude/skills/specs
Collection: One of 25 skills cataloged from this repository
Category: Writing — 1012 skills

What Human-First Visual Digest does

Human-First Visual Digest restates specs, tasks, diffs, or conversation topics as compact markdown visuals. Use it when a review needs a quick structural view instead of long prose.

Human-First Visual Digest is cataloged under Writing on DirSkills. Human-First Visual Digest comes from a repository tagged agentic-workflow, ai-agent, ai-workflow, anthropic and autonomous-agent.

Documentation

README

Excerpt

Human-first visual digest skill + structural sketches in make-pr

Goal & Context

flow-next has two visual registers and nothing between them. At one extreme: raw spec/task markdown - after /flow-next:plan a reviewer faces the spec plus N task files (500+ lines for a 7-task spec) and must reconstruct the structure in their head by serial reading. At the other: the opt-in HTML render lenses (artifacts.html.enabled) - full instrument-panel documents with mastheads, dials, and DAG hover wires, heavyweight to generate and consume. The middle register is missing: a fast, compact, markdown-only visual restatement that renders natively in the terminal, in chat, and on every forge, with zero machinery.

This spec adds that register in two moves:

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

Frequently asked about Human-First Visual Digest

What else does gmickel publish alongside Human-First Visual Digest?
Human-First Visual Digest 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 Human-First Visual Digest 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 Human-First Visual Digest compare to other Writing skills?
Human-First Visual Digest ranks #606 by stars among the 1012 Writing skills in this catalog. The most-starred ones next to it are Article Writing, Social Media Content Calendar and Knowledge Comic Creator. 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 Human-First Visual Digest against them. Open each page to compare what they document and how they install.