Skip to content
Get packs

Review Storybook

Review Paperclip UI stories and report render, interaction, and visual evidence separately

Source Download skill
Repository
paperclipai/paperclip
Stars
110,078
Licence
MIT
Files
2 files

What it does

When installed, this skill tells an AI agent how to check a Paperclip user-interface change by using its Storybook catalog, the production source code, and existing browser tests. The agent picks meaningful states (normal use, errors, permission gates, mobile and theme variants), runs the stories, and reports what was actually observed for each case, keeping rendering, interaction, visual comparison, and production acceptance results separate.

Great for

  • Developers reviewing a UI change in the Paperclip repository who want a structured Storybook-based check
  • Maintainers who need clear records of which story IDs, environments, and mocked boundaries were used in a review

Skip it if

  • People outside the Paperclip repository, since it depends on its specific maps, doc paths and test suites (the skill would not help with other projects)
  • Final sign-off on backend persistence, real authorization or live provider behaviour, which the skill says must go to a separate production verification skill

Try asking

  • “Review the Storybook stories for the new approvals panel change and report results per story”
  • “Check whether the navigation and sidebar changes keep existing Storybook links working after the rebuild”
  • “Run the visual regression check for the mobile layout of the issue board and report any blocked comparisons”
Step-by-step guide: how to use Review StorybookInstall, first run, examples, tips and FAQs

Install in 3 steps

  1. 1

    Download the skill

    The ZIP contains the 2 original files, the MIT licence and an attribution note.

    review-storybook.zip
  2. 2

    Add it to your agent

    Claude Code (all projects)

    mkdir -p ~/.claude/skills && unzip review-storybook.zip -d ~/.claude/skills/

    Claude Code / Agent SDK (this project only)

    mkdir -p .claude/skills && unzip review-storybook.zip -d .claude/skills/

    Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.

  3. 3

    Ask for the task

    No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.

Get better results

  • Point the agent at a specific feature or change so it selects discriminating story IDs instead of sampling broadly
  • Ask for the report format the skill defines (revision, story ID, environment, observed result) so evidence can be checked later
  • Make sure the visual baseline manifest is published before asking for a visual regression verdict; otherwise the comparison will be blocked

What's inside

  • agents/openai.yaml
  • SKILL.md

Redistributed unmodified from paperclipai/paperclip under the MIT licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.