bayes-platform: Skill for Claude Code

.claude/skills/storybook-screenshot/SKILL.md

storybook-screenshot is a skill for Claude Code from bayesimpact/bayes-platform. It costs 68 tokens per session (1,964 once invoked), scanned A, original, MIT.

A workflow for taking screenshots of Storybook web components and routes using seeded data and mocked services. Storybook is a tool for viewing UI components in isolation, and headless Chromium is a browser that runs without a visible window.

In plain words
What is it for?
Use it to check web screens in different languages and phone-sized layouts, or investigate blank pages, missing data, clipping, overflow, and browser errors.
Why use it?
It lets you inspect UI changes without starting the real API, database, or login system. It also reports console problems, failed requests, uncaught errors, and content that is wider than the viewport.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: reads .claude/ paths.

This is bayesimpact/bayes-platform's own configuration. It tells Claude Code how to work on bayes-platform itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything bayes-platform configures →

Reuse

Borrowing it

Nothing to install: this file belongs to bayesimpact/bayes-platform. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/bayesimpact/bayes-platform/main/.claude/skills/storybook-screenshot/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/bayesimpact/bayes-platform

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for storybook-screenshot

README.md
[![agentmods](https://agentmods.dev/badge/skills/bayesimpact/bayes-platform/storybook-screenshot/github.svg)](https://agentmods.dev/skills/bayesimpact/bayes-platform/storybook-screenshot)
Your own site
<a href="https://agentmods.dev/skills/bayesimpact/bayes-platform/storybook-screenshot"><img src="https://agentmods.dev/badge/skills/bayesimpact/bayes-platform/storybook-screenshot/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for storybook-screenshot

Your own site · 80×15
<a href="https://agentmods.dev/skills/bayesimpact/bayes-platform/storybook-screenshot"><img src="https://agentmods.dev/badge/skills/bayesimpact/bayes-platform/storybook-screenshot.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 68 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,964 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00068 $0.01964
Opus 5.5 $0.00027 $0.00786
Sonnet 5.5 $0.00014 $0.00393
Haiku 4.5 $0.00007 $0.00196

Measured 6d ago against content hash e0d6b8fd6157, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

storybook-screenshot scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/custom-check.example.mjs, scripts/screenshot.mjs), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

until curl -sf http://localhost:PORT/index.json >/dev/null; do sleep 3; done
.claude/skills/storybook-screenshot/SKILL.md · 102 lines

How it starts

The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Storybook screenshot

Overview

Storybook renders every route and component of apps/web with seeded state and mocked services, and the whole Desk (apps/desk) on its MSW handlers, without the API, a database or a login. The script opens one story in headless Chromium, saves a PNG to read with the Read tool, and lists console errors and warnings, uncaught exceptions, failed requests and content wider than the viewport.

Steps

Run every command from the repository root. Pick a port and use it everywhere below as PORT: in the main checkout 6006 for apps/web, 6007 for apps/web-embed, 6008 for packages/ui, 6009 for apps/desk; in a worktree another one (for example 6016), since those may belong to another checkout's Storybook. In a fresh worktree, run npm ci first.

In a worktree with an environment (infra/worktree/.env exists), never start a Storybook on the host: the environment serves them. Skip steps 1 and 6, start the one you need with bayes wt up --with storybook-web (or storybook-ui, storybook-embed, storybook-desk), and pass its URL, which bayes wt up prints, as --base-url instead of --port: https://<name>-storybook.<domain> for apps/web, https://<name>-desk-storybook.<domain> for the Desk. Use the same URL in place of http://localhost:PORT in step 2.

  1. Start Storybook as a background command (Bash run_in_background: true):

    npm --prefix apps/web run storybook -- -p PORT --ci --no-open
    

    For shared components, use --prefix packages/ui; for the embed widget, --prefix apps/web-embed; for the Desk, --prefix apps/desk.

  2. Wait until it serves stories, as a background command (a foreground sleep may be blocked), then find the story id with a word of the screen you want:

    until curl -sf http://localhost:PORT/index.json >/dev/null; do sleep 3; done
    curl -s http://localhost:PORT/index.json | grep -o '"id":"[^"]*SEARCH_WORD[^"]*"'
    

    The Desk's stories are in apps/desk/src/stories/, one per state of its mocked world, in three folders: Desk/General (Desk.stories.tsx), Desk/Conversation and Desk/Extraction (desk-general--terms-to-accept, desk-conversation--conversation, desk-extraction--csv-run...): each opens the whole Desk at a page. An id is the story title in kebab case, --, then the export name: title: "routes/studio/project/membership" with export const Default gives routes-studio-project-membership--default. Open the story file (apps/web/src/stories/...) to see its exports and argTypes: the states you can reach come from both, for example a WithData export or a withMemberAgents toggle. Storybook silently ignores an arg the component does not use, so pass names you saw in the story's argTypes or args, or props of its component.

Read the full file on GitHub · 102 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 6d ago Changed · +2 lines · +2 tokens per session e0d6b8fd6157
  2. 29d ago First seen · 100 lines · 66 tokens per session scan A d0be99d57c40

Subscribe to this mod's changes

storybook-screenshot is a skill published in the GitHub repository bayesimpact/bayes-platform (23 stars, last pushed yesterday), licensed MIT. It adds 68 tokens to every session and 1,964 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-08.

Related

storybook-screenshot compared with skills from other repositories

storybook-screenshot next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
storybook-screenshotbayesimpact/bayes-platformSkill23yesterdayMITA68Claude Code
verify-omnigentomnigent-ai/omnigentSkill11kyesterdayApache-2.0A100Claude Code, Codex
test-masterJeffallan/claude-skillsSkill12k7d agoMITA104Claude Code
eval-dataset-designbojieli/ai-agent-bookSkill57k29d agoApache-2.0A138Claude Code, Codex
dogfoodcallstack/agent-deviceSkill5.3kyesterdayMITA55Claude Code
cua-driverdavidondrej/skillsSkill4.3k3d agoMITA68Claude Code, Codex
test-warp-uiwarpdotdev/warpSkill66kyesterdayAGPL-3.0A55Claude Code