The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted project data and has shell execution capabilities, which creates a potential surface for indirect prompt injection attacks.
Ingestion points: The skill reads project configuration files like package.json and component story files (*.stories.tsx) to identify versions and implementation styles.
Boundary markers: There are no specific delimiters or instructions for the agent to treat content within these files as untrusted data or to ignore instructions embedded within them.
Capability inventory: The skill is designed to execute shell commands including bunx storybook build, bunx storybook doctor, and vitest.
Sanitization: The skill does not describe any sanitization or validation of the content processed from project files.
[COMMAND_EXECUTION]: The skill instructs the agent to execute various shell commands to manage the Storybook project lifecycle, which is standard for development tools but involves running commands in the user environment.
Evidence: Instructions include running bunx storybook build, bunx storybook doctor, and vitest --project=storybook.
[EXTERNAL_DOWNLOADS]: The skill uses package managers and official CLI tools to download dependencies and environment binaries.
Evidence: It utilizes bunx to fetch Storybook updates and addons from the official npm registry and bunx playwright install to download browser binaries for testing.

storybook