The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes several shell-based tools to perform its migration tasks.
Git Operations: Employs git log, git show, git branch, and git tag for analyzing the history and versions of both the design system and the product repositories as described in phases/phase-1-assessment.md and phases/catch-up.md.
Package Management: Uses npm view, npm pack, and potentially npm install or npm link to check and manage design system versions in phases/phase-3-integration.md.
Build Tools: Executes the product's own build and testing commands in the 'Proof' phase (phases/phase-5-proof.md) to verify the migration.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data which could potentially contain instructions intended to influence the agent's logic during the translation and wiring phases.
Ingestion points: The skill reads story files, pattern files, and fixture data (JSON) from external design system repositories as specified in phases/phase-1-assessment.md.
Boundary markers: There are no explicit instructions or delimiters defined in the instructions to isolate the content being processed from the agent's operational logic during the translation phase.
Capability inventory: The skill possesses extensive capabilities including file system modification, shell command execution (git, npm, build scripts), and automated creation of pull requests.
Sanitization: While the skill performs structural translation (e.g., stripping data-p2s-* attributes in reference/TRANSLATION.md), it does not specifically sanitize input for natural language instructions that could trigger unintended actions.

storybook-to-product