The Agent Skills Directory

[COMMAND_EXECUTION]: The skill includes instructions for the agent to suggest a command to the user (npx skills add wondelai/skills/<slug> --global) if a required sub-skill is missing. This command targets the vendor's own resource repository and requires manual user execution.
[DATA_EXPOSURE]: The skill is designed to manage project state by reading from and writing to a local docs/ folder. Files such as MARKETING.md and DESIGN.md are used to persist decisions across sessions. The access is scoped to the project environment and is necessary for the skill's primary purpose.
[PROMPT_INJECTION]: The skill processes data from project files to inform its logic, creating a surface for indirect prompt injection.
Ingestion points: The agent reads docs/CREATE-WEBSITE-PLAN.md and other artifacts listed in the Journey Map at the start of every session to resume progress.
Boundary markers: No explicit delimiters or instructions to ignore embedded commands within the documentation files are provided.
Capability inventory: The skill can invoke other skills by slug and recommends npx installation commands to the user.
Sanitization: There is no evidence of sanitization for the content read from the docs/ folder.

create-website