The Agent Skills Directory

[NO_CODE]: The skill consists entirely of Markdown reference files and documentation. It does not include any executable scripts, binaries, or active code components.
[COMMAND_EXECUTION]: Documents the usage of the Slidev CLI (slidev, slidev build, slidev export) to manage presentation lifecycles. These are standard operational instructions for the documented tool.
[EXTERNAL_DOWNLOADS]: References the installation of dependencies such as Playwright and Iconify collections from official package registries and well-known service repositories.
[DATA_EXFILTRATION]: Mentions the --tunnel feature which utilizes Cloudflare Quick Tunnels to expose a local presentation server for remote access. This is a documented feature of Slidev using a well-known service.
[INDIRECT_PROMPT_INJECTION]: The skill describes features for importing content from external Markdown files and code snippets, which represents a potential injection surface if the imported content originates from an untrusted source.
Ingestion points: External Markdown files via src frontmatter and code snippets via <<< syntax.
Boundary markers: None explicitly defined in the documented templates to separate imported content from agent instructions.
Capability inventory: Includes filesystem modification capabilities via the monaco-write feature and CLI command execution.
Sanitization: Relies on Slidev's internal Markdown and Vue rendering engines; no additional sanitization logic is provided in the skill instructions.

slidev