The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to perform standard development tasks using local tools. Evidence includes calls to pnpm exec eslint, pnpm --filter website-weapp-vite build, and repository-specific scripts like pnpm skills:check:yaml or pnpm skills:score:json. These actions are confined to the local development environment and are appropriate for the skill's documented purpose.
[INDIRECT_PROMPT_INJECTION]: The skill functions by reading and processing local repository content, which creates a potential surface for indirect prompt injection. Ingestion points: The agent reads from packages/weapp-vite/src/types/config/**, packages/weapp-vite/docs/**/*.md, and skills/*/SKILL.md as documented in SKILL.md and references/docs-sync-checklist.md. Boundary markers: There are no explicit instructions for the agent to use delimiters or ignore embedded instructions within the ingested files. Capability inventory: The skill has the capability to write files to the repository and execute local build/validation scripts via pnpm and wv CLI. Sanitization: The skill does not specify any sanitization procedures for the data processed from the source files.

docs-and-website-sync