The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill recommends installing and using reputable development tools such as @biomejs/biome and oxlint from official package registries.\n- [COMMAND_EXECUTION]: The instructions guide the agent to perform standard development tasks using shell commands, including npm test, npx oxlint ., npx @biomejs/biome check, and git commit.\n- [PROMPT_INJECTION]: The skill documentation creates a surface for indirect prompt injection by instructing the agent to ingest untrusted data (source code) and then execute powerful commands.\n
Ingestion points: The agent is instructed to read and explore codebase files in references/02-planning-workflow.md.\n
Boundary markers: No instructions are provided to use delimiters or to ignore potential instructions found within the code being analyzed.\n
Capability inventory: The agent is granted capabilities to execute subprocess commands for testing, linting, and version control as described in references/20-cheatsheet.md.\n
Sanitization: No sanitization or validation of the ingested code content is specified before processing.

typescript-refactoring