The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes several repository-local command-line operations and scripts via bun run, including verify-doc-budgets, change-scope, doc-sync, and verify-translation-pairing. It also employs standard shell utilities like git, grep, xargs, and wc to perform audits and link checks within the repository environment.
[INDIRECT_PROMPT_INJECTION]: The skill identifies a surface for indirect prompt injection by design, as its primary purpose is to ingest and audit untrusted documentation content.
Ingestion points: The skill processes all Markdown files (*.md), JSDoc, and TypeScript code comments within the repository scope (excluding archived notes).
Boundary markers: There are no explicit instructions to use delimiters or ignore embedded instructions when reading these external files.
Capability inventory: The skill has the ability to execute shell commands and repository scripts, and can modify files during the synchronization and PR hygiene phases.
Sanitization: While the skill includes instructions to remove "reasoning-transcript leakage" and "doc slop," these measures are intended for editorial quality rather than security sanitization against adversarial inputs.

dsh-doc-standards