The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes shell commands to establish symlinks and verify the integrity of the generated documentation. * Evidence: The agent is instructed to use ln -sf AGENTS.md CLAUDE.md for symlinking and cat CLAUDE.md for verification in SKILL.md. * Evidence: The verification pass requires the agent to execute existing project scripts (e.g., from package.json) to confirm they function as documented. * Evidence: Portable skill templates included in the references (skill-code-review.md) utilize standard commands such as git diff, git show, and gh pr for context gathering.
[PROMPT_INJECTION]: The skill processes untrusted repository files to generate its documentation, creating an indirect prompt injection surface. * Ingestion points: Local files including package.json, lockfiles, CI configuration files (.github/workflows/), and existing documentation (README.md). * Boundary markers: Absent; the skill lacks specific delimiters or instructions for the agent to ignore embedded commands within the ingested project files. * Capability inventory: The agent has the capacity to write files to the local file system, create symlinks, and execute project-defined shell scripts. * Sanitization: There is no requirement for the agent to sanitize or escape data gathered from repository files before using it in documentation generation or command execution.

bootstrap-agents-md