The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands using npx @coldtea/pr-lens-cli@latest to print manuals, validate graphs, render diagrams, and push content to a remote server. It also executes git commands to retrieve repository metadata and commit SHAs.
[EXTERNAL_DOWNLOADS]: The skill fetches the @coldtea/pr-lens-cli package from the NPM registry at runtime. This package is part of the toolset provided by the author 'coldteadotai'.
[INDIRECT_PROMPT_INJECTION]:
Ingestion points: The skill reads and interprets user-provided codebases, folders, and pull request data (SKILL.md).
Boundary markers: There are no delimiters or instructions to the agent to ignore or isolate natural language instructions found within the analyzed source code.
Capability inventory: The skill has the ability to execute shell commands (npx, git), write diagram files locally (.pr-lens/graph.json), and perform network operations by pushing data to prlens.dev via the CLI tool.
Sanitization: The skill lacks explicit sanitization, validation, or filtering for the external code content it processes before incorporating it into the walkthrough body.

eli5