The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests potentially untrusted data by reading and scanning Markdown files from the local project environment using Read, Glob, and Grep tools.
Ingestion points: Markdown files (.md) are read during the planning (Phase 1) and validation (Phase 3) stages.
Boundary markers: No explicit delimiters or instructions are provided to the agent to ignore or isolate instructions that might be embedded within the processed Markdown files.
Capability inventory: The skill utilizes shell command execution capabilities, specifically running the Scala build tool (sbt mdoc) and a provided bash validation script.
Sanitization: No sanitization or filtering logic is present to validate the content of the files before they are processed by the agent or the build tools.
[COMMAND_EXECUTION]: The skill requires the agent to execute shell commands to fulfill its primary purpose. This includes running sbt mdoc to compile Scala code blocks and executing the local validation script check-mdoc-conventions.sh via bash. These commands are executed using paths that include environment variables like ${CLAUDE_PLUGIN_ROOT}.

docs-mdoc-conventions