The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and follow instructions from external files which can be influenced by project content or environment variables.
Ingestion points: The skill reads content from .claude/brainstorm-rules.md and $CLAUDE_PLUGIN_DATA/brainstorm-rules.md using the resolve-rules.sh script.
Boundary markers: Absent. The skill instructions explicitly state that the agent should treat the loaded content as supplementary instructions that influence design and technical choices without providing delimiters or warnings to ignore embedded commands.
Capability inventory: The skill is configured with access to powerful tools including Bash, Write, Edit, Agent, and Skill (defined in SKILL.md frontmatter).
Sanitization: None. The external rules are loaded via script output and applied directly to the agent's behavior during the brainstorming process.
[COMMAND_EXECUTION]: The skill utilizes the Bash tool to execute resolve-rules.sh for loading rules and checks environment variables like $CLAUDE_PLUGIN_DATA to determine file paths for storage and retrieval.

brainstorm