The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill directs the agent to read various files within the repository to guide its development tasks, which introduces a potential surface for indirect instructions to influence agent behavior.
Ingestion points: The agent is instructed to read crates/biome_analyze/CONTRIBUTING.md, existing rule implementations in crates/biome_*_analyze/src/lint/, and test fixtures.
Boundary markers: No specific boundary markers or instructions to ignore embedded commands are present in the skill.
Capability inventory: The skill leverages the just task runner for code generation and testing, and accesses various project-specific metadata.
Sanitization: Content from the repository is ingested and used for context without explicit sanitization or validation logic.
[COMMAND_EXECUTION]: The skill uses a local task runner to automate development processes.
Evidence: It invokes several just commands such as just new-js-lintrule, just test-lintrule, just gen-rules, and just gen-configuration to scaffold code and run tests within the Biome development environment.

lint-rule-development