The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill implements a workflow that requires the agent to ingest and process data from the existing codebase and external documentation queries, which are potentially untrusted sources. 1. Ingestion points: The agent workflow in SKILL.md mandates the use of fuse-ai-pilot:explore-codebase and mcp__context7__query-docs to analyze the environment and research documentation. 2. Boundary markers: There are no explicit boundary markers or instructions provided to isolate or sanitize instructions that might be embedded within the codebase or documentation results. 3. Capability inventory: The skill provides instructions for the agent to execute shell commands such as php artisan test and ./vendor/bin/pest, and implies codebase modification as part of TDD implementation. 4. Sanitization: No sanitization or validation mechanisms are described for data retrieved from external tools or codebase exploration.
[COMMAND_EXECUTION]: The skill provides specific command-line instructions for running the test suite and checking coverage. Evidence: SKILL.md and troubleshooting.md explicitly list commands like php artisan test, ./vendor/bin/pest --parallel, and ./vendor/bin/pest --coverage for execution by the user or agent.

laravel-testing