The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill's primary function is to ingest and analyze source code from user-provided directories, which could contain hidden malicious instructions.\n
Ingestion points: The MigrationAnalyzer class in resources/implementation-playbook.md recursively reads all files from a provided directory path using Path.rglob('*').\n
Boundary markers: There are no specific delimiters or instructions to the AI to ignore embedded prompts within the analyzed source files.\n
Capability inventory: The skill is capable of generating executable code, migration plans, and performing network requests (e.g., via generated fetch calls in RESTToGraphQLMigrator).\n
Sanitization: The skill does not perform sanitization or filtering of content read from source files before processing it.\n- [COMMAND_EXECUTION]: The skill provides templates for generating Python-based command-line interface (CLI) tools and automated migration scripts meant to be executed on the user's system.\n- [EXTERNAL_DOWNLOADS]: The MigrationMonitor class in resources/implementation-playbook.md generates a dashboard that includes a script tag pointing to https://cdn.jsdelivr.net/npm/chart.js, which is a well-known and standard service for data visualization.

framework-migration-code-migrate