The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to utilize various command-line tools for architectural analysis, including grep, dependency-cruiser, import-linter, jdeps, and go list. It also recommends executing database-specific commands such as EXPLAIN (ANALYZE, BUFFERS) and SELECT ... FOR UPDATE to audit performance and concurrency, as detailed in the references/methods.md file.
[EXTERNAL_DOWNLOADS]: The SKILL.md file directs the agent to suggest installing additional components using the command npx skills add wondelai/skills/<slug> --global. This command fetches and executes code from the NPM registry associated with the skill's author.
[INDIRECT_PROMPT_INJECTION]: The skill maintains state and manages its multi-phase journey by reading project documentation files, which could serve as an attack surface for instructions embedded in data.
Ingestion points: The agent reads the docs/ARCHITECTURE-OPTIMIZATION-PLAN.md file and other artifacts in the docs/ directory to resume its journey across sessions.
Boundary markers: Absent; the skill does not employ specific delimiters or integrity checks to verify that the state documentation files remain untampered with between sessions.
Capability inventory: The skill possesses capabilities to read and write local files and to execute various shell-based analysis tools across its eight phases.
Sanitization: Absent; the instructions do not include any logic for validating or sanitizing the contents of the documentation files prior to their ingestion into the agent's context.

architecture-optimization