The Agent Skills Directory

[SAFE]: The skill consists entirely of markdown files containing prompt engineering templates and instructions. No executable code, remote script downloads, or unauthorized data access patterns were found.
[PROMPT_INJECTION]: The skill's primary function is to process and optimize user-provided prompts, which constitutes an indirect prompt injection surface. However, the templates provided are for legitimate improvements in agent performance and do not attempt to bypass safety filters.
Ingestion points: User prompts submitted for optimization via the workflow described in SKILL.md.
Boundary markers: The templates do not utilize specific delimiters or 'ignore' instructions for the user input.
Capability inventory: The snippets in references/agentic.md and references/patterns.md include instructions for the agent to use tools (file reading/writing, pwd), manage state, and orchestrate subagents.
Sanitization: No sanitization or validation of the input prompt is performed by the provided snippets.

prompt-optimizer