The Agent Skills Directory

[SAFE]: The skill content is educational and focuses on best practices for semantic search and retrieval evaluation. No malicious instructions, obfuscation, or safety bypasses were identified.\n- [COMMAND_EXECUTION]: The skill includes a shell script scripts/verify.sh intended for use as a heuristic linter. Analysis of the script confirms it uses standard Unix tools like find and grep to perform pattern matching on local project files. It does not perform network operations, access sensitive system paths, or execute external code.\n- [EXTERNAL_DOWNLOADS]: The skill documentation references industry-standard embedding models (e.g., OpenAI, Cohere, Voyage, Gemini) and common Python libraries (tiktoken, langchain-text-splitters, numpy). These references are strictly for documentation and architectural guidance within the skill's domain.

embeddings-search