The Agent Skills Directory

[SAFE]: The skill provides structured templates and documentation for experiment planning, hypothesis writing, and ICE prioritization. No malicious patterns or bypass attempts were detected.
[COMMAND_EXECUTION]: The skill utilizes a local Python script (scripts/sample_size_calculator.py) to perform statistical calculations. The script uses only standard Python libraries (math, statistics, argparse) and does not access the network or sensitive files.
[INDIRECT_PROMPT_INJECTION]: The skill defines a workflow that processes user-provided content (e.g., experiment interventions and metrics). This represents a standard prompt interpolation surface, but the skill lacks high-risk capabilities (like network access or file writing) that would make this surface exploitable.

experiment-designer