The Agent Skills Directory

[NO_CODE]: The skill consists entirely of Markdown documentation, facilitation playbooks, and workshop templates. There are no executable scripts (Python, JavaScript, shell), binaries, or configuration files that trigger code execution.
[SAFE]: The skill does not perform any network operations, file system modifications (outside of the agent's standard output), or credential handling. All instructions are focused on guiding a human facilitator or providing structured analysis of workshop data.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and synthesize user-provided customer interview transcripts. While the instructions do not include specific safety delimiters for this untrusted data, the skill lacks any 'sink' capabilities (such as shell access or network tools) that would allow a prompt injection attack to cause harm. The risk is limited to content manipulation within the generated workshop artifacts.

jtbd-workshop