The Agent Skills Directory

[SAFE]: The skill consists exclusively of Markdown documentation and a JSON evaluation file. There are no executable scripts (Python, Node.js, Shell), binaries, or automation files that could perform actions on a host system.- [PROMPT_INJECTION]: The instructions are strictly limited to workshop design methodology. There are no patterns found that attempt to bypass safety guardrails or override the agent's core instructions.- [DATA_EXFILTRATION]: The skill does not access sensitive file paths, environment variables, or credentials. It contains no network-enabled tools or instructions to send data to external servers.- [OBFUSCATION]: All content is provided in clear, human-readable text. No Base64, zero-width characters, or other encoding techniques were used to hide malicious intent or URLs.- [REMOTE_CODE_EXECUTION]: There are no package installation commands or remote script fetch-and-execute patterns. All external references are to other skills within the same author's (samber) organizational scope, used for logical boundary definition.- [DYNAMIC_CONTEXT_INJECTION]: No use of the exclamation-backtick syntax for shell command execution was found in the SKILL.md or reference files.

workshop-program-design