The Agent Skills Directory

[SAFE]: The skill is entirely instructional, offering guidance on how to structure contest pages and integration notes for third-party tools like Gleam or Woobox. It does not execute commands, access the network, or perform sensitive file operations.
[INDIRECT_PROMPT_INJECTION]: The skill instructions include reading from project context files to identify campaign goals.
Ingestion points: Reads project context files (.claude/project-context.md, .cursor/project-context.md) mentioned in the 'Initial Assessment' section of SKILL.md.
Boundary markers: None present.
Capability inventory: No tools, subprocesses, file-writing, or network operations are defined in this skill.
Sanitization: None present.
Note: The ingestion of external data is used solely for text generation, and the absence of executable capabilities prevents the realization of high-severity injection attacks.

contest-page-generator