The Agent Skills Directory

[SAFE]: The skill's primary function is project documentation management. It does not perform any network operations, data exfiltration, or privileged command execution.
[NO_CODE]: The skill consists entirely of natural language instructions and a markdown template. It does not include or execute any Python scripts, Node.js packages, or binary executables.
[PROMPT_INJECTION]: The skill reads external data from project files, creating an attack surface for indirect prompt injection. However, the risk is negligible as the skill's capabilities are limited to generating static documentation.
Ingestion points: Reads data from planning/<initiative>/intake.md, planning/<initiative>/roadmap.md, and planning/<initiative>/business/*.md.
Boundary markers: Absent; the instructions do not explicitly direct the agent to delimit or ignore instructions found within the ingested project files.
Capability inventory: File-writing capability to create structured markdown files in the planning/ directory.
Sanitization: No specific sanitization or validation logic is applied to the ingested text before it is used to populate templates.
[EXTERNAL_DOWNLOADS]: No external dependencies, scripts, or remote resources are downloaded or executed by this skill.

agile-epic