The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes local Python scripts located within the project's internal structure to perform validation and search operations.
Evidence: The skill runs python .codestable/tools/validate-yaml.py to verify the syntax of generated checklist files.
Evidence: The skill invokes python .codestable/tools/search-yaml.py to look up existing architectural decisions and conventions within the .codestable/compound directory.
[PROMPT_INJECTION]: The skill demonstrates an indirect prompt injection surface because it reads and processes data from various external project files that are not part of the skill itself.
Ingestion points: The skill reads content from {slug}-intent.md, {roadmap-slug}-roadmap.md, {roadmap-slug}-items.yaml, and various project source code files during the design drafting phase.
Boundary markers: There are no explicit instructions or delimiters defined to isolate the agent from potentially malicious instructions embedded within these external project files.
Capability inventory: The skill possesses the ability to write new documentation files and execute local scripts for validation and searching.
Sanitization: The instructions do not specify any validation, filtering, or escaping of the ingested file content before it is used in the prompt generation process.

cs-feat-design