The Agent Skills Directory

[SAFE]: The skill consists of static markdown templates and instructional rules for document consistency. It does not include any executable code, remote script downloads, or persistent access mechanisms.- [INDIRECT_PROMPT_INJECTION]: The templates are designed to ingest and process data from external sources to generate pipeline artifacts. Ingestion points include PRD sections and User Input (spec-template.md), Figma URLs and design tokens (design-setup-template.md), and Figma component data (ui-template.md). Boundary markers are present in the form of [BRACKETS] for placeholders and standardized ID prefixes (e.g., FR-XXX, TEST-XXX, CHK###) used to separate generated content. While the templates guide the creation of executable tasks in tasks-template.md (such as INIT-, TEST-, and IMPL- tasks), there is no explicit sanitization logic for the external input defined within the templates themselves.

doc-templates