The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes project specification files (spec.md) which may contain instructions that could influence agent behavior. The logic in scripts/progress.mjs determines the next_skill to be loaded based on the Status field found in these documents.
Ingestion points: Data is ingested from files located in the specs/ directory tree (e.g., specs/draft/*/spec.md).
Capability inventory: The skill can execute local shell commands (Node.js scripts) and initiate automatic handoffs to other agent skills without user confirmation.
Boundary markers: The skill does not use specific delimiters or instructions to prevent the agent from following directions potentially embedded in the specification files.
Sanitization: Data parsed from markdown files is used directly to drive the workflow and transition logic without sanitization or validation.
[COMMAND_EXECUTION]: The skill's primary function involves running several local Node.js scripts (progress.mjs, analyze_context.mjs) and utility scripts from related skills (monitor_context.mjs, build_documentation.mjs). It also utilizes the npx command for installing additional components.
[EXTERNAL_DOWNLOADS]: The references/specialists.md file provides instructions for downloading and installing additional specialist skills from the vendor's GitHub repository (github.com/promovaweb/specsfy) using the npx skills add command. This represents expected vendor functionality for extending the skill's capabilities.

specsfy-progress