The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes shell commands to manage the development lifecycle, including repository cloning and Pull Request creation. Evidence: Commands such as gh repo clone, git add, git commit, git push, and gh pr create are employed in references/block4-prd-and-github.md to submit the user's PRD to their personal repository within the vendor's organization.
[EXTERNAL_DOWNLOADS]: The skill facilitates the installation of additional training materials and plugins from vendor-associated sources. Evidence: SKILL.md contains instructions to run npx skills add ai-native-camp/camp-2 and to install plugins via the marketplace or specific author repositories.
[INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied text to generate structured requirements and PRD documents, creating a surface for potential injection. 1. Ingestion points: User input provided during the 'clarify:vague' process and the GitHub ID requested in references/block4-prd-and-github.md. 2. Boundary markers: The instructions do not define specific delimiters or guardrails to prevent the agent from executing instructions potentially embedded in the user's requirements text. 3. Capability inventory: The agent has access to powerful tools including file system modification, network fetching via curl, and GitHub CLI operations. 4. Sanitization: There is no explicit validation or sanitization step for the external data before it is processed or used in shell commands.

day3-clarify