The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes the Bash tool to execute project-related commands such as npm test, npm run lint, and npm run build during quality gate checks. This is a core part of its autonomous orchestration function but involves executing code defined within the project files.
[EXTERNAL_DOWNLOADS]: The skill is designed to manage project foundations and core phases, which typically involve fetching dependencies from public registries (e.g., via npm or other package managers) based on the project's archetype.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it ingests and processes untrusted data from project files.
Ingestion points: Reads project requirements (prd.md), discovery answers (discovery-answers.yaml), and architectural specifications (api-spec.md) using Read, Glob, and Grep tools.
Boundary markers: None explicitly defined in the provided markdown to separate external data from system instructions.
Capability inventory: Includes Bash, Write, Edit, and Task tools, allowing for significant environmental changes.
Sanitization: No specific sanitization or validation logic is described for the content of processed project files.
[COMMAND_EXECUTION]: The decision framework categorizes actions by autonomy levels (0-4), specifically requiring human intervention for level 4 tasks like handling API credentials, which serves as a mitigation for potential command abuse.

Project Orchestration