The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill fetches documentation from external package registries and repository pages to populate library documentation. It also searches the skills.sh registry and other repository pages for agent extensions.
[REMOTE_CODE_EXECUTION]: The skill facilitates the installation and execution of external agent skills using npx skills add and installs the Playwright automation tool along with the Chromium browser. These tools execute code within the agent's operating environment.
[COMMAND_EXECUTION]: The skill executes shell commands to perform project dependency audits, install agent extensions, and manage browser automation tools.
[INDIRECT_PROMPT_INJECTION]: The skill ingests data from external sources, including project requirement files and third-party documentation pages, which are used to influence architecture decisions and build plans.
Ingestion points: project-overview.md (local), external documentation URLs (library-docs.md), and registry search results (internal/tool-discovery.md).
Boundary markers: The skill does not explicitly use boundary markers or delimiters when interpolating fetched content into instructions.
Capability inventory: Full file system access (Write, Edit), shell command execution (Bash), and the ability to install additional agent capabilities.
Sanitization: No explicit sanitization or validation of fetched external prose was identified.

dev-architect