The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill fetches resources from well-known content delivery networks to render its architectural reports.
Evidence: Loads the Tailwind CSS library from https://cdn.tailwindcss.com in HTML-REPORT.md.
Evidence: Downloads the Mermaid diagramming tool from https://cdn.jsdelivr.net/npm/mermaid@11/dist/mermaid.esm.min.mjs in HTML-REPORT.md.
[COMMAND_EXECUTION]: The skill uses system shell commands to perform codebase analysis and display the final report to the user.
Evidence: Executes git log --oneline in SKILL.md to identify frequently changed files and hotspots.
Evidence: Utilizes platform-specific commands xdg-open, open, or start in SKILL.md to automatically launch the generated HTML report in the user's default browser.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the codebase being scanned, which is then interpolated into a generated HTML file that the user is encouraged to open.
Ingestion points: The skill reads file names, codebase structures, git log output, CONTEXT.md files, and Architecture Decision Records (ADRs) as specified in SKILL.md.
Boundary markers: The instructions do not specify the use of strict delimiters or sanitization routines when including this external data in the HTML report.
Capability inventory: The skill has the capability to write to the system temporary directory and invoke system commands to open generated files (SKILL.md).
Sanitization: There is no explicit requirement for the agent to escape or validate data retrieved from the codebase before including it in the report cards or diagrams.

improve-codebase-architecture