The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes the Bash tool to perform local repository operations and run developer utilities. It uses git diff to identify modified files, runs npm test and npm run typecheck for validation, and executes analysis tools like jscpd and ast-grep (sg). These actions are aligned with the skill's stated purpose of code maintenance.
[EXTERNAL_DOWNLOADS]: The skill uses npx to execute the jscpd and tsc packages. This may involve downloading the packages from the public npm registry if they are not present in the local cache. This is standard behavior for JavaScript/TypeScript development environments.
[PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection because it reads and processes external data (source code files) that could be controlled by an attacker. This data is then used to guide the agent's refactoring actions.
Ingestion points: Reads files identified via git diff, the Read tool, and output from analysis tools like jscpd and sg in SKILL.md.
Boundary markers: The skill does not employ explicit delimiters or system instructions to ignore potential commands embedded within the source code being analyzed.
Capability inventory: The agent has access to Bash for command execution and Edit for file modification across the project.
Sanitization: The skill does not implement sanitization or filtering of the code content before it is processed by the model for simplification.

simplify