The Agent Skills Directory

[COMMAND_EXECUTION]: The skill performs local file searches using grep to identify specific comment patterns across multiple programming languages including TypeScript, Python, and Go.
[COMMAND_EXECUTION]: To verify that comment removal does not disrupt project tooling, the skill executes standard development commands such as bunx biome, npx eslint, and ruff.
[COMMAND_EXECUTION]: The skill attempts to run documentation generation scripts defined within the user's project (npm run docs, bun run docs), which executes code defined in the project's own configuration.
[PROMPT_INJECTION]: The skill has an indirect prompt injection surface because it reads and processes untrusted data from the local codebase to generate reports and determine deletion targets.
Ingestion points: Source code files processed via grep and read during the assessment phase.
Boundary markers: The skill does not define explicit delimiters or use specific 'ignore' instructions when the agent processes the content of the discovered comments.
Capability inventory: The agent is authorized to modify files using the Edit tool and execute shell commands for linting and verification.
Sanitization: There is no evidence of sanitization or filtering of the comment content before it is processed by the agent to create the 'Critical Assessment' report.

cleanup-slop