The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process user-provided prose drafts for refinement and editing, which represents a standard indirect instruction surface for AI agents. * Ingestion points: User-provided text drafts processed by the agent and the bundled linter. * Boundary markers: The skill does not currently define specific delimiters or instructions to ignore embedded commands within the draft text. * Capability inventory: Capabilities are limited to text processing and local execution of the bundled linter script. * Sanitization: No specific sanitization of input text is performed before it is analyzed against stylistic rules.- [DYNAMIC_EXECUTION]: The skill includes a bundled Node.js script, slop-lint.mjs, to provide automated stylistic feedback. * The script is self-contained and imports only the standard node:fs library for file reading. * Execution is limited to local pattern-matching against stylistic guidelines and does not include network access or dynamic code evaluation (e.g., eval or exec).

no-slop