The Agent Skills Directory

[COMMAND_EXECUTION]: The skill includes and instructs the user to run scripts (scripts/check.mjs, scripts/config.mjs) that use node:child_process's spawnSync to execute Git commands like git diff and git rev-parse to identify changed files in the repository.
[EXTERNAL_DOWNLOADS]: The documentation mentions using npx github:timschoch/skilly update to perform configuration migrations, which involves fetching and executing code from the author's public GitHub repository.
[INDIRECT_PROMPT_INJECTION]: The naming linter acts as a processing surface for untrusted data by reading source code files from the user's repository.
Ingestion points: The scripts/check.mjs script reads content from code files (.ts, .js, etc.) and environment example files (.env.example).
Boundary markers: The script implements a blankNoise function that identifies and removes the contents of strings and comments, ensuring the linter only evaluates declared identifiers and reducing the risk of processing malicious instructions embedded in prose.
Capability inventory: The skill possesses capabilities to execute local Git commands and write to project configuration files (.skilly/naming.json).
Sanitization: Source code content is stripped of literal strings and comments before being passed to the identification logic.

naming