The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill downloads and executes the aislop CLI from the public npm registry. This is a vendor-owned resource that matches the skill's author, and the skill provides clear guidance on using pinned versions to mitigate supply-chain risks.
[COMMAND_EXECUTION]: The skill involves executing various shell commands such as aislop scan and aislop fix. It also supports installing pre-commit hooks and launching other agent interfaces, which are standard operations for development quality tools.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its processing of untrusted project code and scan output. Ingestion points: Findings from aislop scan --json and the content of project source files. Boundary markers: No explicit delimiters or isolation instructions are defined for processing scan results. Capability inventory: The skill can modify project files through aislop fix and manual edits, and can execute subprocesses via aislop fix --claude. Sanitization: The skill relies on a human-in-the-loop approach, instructing the agent to manually verify the context and accuracy of every finding before acting.

aislop