The Agent Skills Directory

[SAFE]: All external references and API endpoints target official Replicate domains (replicate.com, api.replicate.com, mcp.replicate.com). No unauthorized or suspicious third-party domains are present.
[SAFE]: No prompt injection or instructions to bypass safety filters were found. The skill provides neutral technical guidance for model discovery.
[SAFE]: No obfuscation, data exfiltration, or malicious command execution patterns were detected in the instructions.
[SAFE]: The skill documents intended functionality for interacting with a public API and does not request sensitive local file access or persistent system changes.

find-models