The Agent Skills Directory

[SAFE]: The skill is designed to manage feature targeting rules for LaunchDarkly's AI Configs. All network operations are directed at the official LaunchDarkly API domain (app.launchdarkly.com).
[DATA_EXPOSURE]: The skill provides guidance for the agent to locate LaunchDarkly API keys within environment variables or specific configuration files (e.g., ~/.claude/config.json). This is documented as a prerequisite for the tool's functionality and does not involve transmitting these credentials to any unauthorized third party.
[COMMAND_EXECUTION]: While the documentation provides examples using curl commands, the core implementation is provided in a Python class using the requests library. The use of structured JSON payloads for API requests prevents command injection vulnerabilities.
[EXTERNAL_DOWNLOADS]: The Python implementation relies on the standard requests library for HTTP communication. No untrusted or third-party external scripts are downloaded or executed.

aiconfig-targeting