drippy-passport968
UserDelegate coding tasks to agents, collect artifacts, and verify results locally with standalone supervision skills for Claude, Codex, and Kimi automation.
Categories
Indexed Skills (3)
claude-supervision
Use when the user wants to delegate work to the local Claude Code CLI (`claude --print`, `claude --bg`, `claude ultrareview`) — substantive tasks, multi-turn resume, structured output, multi-agent code review, background sessions — and then independently verify what Claude did. Useful from Codex / Kimi / any agent that wants to hand work to Claude Code and inspect the result. Wraps the CLI as PowerShell scripts with deadlock-safe async I/O, timeout, native JSONL recovery, and on-disk artifacts.
codex-supervision
Use when the user wants Claude to delegate work to the local Codex CLI — code review, adversarial review, or substantive rescue tasks — and then independently verify what Codex did. Works in Claude Desktop (no plugin system required); wraps codex exec as PowerShell scripts and keeps run artifacts on disk.
kimi-supervision
Use when the user wants Codex to delegate work to local Kimi Code, supervise its progress, inspect intermediate/native artifacts, continue a native Kimi session, and verify Kimi's results instead of trusting only the flattened final output.
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.