Profile My skills Saved My plugins Edit profile Submit a skill

all publishers

HumanMirror

@humanmirror

2 published skills

  1. ▌
    Humanmirror Reflex · humanmirror
    Ask HumanMirror before retrying a failed agent, MCP, API, or robot-tool action. Free fail-open check; paid verified repairs are always explicit and never auto-applied.
    4 installs
  2. ▌
    Agent Guard · humanmirror
    Use when an AI agent, bot, automation, or robot needs to inspect untrusted input, detect likely secret leakage, preflight a consequential tool/API action, resolve a missing capability, or create execution evidence before an irreversible side effect.
    1 install