effect-uai-tool-call-approval

Official

Gate sensitive tool calls with human approval.

Authorbetalyra
Version1.0.0
Installs0

System Documentation

What problem does it solve?

Some tool calls can cause significant impact if executed without oversight. This Skill enforces a human-in-the-loop to approve sensitive actions before they run, reducing risk and ensuring accountability.

Core Features & Use Cases

  • Approval-based gating for calls like send_email, delete_user, or transfer_funds.
  • Supports HTTP synchronous approvals and verdict-queue workflows for asynchronous contexts.
  • Ensures a matching function_call_output is written to history for all outcomes (approved, denied, cancelled, or execution_error).

Quick Start

Configure the workflow to require a human approval before executing sensitive tool calls like send_email or delete_user.

Dependency Matrix

Required Modules

None required

Components

Standard package

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: effect-uai-tool-call-approval
Download link: https://github.com/betalyra/effect-uai/archive/main.zip#effect-uai-tool-call-approval

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.