Claude-skill-registry approval-workflow

Manages Human-in-the-Loop (HITL) approval workflows for sensitive actions. Use when creating approval requests, processing approved items, or implementing safety controls for autonomous actions.

install
source · Clone the upstream repo
git clone https://github.com/majiayu000/claude-skill-registry
Claude Code · Install into ~/.claude/skills/
T=$(mktemp -d) && git clone --depth=1 https://github.com/majiayu000/claude-skill-registry "$T" && mkdir -p ~/.claude/skills && cp -r "$T/skills/data/approval-workflow" ~/.claude/skills/majiayu000-claude-skill-registry-approval-workflow && rm -rf "$T"
manifest: skills/data/approval-workflow/SKILL.md
source content

Approval Workflow Skill

This skill implements the Human-in-the-Loop (HITL) approval system that ensures human oversight for sensitive autonomous actions.

Core Concept

The approval workflow uses folder-based state management:

/Pending_Approval/  →  Human reviews  →  /Approved/  →  Execute
                                    →  /Rejected/  →  Archive

Approval Request Format

---
type: approval_request
action: [action_type]
created: [ISO timestamp]
expires: [ISO timestamp]
status: pending
priority: [critical|high|medium|low]
requestor: [agent_name]
risk_level: [low|medium|high]
reversible: [true|false]
---

## Action Summary
[Brief description of what will happen]

## Details
[Full action parameters]

## Risk Assessment
- **Reversible**: [Yes|No|Partial]
- **Impact**: [Description]
- **Sensitive Data**: [Yes|No]

## Instructions
- **Approve**: Move to `/Approved/`
- **Reject**: Move to `/Rejected/`
- **Edit**: Modify, then approve

Approval Thresholds

Action TypeAuto-ApproveHuman Required
Email (known contact)Reply onlyNew recipients
Payment< $50 recurringNew payee, > $100
Social postScheduledImmediate, replies
File operationsCreate/readDelete
WhatsAppGreetingsBusiness msgs

Workflow States

  1. pending - Awaiting human decision
  2. approved - Cleared for execution
  3. rejected - Denied by human
  4. expired - Timed out without decision
  5. executed - Action completed
  6. failed - Execution error

Reference

For detailed implementation, see reference.md

For usage examples, see examples.md