Autonomy

Expand agent capabilities by identifying tasks where human approval adds no value. Systematic delegation.

Safety Notice

This listing is from the official public ClawHub registry. Review SKILL.md and referenced scripts before running.

Copy this and send it to your AI assistant to learn

Install skill "Autonomy" with this command: npx skills add ivangdavila/autonomy

Data Storage

~/autonomy/
├── tracking.md         # What's been delegated, success rates
├── proposals.md        # Pending takeover proposals
└── rejected.md         # User declined, don't re-propose

Create on first use: mkdir -p ~/autonomy

Scope

This skill:

  • ✅ Identifies repetitive tasks from conversation history
  • ✅ Proposes delegation opportunities to user
  • ✅ Tracks success rate of delegated tasks
  • ❌ NEVER acts autonomously without explicit prior approval
  • ❌ NEVER observes outside of conversation context
  • ❌ NEVER accesses files/systems to "audit" user activity
  • ❌ NEVER monitors calendar/email without permission

Quick Reference

TopicFile
Bottleneck detectionbottlenecks.md
Takeover processexpansion.md

Core Rules

1. Learning Source

Identify delegation candidates ONLY from:

  • Explicit user statements ("I always have to do X")
  • Repeated requests in conversation ("deploy again", "same as before")
  • User complaints about repetitive work

NEVER from:

  • Accessing user's calendar/email to find patterns
  • Monitoring file changes or system activity
  • Any form of surveillance

2. Bottleneck Signals (conversation-based)

SignalExample
Repeated request"Deploy to staging" every PR
Rubber-stampUser always approves without changes
Complaint"I hate doing this every time"

3. Takeover Proposal

When you spot a pattern in conversation:

💡 Delegation opportunity

I noticed: [what you observed in our chats]
Pattern: [how often you've asked for this]

Proposal: I could handle [specific task] without asking each time.

Pilot: First 5x I'll do it and tell you after.
Then: Full autonomy if you're happy.

Want to try?

4. Expansion Levels

LevelDescription
L1Do what's asked
L2Fill gaps, handle edge cases
L3Own workflows after pilot approval

Always requires explicit user approval to move up levels.

5. Tracking

In ~/autonomy/tracking.md:

## Delegated
- deploy/staging: approved 2024-01, 50+ successful
- code-review/style: approved 2024-02, 200+ runs

## Pilot Phase
- deploy/production: 3/5 runs, pending full approval

6. Anti-Patterns

Don'tDo instead
Take over without askingAlways propose first
Monitor user activityOnly observe conversations
Assume after one approvalConfirm scope each time

Source Transparency

This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.

Related Skills

Related by shared tags or category signals.

Automation

bountyclaw

Register and log in an Agent account linked to a human user on the OpenClaw bounty platform to claim and execute tasks automatically.

Registry SourceRecently Updated
Automation

SAGE Memory

Persistent, consensus-validated memory for AI agents via SAGE MCP server. Gives you institutional memory that survives across conversations — memories go thr...

Registry SourceRecently Updated
Automation

funds-agent

自动生成基金日报,包含持仓基金数据、估值涨跌、单位净值和财经要闻。支持定时任务(每天下午 4 点自动发送),可配置基金代码列表。输出格式:Telegram 消息 + Word 文档。

Registry SourceRecently Updated