ClawKit Logo
ClawKitReliability Toolkit
Back to Registry
Official Verified

autonomy-type-based

Type-based autonomous task queue system. Categorizes tasks by type (research, writing, analysis, maintenance) and lets autonomy work only on value-add tasks while cron handles maintenance. Use when you want autonomous work on specific task types, maximize token efficiency, and maintain clear separation of concerns between autonomous work and scheduled maintenance.

skill-install โ€” Terminal

Install via CLI (Recommended)

clawhub install openclaw/skills/skills/luciusrockwing/autonomy-type-based
Or

Type-Based Autonomy

Transform your agent from reactive to autonomous worker on specific task types.


Concept

The agent pulls from tasks/QUEUE.md but only works on tasks tagged with specific types:

๐Ÿ“š Research  โ†’ โœ… Autonomy works on these
โœ๏ธ Writing   โ†’ โœ… Autonomy works on these
๐Ÿ” Analysis  โ†’ โœ… Autonomy works on these

๐Ÿงน Maintenance โ†’ โŒ Autonomy SKIPS these (cron handles)
๐Ÿ’พ Backup      โ†’ โŒ Autonomy SKIPS these (cron handles)

Cron jobs handle backups, cleanup, security audits. Autonomy handles research, writing, analysis.


How It Works

1. Task Queue Structure

Every task in tasks/QUEUE.md has a @type: label:

## ๐Ÿ”ด Ready

### ๐Ÿ“š Research (@type:research)
- [ ] @priority:high @type:research Competitor pricing for X product
- [ ] @priority:medium @type:research Ollama model alternatives

### โœ๏ธ Writing (@type:writing)
- [ ] @priority:medium @type:writing Blog post on memory systems
- [ ] @priority:low @type:writing Documentation update

### ๐Ÿ” Analysis (@type:analysis)
- [ ] @priority:medium @type:analysis Review weekly metrics
- [ ] @priority:low @type:analysis Analyze token patterns

### ๐Ÿงน Maintenance (@type:maintenance)
โ†’ Autonomy IGNORES, cron handles
- [ ] @priority:medium @type:maintenance Old log cleanup

2. Heartbeat Flow

Heartbeat โ†’ Check urgent โ†’ No โ†’ Read QUEUE.md โ†’ Filter by @type โ†’ Pick task โ†’ Work โ†’ Update QUEUE โ†’ Log

Filter logic:

  • Read all tasks in ๐Ÿ”ด Ready section
  • ONLY pick tasks with @type:research | @type:writing | @type:analysis
  • SKIP tasks with @type:maintenance | @type:backup | @type:security

3. Task Completion

1. Mark task as In Progress: @agent: @type:research [task description]
2. Work on it
3. Move to Done Today with completion notes
4. Log to memory/[today].md
5. Check GOALS.md and .learnings/ for follow-up tasks

Task Types

Research (@type:research)

Definition: Information gathering, investigation, discovery

Examples:

  • Competitor analysis
  • API documentation research
  • Technology exploration
  • Market research
  • Best practices investigation

Output format:

## Research: [Topic]

### Findings
- Key point 1
- Key point 2

### Sources
- [Source 1](url)
- [Source 2](url)

### Recommendations
- Recommendation 1
- Recommendation 2

Add follow-up task to Ideas:

- [Idea: @type:analysis @priority:medium Analyze research findings for X]

Writing (@type:writing)

Definition: Content creation, documentation, communication

Examples:

  • Blog posts
  • Documentation updates
  • Email drafts
  • Announcements
  • Guides/tutorials

Output format:

# [Title]

[Content]

Post-completion:

  • If email: Add to Ideas for review by RA
  • If blog/doc: Add to Ideas for publishing
  • If announcement: Add to Ideas for distribution

Analysis (@type:analysis)

Definition: Data review, metrics analysis, pattern finding

Metadata

Stars1601
Views0
Updated2026-02-27
View Author Profile
AI Skill Finder

Not sure this is the right skill?

Describe what you want to build โ€” we'll match you to the best skill from 16,000+ options.

Find the right skill
Add to Configuration

Paste this into your clawhub.json to enable this plugin.

{
  "plugins": {
    "official-luciusrockwing-autonomy-type-based": {
      "enabled": true,
      "auto_update": true
    }
  }
}
Safety NoteClawKit audits metadata but not runtime behavior. Use with caution.