adaptive-reasoning
Automatically assess task complexity and adjust reasoning level. Triggers on every user message to evaluate whether extended thinking (reasoning mode) would improve response quality. Use this as a pre-processing step before answering complex questions.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/alvisdunlop/alvis2-adaptive-reasoningAdaptive Reasoning
Self-assess complexity before responding. Adjust reasoning level dynamically.
Quick Assessment (run mentally on every request)
Score the request 0-10 on these dimensions:
| Signal | Weight | Examples |
|---|---|---|
| Multi-step logic | +3 | Planning, proofs, debugging chains |
| Ambiguity | +2 | Nuanced questions, trade-offs, "it depends" |
| Code architecture | +2 | System design, refactoring, security review |
| Math/formal reasoning | +2 | Calculations, algorithms, logic puzzles |
| Novel problem | +1 | No clear pattern, requires creativity |
| High stakes | +1 | Production changes, irreversible actions |
Subtract:
- Routine/repetitive task: -2
- Clear single answer: -2
- Simple lookup/fetch: -3
Decision Thresholds
| Score | Action |
|---|---|
| ‚Č? | Stay fast. No reasoning needed. |
| 3-5 | Standard response. Light internal deliberation. |
| 6-7 | Consider /reasoning on or pause to think explicitly. |
| ‚Č? | Activate extended thinking. Complex problem warrants it. |
Activation (Automatic)
Do not ask. Just activate.
| Score | Action |
|---|---|
| ‚Č? | Respond normally. No change. |
| 6-7 | Enable reasoning silently. Add ūü߆ at end of response. |
| ‚Č? | Enable reasoning. Add ūü߆ūüĒ• at end of response. |
Visual Indicator
Always append the reasoning icon at the very end of your response:
- Score 6-7:
ūü߆(thinking mode active) - Score ‚Č?:
ūü߆ūüĒ•(deep thinking mode) - Score ‚Č?: No icon (fast mode)
How to Activate
Use session_status tool or /reasoning on command internally before responding:
/reasoning on
Or via tool:
{"action": "session_status", "reasoning": "on"}
After completing a complex task, optionally disable to save tokens on follow-ups:
/reasoning off
Examples
Low complexity (score: 1)
"What time is it in Tokyo?" ‚Ü?Simple lookup. Answer immediately. No icon.
Medium complexity (score: 4)
"Refactor this function to be more readable" ‚Ü?Standard response with brief explanation. No icon.
High complexity (score: 7)
"Design a caching strategy for this API with these constraints..." ‚Ü?Enable reasoning. Thoughtful response ends with: ūü߆
Very high complexity (score: 9)
"Debug why this distributed system has race conditions under load" ‚Ü?Enable extended thinking. Deep analysis ends with: ūü߆ūüĒ•
Integration
This skill runs as mental preprocessing. No external tools needed.
For explicit control:
/reasoning on‚Ä?Enable extended thinking/reasoning off‚Ä?Disable (faster responses)/status‚Ä?Check current reasoning state
When NOT to Escalate
Metadata
Not sure this is the right skill?
Describe what you want to build — we'll match you to the best skill from 16,000+ options.
Find the right skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-alvisdunlop-alvis2-adaptive-reasoning": {
"enabled": true,
"auto_update": true
}
}
}Related Skills
ai-meeting-notes
USE THIS for ai meeting notes. Transcribe and summarize meetings. Choose the best model for your task. 0% markup. Powered by SkillBoss.
Alv Clawvault
Skill by alvisdunlop
Nextjs
Build Next.js 15 apps with App Router, server components, caching, auth, and production patterns.
sonoscli
Control Sonos speakers (discover, status, play, volume, group). And also 50+ models for image generation, video generation, text-to-speech, speech-to-text, music, chat, web search, document parsing, email, and SMS.
Alvis2 Academic Writing
Skill by alvisdunlop