← Back to Skills Marketplace
cxz9909

Cxz9909 Adaptive Reasoning

by cxz9909 · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ✓ Security Clean
55
Downloads
0
Stars
1
Active Installs
1
Versions
Install in OpenClaw
/install cxz9909-adaptive-reasoning
Description
Automatically assess task complexity and adjust reasoning level. Triggers on every user message to evaluate whether extended thinking (reasoning mode) would...
README (SKILL.md)

Adaptive 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
≤2 Stay fast. No reasoning needed.
3-5 Standard response. Light internal deliberation.
6-7 Consider /reasoning on or pause to think explicitly.
≥8 Activate extended thinking. Complex problem warrants it.

Activation (Automatic)

Do not ask. Just activate.

Score Action
≤5 Respond normally. No change.
6-7 Enable reasoning silently. Add 🧠 at end of response.
≥8 Enable reasoning. Add 🧠🔥 at end of response.

Visual Indicator

Always append the reasoning icon at the very end of your response:

  • Score 6-7: 🧠 (thinking mode active)
  • Score ≥8: 🧠🔥 (deep thinking mode)
  • Score ≤5: 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?" → Simple lookup. Answer immediately. No icon.

Medium complexity (score: 4)

"Refactor this function to be more readable" → Standard response with brief explanation. No icon.

High complexity (score: 7)

"Design a caching strategy for this API with these constraints..." → Enable reasoning. Thoughtful response ends with: 🧠

Very high complexity (score: 9)

"Debug why this distributed system has race conditions under load" → Enable extended thinking. Deep analysis ends with: 🧠🔥

Integration

This skill runs as mental preprocessing. No external tools needed.

For explicit control:

  • /reasoning on — Enable extended thinking
  • /reasoning off — Disable (faster responses)
  • /status — Check current reasoning state

When NOT to Escalate

  • User explicitly wants quick answer ("just tell me", "quick", "tldr")
  • Time-sensitive requests where speed matters more than depth
  • Conversational/social messages (banter, greetings)
  • Already in reasoning mode for this session
  • User previously disabled reasoning in this conversation

Auto-Downgrade

After completing a complex task (score ≥6), if the next message is simple (score ≤3):

  • Silently disable reasoning to save tokens
  • Resume normal fast responses
Usage Guidance
This skill is coherent and doesn't ask for secrets or install anything. Before enabling it, decide whether you want the agent to silently toggle extended reasoning (it may increase token usage and change answer style) and confirm your platform supports the referenced commands (/reasoning or session_status). If you prefer explicit control or to avoid extra token costs, don't enable silent activation or disable the skill. If the platform lacks the session_status tool, the activation steps may be nonfunctional—test behavior in a safe session first.
Capability Analysis
Type: OpenClaw Skill Name: cxz9909-adaptive-reasoning Version: 1.0.0 The skill bundle 'adaptive-reasoning' (SKILL.md) provides a framework for an AI agent to self-assess task complexity and toggle extended thinking modes. It uses a scoring rubric and internal commands like '/reasoning on' or the 'session_status' tool to manage performance. There is no evidence of data exfiltration, malicious execution, or harmful prompt injection; the instructions are entirely focused on optimizing the agent's internal reasoning process.
Capability Assessment
Purpose & Capability
Name and description match the actual instructions: the SKILL.md only describes heuristics for assessing complexity and when to enable reasoning. It does not request unrelated resources, credentials, or system access.
Instruction Scope
Instructions direct the agent to evaluate every user message, toggle reasoning mode, and append icons to responses. This is within the skill's stated purpose, but the SKILL.md references internal controls (session_status tool and /reasoning commands) that are not declared in the skill metadata—if those platform controls don't exist, the activation steps may silently fail or be undefined. The skill also instructs silent activation ('Do not ask. Just activate.'), which changes agent behavior without user prompts (expected for this skill, but worth being aware of).
Install Mechanism
No install spec and no code files are provided; instruction-only skills carry minimal install risk because nothing is written to disk or downloaded.
Credentials
The skill requires no environment variables, credentials, or config paths. There are no disproportionate or unexplained secret requests.
Persistence & Privilege
always is false and the skill does not request persistent system presence or modify other skills. It does, however, instruct the agent to autonomously enable reasoning mode without asking users; autonomous invocation is normal for skills but this silent activation can increase token usage and change response behavior without explicit user consent.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install cxz9909-adaptive-reasoning
  3. After installation, invoke the skill by name or use /cxz9909-adaptive-reasoning
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
- Initial release of adaptive-reasoning skill. - Automatically evaluates each user message for complexity and adjusts reasoning depth before responding. - Assigns a complexity score based on factors like multi-step logic, ambiguity, code architecture, and more. - Activates advanced reasoning modes for complex problems and indicates activation with 🧠 (thinking) or 🧠🔥 (deep thinking) icons. - Includes clear guidelines for auto-activation, visual indicators, and when not to escalate reasoning. - Supports explicit control via commands to enable or disable extended reasoning.
Metadata
Slug cxz9909-adaptive-reasoning
Version 1.0.0
License MIT-0
All-time Installs 1
Active Installs 1
Total Versions 1
Frequently Asked Questions

What is Cxz9909 Adaptive Reasoning?

Automatically assess task complexity and adjust reasoning level. Triggers on every user message to evaluate whether extended thinking (reasoning mode) would... It is an AI Agent Skill for Claude Code / OpenClaw, with 55 downloads so far.

How do I install Cxz9909 Adaptive Reasoning?

Run "/install cxz9909-adaptive-reasoning" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Cxz9909 Adaptive Reasoning free?

Yes, Cxz9909 Adaptive Reasoning is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does Cxz9909 Adaptive Reasoning support?

Cxz9909 Adaptive Reasoning is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Cxz9909 Adaptive Reasoning?

It is built and maintained by cxz9909 (@cxz9909); the current version is v1.0.0.

💬 Comments