Adaptive Reasoning
/install alvis-adaptive-reasoning
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 |
|---|---|
| �? | Stay fast. No reasoning needed. |
| 3-5 | Standard response. Light internal deliberation. |
| 6-7 | Consider /reasoning on or pause to think explicitly. |
| �? | Activate extended thinking. Complex problem warrants it. |
Activation (Automatic)
Do not ask. Just activate.
| Score | Action |
|---|---|
| �? | Respond normally. No change. |
| 6-7 | Enable reasoning silently. Add 🧠 at end of response. |
| �? | 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 �?:
🧠🔥(deep thinking mode) - Score �?: 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 �?), if the next message is simple (score �?):
- Silently disable reasoning to save tokens
- Resume normal fast responses \r
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install alvis-adaptive-reasoning - 安装完成后，直接呼叫该 Skill 的名称或使用
/alvis-adaptive-reasoning触发 - 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
Adaptive Reasoning 是什么？
Automatically assess task complexity and adjust reasoning level. Triggers on every user message to evaluate whether extended thinking (reasoning mode) would... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 125 次。
如何安装 Adaptive Reasoning？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install alvis-adaptive-reasoning」即可一键安装，无需额外配置。
Adaptive Reasoning 是免费的吗？
是的，Adaptive Reasoning 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Adaptive Reasoning 支持哪些平台？
Adaptive Reasoning 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。
谁开发了 Adaptive Reasoning？
由 AlvisDunlop（@alvisdunlop）开发并维护，当前版本 v2.0.0。