enzoricciulli

Adaptive Reasoning

AI 智能体v1.0.0
作者:enzoricciulli更新于 2026-05-11adaptive-reasoning@clawhub_enzoricciulli/adaptive-reasoning
工作流编排提示词优化上下文管理#Message

据 AlphaMoat 统计,截至 2026-10,Adaptive Reasoning 累计下载 27,306 次、获 12 个星标,按累计下载量在本次参与排名的 10,914 个 AI 技能中排名第 1,032 位,在「AI 智能体」分类(1,632 个)中排名第 157 位。

列表默认按累计下载量排序,也可按星标排序;详情页排名按累计下载量计算。

累计下载
2.7万
星标
12
全站下载量排名
#1,032
全站前 10% · 「AI 智能体」前 10%
平台累计下载星标评论
ClawHub ↗1.4万112
SkillHub ↗2.7万12—

各平台的计数口径不同,统计时间不一致。

这个技能是做什么的

该技能指示按多个维度给每条用户消息评 0 到 10 分,并据此建议推理档位:6–7 分使用扩展思考,8 分及以上使用深度思考,5 分及以下保持快速模式;高分时还会要求追加视觉标记。这可能跨多条消息改变回复行为、加入用户未要求的格式,并增加 token 用量。文档描述的是一套流程,并不保证运行环境设置一定会改变。仅在确实需要自动切换推理档位和添加标记时使用,并先评估这些影响。

资料发布于 2026-10-27

可以用来做什么

  • 查看文档中的复杂度评分方式和档位阈值。
  • 判断自动推理标记是否符合回复规范。

什么时候用

  • 评估用于选择推理模式的提示词指南时。
  • 明确需要自动评估复杂度时。

示例提示词

以下是根据技能文档生成的示例,不代表实际运行结果。

总结评分阈值及文档说明的影响。
检查添加推理标记是否符合这种回复风格。

月度数据趋势

累计下载2.7万
7,8281.8万2.9万2026-03 · 累计下载 9,2712026-05 · 累计下载 1.2万2026-06 · 累计下载 1.2万2026-07 · 累计下载 1.3万2026-08 · 累计下载 1.4万2026-09 · 累计下载 1.6万2026-10 · 累计下载 2.7万26-0326-0926-10
星标12
811132026-03 · 星标 82026-05 · 星标 132026-06 · 星标 122026-07 · 星标 122026-08 · 星标 122026-09 · 星标 122026-10 · 星标 1226-0326-0926-10

2026-09 起统计方法调整:同名技能按作者分别统计,并覆盖全部技能。图中虚线为调整前的月份,与之后的数据不直接比较,也不计算跨越调整的增长。 该技能有同名的其他版本,调整前的数据归属当前下载量最大的这一个。

月份累计下载环比星标
2026-102.7万—12
2026-091.6万—12
2026-081.4万+3.7%12
2026-071.3万+6.2%12
2026-061.2万+4.1%12
2026-051.2万—13
2026-039,271—8

SKILL.md 原文

以下是作者发布的原始文件,按纯文本显示,本站未做修改或审核;其中的链接不可点击,命令请核实后再运行。抓取于 2026-10-23。

3.4 KB · ClawHub v1.0.0
---
name: adaptive-reasoning
description: 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.
---

# Adaptive Reasoning

Self-assess complexity before responding. Adjust reasoning level dynamically.

## Quick Assessment (run mentally on every request)
展开全部(共 113 行)

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:
```json
{"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

「AI 智能体」分类下的热门技能

enzoricciulli 的其他技能

数据月份:2026-10 · 下载/星标数聚合自公开技能注册库(ClawHub、SkillHub),按月更新。口径说明见数据方法。