據 AlphaMoat 統計,截至 2026-10,Adaptive Reasoning 累計下載 27,306 次、獲 12 個星標,按累計下載量在本次參與排名的 10,914 個 AI 技能中排名第 1,032 位,在「AI 智慧體」分類(1,632 個)中排名第 157 位。
列表預設按累計下載量排序,也可按星標排序;詳情頁排名按累計下載量計算。
| 平台 | 累計下載 | 星標 | 評論 |
|---|---|---|---|
| ClawHub ↗ | 1.4萬 | 11 | 2 |
| SkillHub ↗ | 2.7萬 | 12 | — |
各平台的計數口徑不同,統計時間不一致。
此技能指示依多個面向為每則使用者訊息評 0 到 10 分,並據此建議推理方案:6–7 分使用擴充思考,8 分以上使用深度思考,5 分以下維持快速模式;高分時也會要求附加視覺標記。這可能跨多則訊息改變回覆行為、加入使用者未要求的格式,並增加 token 用量。文件描述的是一套流程,不保證執行環境設定一定會變更。僅在確實需要自動切換推理方案和新增標記時使用,並先評估這些影響。
資料釋出於 2026-10-27
以下是根據技能文件生成的示例,不代表實際執行結果。
2026-09 起統計方法調整:同名技能按作者分別統計,並覆蓋全部技能。圖中虛線為調整前的月份,與之後的資料不直接比較,也不計算跨越調整的增長。 該技能有同名的其他版本,調整前的資料歸屬當前下載量最大的這一個。
| 月份 | 累計下載 | 環比 | 星標 |
|---|---|---|---|
| 2026-10 | 2.7萬 | — | 12 |
| 2026-09 | 1.6萬 | — | 12 |
| 2026-08 | 1.4萬 | +3.7% | 12 |
| 2026-07 | 1.3萬 | +6.2% | 12 |
| 2026-06 | 1.2萬 | +4.1% | 12 |
| 2026-05 | 1.2萬 | — | 13 |
| 2026-03 | 9271 | — | 8 |
以下是作者釋出的原始檔案,按純文字顯示,本站未做修改或稽核;其中的連結不可點選,命令請核實後再執行。抓取於 2026-10-23。
--- 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)
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
將開發過程中的經驗、錯誤與修正記錄為 Markdown 檔案,供日後重用並提升為工作區記憶。
用自然語言描述需求,在本機與遠端技能市場尋找技能並取得推薦。
給 AI agent 用的瀏覽器自動化命令列技能。
將使用者明確糾正與自我檢視整理成分層記憶,並依使用情況升級或封存。
規劃 AI 代理主動跟進、工作記憶與回顧流程的工作區設定指南。
指導如何建立與更新有效 Claude 技能的寫作指南。
在安裝第三方技能之前,按清單審查來源、許可權與危險模式的技能。
把盛唐詩人李白的詩學觀、意象系統與口吻,蒸餾成 AI 可呼叫的角色包。
資料月份:2026-10 · 下載/星標數聚合自公開技能註冊庫(ClawHub、SkillHub),按月更新。口徑說明見資料方法。