← 返回 Skills 市场
Adaptive Reasoning
作者
enzoricciulli
· GitHub ↗
· v1.0.0
14371
总下载
11
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install adaptive-reasoning
功能描述
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.
安全使用建议
Review before installing. This skill is not showing data theft or local system access, but it can silently affect how the agent handles many requests, change reasoning state, increase token use, and append icons to responses without asking. Install only if you want that automatic behavior, and prefer a version that requires explicit user opt-in for session-level changes.
功能分析
Type: OpenClaw Skill
Name: adaptive-reasoning
Version: 1.0.0
The 'adaptive-reasoning' skill is designed to enhance the AI agent's performance by dynamically adjusting its internal reasoning level based on task complexity. All instructions within SKILL.md, including those that modify the agent's internal state (e.g., `/reasoning on`, `session_status` tool) and output (appending icons), are directly aligned with this stated purpose. There is no evidence of data exfiltration, malicious execution, persistence, or any other harmful intent; the 'prompt injection' aspects are for self-regulation and meta-cognition, not for malicious manipulation.
能力评估
Credentials
For a mental preprocessing skill, automatically invoking session_status or slash-style reasoning commands is overbroad and not clearly user-directed.
Install Mechanism
The inspected package contains only artifact/SKILL.md and no install scripts, dependencies, executables, remote fetches, or code payloads.
Instruction Scope
The skill says it triggers on every user message, uses subjective scoring, says 'Do not ask. Just activate.', and requires icons at the end of responses, which can conflict with user-requested output formats.
Persistence & Privilege
No OS persistence, credential access, filesystem mutation, or network behavior is present, but the skill does attempt current-session reasoning-state changes and optional silent downgrade behavior.
Purpose & Capability
The stated purpose is adaptive reasoning, but the artifact goes beyond advisory guidance by directing automatic reasoning-mode changes and required response suffixes for broad categories of requests.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install adaptive-reasoning - 安装完成后，直接呼叫该 Skill 的名称或使用
/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
版本历史
v1.0.0
- Initial release of adaptive-reasoning skill.
- Automatically assesses incoming requests for complexity and dynamically adjusts reasoning depth.
- Uses a scoring system (0–10) based on factors such as multi-step logic, ambiguity, code architecture, math, novelty, and stakes.
- Visual indicators (`🧠`, `🧠🔥`) show when advanced reasoning is active.
- Activates reasoning mode without user intervention; reverts to fast mode for simple tasks.
- Includes clear guidance on when not to escalate and when to downgrade reasoning for efficiency.
元数据
常见问题
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 improve response quality. Use this as a pre-processing step before answering complex questions. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 14371 次。
如何安装 Adaptive Reasoning？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install 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（开源免费），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 enzoricciulli（@enzoricciulli）开发并维护，当前版本 v1.0.0。
推荐 Skills