← 返回 Skills 市场
Adaptive Reasoning
作者
TobeyRebecca
· GitHub ↗
· v1.0.0
· MIT-0
113
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install toby-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...
安全使用建议
This skill is coherent and does not ask for secrets or installs. Before enabling it, confirm your agent platform supports the `/reasoning` command or a session_status tool (the skill assumes those exist). Be aware it instructs the agent to silently enable/disable extended reasoning and to append icons (🧠 or 🧠🔥) to responses — if you prefer explicit user consent before mode changes, disable or modify the skill. Test it in a safe session to verify the toggles and output formatting behave as you expect.
功能分析
Type: OpenClaw Skill
Name: toby-adaptive-reasoning
Version: 1.0.0
The skill bundle is a utility designed to help an AI agent self-assess task complexity and toggle internal reasoning modes. The instructions in SKILL.md are transparent, focusing on logic thresholds and visual indicators (emojis) for the user, with no evidence of data exfiltration, malicious execution, or unauthorized access.
能力评估
Purpose & Capability
Name/description match the SKILL.md: it evaluates message complexity and toggles reasoning. No unrelated binaries, env vars, or installs are requested.
Instruction Scope
Instructions explicitly tell the agent to toggle reasoning (via `/reasoning on` or a session_status tool) and to append icons at the end of responses. This is consistent with the purpose but is platform-specific (relies on an available `/reasoning` command or session_status tool) and silently changing reasoning state may be undesirable to some users.
Install Mechanism
Instruction-only skill with no install spec and no code files — nothing is written to disk and no external downloads are performed.
Credentials
No environment variables, credentials, or config paths are requested; nothing disproportionate is required for the described task.
Persistence & Privilege
Skill does not request always:true or other elevated persistence. It instructs toggling session reasoning state but does not modify other skills or system-wide configs.
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 toby-adaptive-reasoning - 安装完成后，直接呼叫该 Skill 的名称或使用
/toby-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
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... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 113 次。
如何安装 Adaptive Reasoning？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install toby-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 TobeyRebecca（@tobeyrebecca）开发并维护，当前版本 v1.0.0。
推荐 Skills