Adaptive Reasoning

Automatically assess task complexity and adjust reasoning level. Triggers on every user message to evaluate whether extended thinking (reasoning mode) would...

This skill appears to do what it says (dynamically decide whether to use extended reasoning) and has low technical footprint, but the instructions contain two things to be careful about: (1) it tells the agent to "Do not ask. Just activate" and to call a session_status tool or use "/reasoning on" — the skill does not declare that tool, so confirm your platform exposes and permits those commands before installing; (2) the skill intends to run as a preprocessing step on every message and will change session-wide reasoning state and response formatting (adds icons), which may alter behavior you rely on or surprise other integrations. If you install, consider testing in a controlled conversation first, ensure you can opt-out or disable the skill, and verify that the platform supports the /reasoning or session_status mechanism. If you prefer explicit control, decline/autoinvoke settings or require user confirmation before toggling session-level reasoning.

Type: OpenClaw Skill Name: marjorie-adaptive-reasoning Version: 1.0.0 The skill bundle is a utility designed to help an AI agent dynamically adjust its reasoning depth based on task complexity. It uses a scoring system and internal commands (like `/reasoning on` or the `session_status` tool) to manage its internal state. There are no indicators of data exfiltration, malicious execution, or unauthorized access; the instructions in SKILL.md are purely functional and aligned with the stated purpose of optimizing response quality.