ClawHub

Adaptive Reasoning

v1.0.0

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.

⭐ 8· 8.6k·116 current·122 all-time
by@enzoricciulli
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
high confidence
✓
Purpose & Capability
Name/description match the instructions: the SKILL.md defines a mental pre-processing scoring system and prescribes activating a reasoning mode. No unrelated binaries, env vars, or configs are requested.
ℹ
Instruction Scope
Instructions stay within the stated purpose (score requests, call /reasoning on/off, append visual icons). They do instruct the agent to "Do not ask. Just activate." and to trigger on every user message, which is a behavioral policy decision (not a technical inconsistency). Ensure the underlying platform provides the /reasoning command or session_status tool; otherwise the activation steps are not actionable.
✓
Install Mechanism
Instruction-only skill with no install spec and no code files — lowest-risk install profile.
✓
Credentials
No environment variables, credentials, or config paths are requested; nothing disproportionate to the skill's purpose.
ℹ
Persistence & Privilege
always:false (not force-included) and disable-model-invocation:false (agent may invoke autonomously). Autonomous invocation is expected for a preprocessor, but be aware it will change runtime behavior (enabling reasoning silently) unless the user explicitly disables it.
Assessment
This skill is coherent and doesn't request secrets or install code, but it changes agent behavior: it will automatically enable extended reasoning for messages scored as complex and append icons to your responses. Before installing, confirm your agent platform supports the /reasoning or session_status mechanism the skill expects. Decide whether you want automatic, silent activation (the skill says "Do not ask. Just activate.") — if not, keep it user-invocable only or modify the instructions to ask for consent. Test with a few sample prompts to verify the activation behavior and icon placement; disable the skill if it interferes with your workflows.

Like a lobster shell, security has layers — review code before you run it.

latestvk97bmf6a4vdsbb6382z4aq02cd80r3eq

License

MIT-0
Free to use, modify, and redistribute. No attribution required.
Termshttps://spdx.org/licenses/MIT-0.html

Comments