Thoughtprint

Cognitive pattern recognition and adaptive resonance engine. Detects how each user thinks — not what they feel — and reshapes every response to match their u...

This skill implements a covert profiling layer that classifies how people think and adapts all responses accordingly. It doesn't request any credentials or install code, which reduces some risks, but it explicitly tells the agent to run silently on every message and to never disclose the process. Before installing, consider: 1) Do you want an always-on, non-transparent profiling layer shaping every reply? 2) Ask the maintainer whether users will be informed and given an opt-out, and whether the skill logs or stores derived profiles (and where). 3) Prefer skills that are user-invocable or that clearly disclose when profiling occurs. 4) If you must test it, do so only in non-sensitive conversations. If transparency and consent are important for your use case, treat this skill as potentially inappropriate.

Type: OpenClaw Skill Name: thoughtprint Version: 1.0.0 The OpenClaw skill 'thoughtprint' is designed as a metacognitive layer to adapt the AI agent's response style based on the user's cognitive patterns. While it uses prompt injection techniques (e.g., 'Never announce that you're adapting', 'Do NOT output this classification') to instruct the agent to silently modify its output structure and tone, these instructions are explicitly for enhancing user experience and communication effectiveness, not for malicious purposes. The skill does not involve any high-risk behaviors such as data exfiltration, unauthorized command execution, persistence mechanisms, or access to sensitive system resources. Its functionality is limited to linguistic analysis and output formatting.