Extract recurring patterns and calibrate confidence from self-model hypotheses.
npx skills add https://github.com/zkysar1/Claude-Mind --skill reflect-on-self
Please help me install this Agent Skill. Skill: reflect-on-self Source: https://github.com/zkysar1/Claude-Mind/tree/main/.claude/skills/reflect-on-self Command: npx skills add https://github.com/zkysar1/Claude-Mind --skill reflect-on-self
This sub-skill enables automated self-model reflection to audit reasoning, extract recurring patterns, and synthesize strategic insights from hypotheses, helping autonomous systems align with long-term goals.
Activate the /reflect-on-self workflow to begin extracting patterns and calibrating your strategic self-model.
High-intent search queries and answers about installing and using this skill.
Self-model reflection is a mechanism where autonomous agents audit their own reasoning to improve decision-making. It identifies recurring hypotheses and extracts patterns to synthesize strategic insights, aligning autonomous systems with long-term goals.
To extract patterns from resolved hypotheses, activate the pattern extraction mode within the reflection workflow. This process analyzes resolved hypotheses to build Level 1/2 self-models and stores the discovered patterns directly into the memory tree for knowledge-base reuse.
Calibration analysis for confidence assessment operates by evaluating historical hypotheses against actual outcomes. This calibration mode checks and adjusts confidence levels, ensuring that future strategic reasoning and decision-making are accurately calibrated.
Yes, you can use self-reflection to synthesize strategic insights for long-term goal alignment. The automated self-model reflection process audits reasoning and extracts recurring patterns from hypotheses to ensure autonomous systems remain aligned with long-term goals.
Yes, this pattern extraction approach requires a modular memory tree architecture. It fulfills specific requirements for modular knowledge updates and pattern storage within the memory tree to successfully integrate discovered strategies into knowledge graphs.
Fr-e-dAnalyze project directory structures to generate architectural summaries.
arthrodApply meta-cognitive reasoning frameworks to improve AI response quality.
an8079Implement LangChain agents, chains, memory, and RAG systems for LLM applications.
QredenceManage AgenticFleet development sessions with dual memory and auto-learning.
