Integrate feedback into model evaluation with sympy-based convexity proofs.
npx skills add https://github.com/lofibrainwav/AFO_Kingdom --skill ml-metacognition
Please help me install this Agent Skill. Skill: ml-metacognition Source: https://github.com/lofibrainwav/AFO_Kingdom/tree/main/skills/ml-metacognition Command: npx skills add https://github.com/lofibrainwav/AFO_Kingdom --skill ml-metacognition
This Skill enhances machine-learning model metacognition: a feedback loop with convexity proofs to improve self-reflection over time.
result = await metacognition.run(input_batch)
High-intent search queries and answers about installing and using this skill.
Self-reflection optimization uses feedback integration loops with convexity proofs to enable models to analyze their own performance and iteratively improve. This Skill applies symbolic analysis via sympy and second-derivative optimization to achieve measurable convergence gains within 10 iterations.
Convexity proof is a mathematical justification—generated via sympy—that guarantees an optimization landscape has no local minima, ensuring your model's improvement strategy converges reliably. This Skill provides symbolic proofs to validate that your feedback-driven adjustments move toward better performance.
Yes. Second-derivative optimization leverages curvature information to guide more precise parameter updates than first-order methods. This Skill integrates second-derivative tuning into its metacognitive feedback loop for accelerated performance gains.
Feed performance metrics and user feedback into the metacognition pipeline using `await metacognition.run(input_batch)`. The Skill processes this feedback through convexity-validated optimization to produce refined model behavior over successive iterations.
Yes. This Skill targets adaptive systems requiring continuous-improvement pipelines and model evaluation loops. Its 10-iteration convergence design and symbolic validation make it suitable for systems that must tune behavior based on live feedback.
Convexity assumptions hold for well-formed objective landscapes but may not apply to highly non-convex problem spaces. This Skill provides sympy-based proofs to confirm convexity in your specific context before relying on convergence guarantees.
OpenSenseNovaAutomates KPI validation and ranking in large Excel datasets using Python scripts.
KentoShimizuDetect data drift, concept drift, and quality degradation in production ML pipelines.
parcadeiGuides users to appropriate math tools with concrete command examples for SymPy, Z3, NumPy, SciPy, mpmath, and visualization tools.
ybbms777Reviews technical plans to flag scope misalignment and unjustified complexity.
