local-finetune

Local Compositionality Gadget

Bootstrap skill loader for instance startup. Pulls fresh skills from plurigrid/asi and loads GF(3)-balanced startup triads. MUST run at beginning of every new instance.

LiveKit omni-modal continuous coaching with stick-breaking color selection,

Little Schemer Skill

Local approximation of nonlinear dynamics

Linear Logic Skill

Asymptotic behavior of trajectories (ω/α-limit sets)

Fuzzing with libFuzzer for finding vulnerabilities in code.

Fuzzing framework LibAFL for custom fuzzing campaigns.

Playful mutual ingression meets Leonid Levin's algorithmic bounds. Use for: playful exploration with theoretical guarantees, mutual ingression with convergence proofs, emergent solutions within complexity bounds, social computation meeting algorithmic optimality.

Leonid Levin''s algorithmic complexity meets playful mutual ingression. Use for: BB(n) prediction markets, Kolmogorov complexity rewards, WEV extraction from proof inefficiencies, Nash equilibrium between exploration (LEVITY) and convergence (LEVIN).

Draws 4 Tarot cards using os.urandom() to inject entropy into planning when prompts are vague or underspecified. Interprets the spread to guide next steps. Use when the user is nonchalant, feeling lucky, says 'let fate decide', makes Yu-Gi-Oh references ('heart of the cards'), demonstrates indifference about approach, or says 'try again' on a system with no changes. Also triggers on sufficiently ambiguous prompts where multiple approaches are equally valid.

GF(3)-balanced random walk through Lean proof states. Use when generating formal proof chains with parallel triad verification. Invokes 3 agents (Generator +1, Coordinator 0, Validator -1) to traverse proof space via prime geodesics.

Identifies high-quality leads for your product or service by analyzing

Latent-Latency Skill

Invariance principle for asymptotic stability

Layer 5: SDE-Based Learning Analysis via Langevin Dynamics

Lambda Calculus Skill

L-Space Skill: The Library of All Libraries

Coupled oscillators with sinusoidal coupling

RL training library for humanoid locomotion and manipulation built on MuJoCo and JAX. Provides PPO, AMP, and custom task abstractions for sim-to-real robotics policy training.

K-Scale Labs robotics skill collection - unified index for humanoid robot development, RL training, sim-to-real transfer, and deployment. Aggregates 9 specialized skills with GF(3) triadic organization.

Rust library for controlling actuators (Robstride servo motors) on K-Scale robots. CAN bus communication, position/velocity/torque control.