GitHub
numerical-validation
Verify mathematical correctness and numerical accuracy after code changes
Skills IA tools framework internals
Découvrez les skills tools framework internals, comparez leurs dépôts et consultez leurs instructions.
Catégories: tools framework internals
tools framework internals Effacer les filtres
Explorer
GitHub
webgpu-canvas
WebGPU fundamentals for high-performance canvas rendering. Covers device initialization, buffer management, WGSL shaders, render pipelines, compute shaders, and web component integration. Use when building GPU-...
GitHub
pyomo
Expert in Pyomo mathematical optimization modeling in Python - use for optimization problems, linear/nonlinear programming, constraint programming, and dynamic optimization
GitHub
ebpf-attach-hook
Implement eBPF program attachment logic for various hooks (XDP, TC/tcx, netkit, kprobe, tracepoint, cgroup) with proper error handling, cleanup, and link management. Includes Go code using cilium/ebpf library....
GitHub
ebpf-packet-redirect
Implement packet redirection and routing in eBPF programs using bpf_redirect and bpf_redirect_neigh helpers. Includes source-based policy routing, map-based routing tables, load balancing, and CNF router patter...
GitHub
ebpf-packet-parser
Generate verifier-safe packet parsing logic for eBPF programs including bounds checking, header extraction (Ethernet, IPv4/IPv6, TCP/UDP, ICMP), protocol identification, and proper pointer arithmetic. Use when...
GitHub
full-stack-optimizer
Multi-agent orchestration for comprehensive frontend + backend improvements. Use when user requests "improve the app", "optimize functionality", "make it perfect", or "enhance the system". Deploys specialized a...
GitHub
ray
Expert in Apache Ray distributed computing. Use when converting Python code to Ray workloads, debugging Ray applications, optimizing Ray performance, or working with Ray Core, Ray Data, Ray Train, Ray Serve, or...
GitHub
k1-architecture
Deep understanding of K1.reinvented's compilation architecture, node system, and extension methodology. Teaches why graphs compile to C++ and how to extend the system without violating minimalism.
GitHub
dspy-basics
Core DSPy fundamentals for signature design, basic modules (Predict, ChainOfThought), and program composition patterns. Use when creating new signatures, building simple DSPy programs, or learning foundational...
GitHub
gem-integration
Skill especializado en integración de Gem Bundles compilados por Gem Builder Compiler en AGCCE v4.0. Permite configurar agentes MAS dinámicamente desde Gems versionados.
GitHub
deterministic-math-guidelines
Use when writing game logic code - ensures deterministic math operations across platforms
GitHub
dspy-optimization
DSPy optimizers (teleprompters), evaluation metrics, and optimization workflows. Use when compiling programs with BootstrapFewShot, KNNFewShot, MIPROv2, GEPA, or defining custom metrics.
GitHub
iterate-implementation
iterate on implementation based on user feedback
GitHub
corregir-graficos
Ejecuta 📚 SUBFASE 3A para errores gráficos - Corrección basada en ejemplos funcionales.
GitHub
grpo-rewards
Implement token-level rewards in TRL's GRPOTrainer. Use when modifying reward computation or debugging reward tensor shapes.
GitHub
sensorless-control
🚧 STUB - Sensorless FOC observer implementations and estimation algorithms
GitHub
control-algorithms
🚧 STUB - Common motor control algorithm implementations and patterns
GitHub
r3f-performance
Performance optimization techniques for R3F and Three.js
GitHub
shader-sdf
Signed Distance Functions for shader-based 3D primitives
GitHub
shader-development
GLSL shader creation process and patterns for R3F
GitHub
reference-chimerax-dev
ChimeraX bundle/extension development reference
GitHub
x07-ffi-c
Emit C output and a C header for embedding X07 in C/C++ via `x07 build --emit-c-header`.
GitHub
devops-mastery
Elite software engineering toolkit for building production-grade applications. Use when developing, debugging, optimizing, or deploying code—especially for API development, database design, performance tuning,...
Le classement utilise les étoiles du dépôt GitHub indexé. Plusieurs skills peuvent partager ce nombre : ce n’est ni un nombre d’installations ni une note de qualité.