GitHub
precision-protocol
Protocol untuk meningkatkan kecerdasan, presisi, dan keamanan dalam coding dan debugging.
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
sdd-design-perf
Design bundle strategy, lazy loading, and render optimization. Use when: sdd-design assigns Performance Strategy section. Triggers: "performance design", "bundle size", "lazy loading", "optimization"
GitHub
opencode-zen
Invoke the 'opencode' CLI in headless mode for AI-powered code analysis, reviews, and second opinions. Use when you need a different AI perspective, the user mentions opencode, or requests batch code analysis.
GitHub
ultra-performance-resilience-specialist
Experto en optimización de bajo nivel. Su misión es garantizar 60 FPS constantes, gestión de memoria eficiente mediante Isolates y disponibilidad offline total.
GitHub
rimitive-adapter
Create custom adapters for Rimitive view primitives. Use when building renderers for Canvas, WebGL, terminal, native platforms, or any tree-based target.
GitHub
rust-engineer
Use when building Rust applications requiring memory safety, systems programming, or zero-cost abstractions. Invoke for ownership patterns, lifetimes, traits, async/await with tokio. Keywords: Rust, ownership,...
GitHub
ffi-bindings
Create FFI bindings between Lean 4 and C code. Use when working with foreign functions, native libraries, Metal, or system APIs.
GitHub
collimator-optics
Use profunctor optics from the Collimator library for Lean 4. Use when working with lenses, prisms, traversals, or nested data access.
GitHub
ffi-pyo3-maturin
Build or modify the Rust↔Python FFI using PyO3+maturin. Use for binding builds, smoke tests, and boundary validation workflow.
GitHub
implementing-python
Implements concise, streamlined Python code matching exact architect specifications. Use when writing Python code, creating modules, or when the user asks to implement features in Python.
GitHub
new-provider
Scaffold a new model provider for obot-tools
GitHub
c-timelog-engineering
High-performance C development for data-intensive systems, with explicit emphasis on time-indexed / log-structured in-memory engines (e.g., Timelog-class designs). Use when building advanced data structures, al...
GitHub
cpu-mode-assertions-torch
Assert CPU-only runtime inside a container using PyTorch (torch.cuda.is_available()==False) and optional env var checks. Use to prevent accidental GPU execution during CPU smoke tests.
GitHub
iterate
Autonomous TDD implementation workflow with phase gates
GitHub
load-anomaly-guard
Detects unsafe spikes in training load and emits SafetyFlags with conservative adjustments.
GitHub
performance-engineer
Optimize application performance including build times, runtime speed, bundle size and resource usage. Use when addressing performance issues, implementing caching strategies, or optimizing rendering.
GitHub
performance-tuner
Specialized in speed and resource optimization for Gravito. Trigger this for query profiling, caching strategies, or frontend performance audits.
GitHub
binary-parsing-mixed-endian
Parsing binary files with mixed endianness and variable-length records in Python.
GitHub
ml-optimization
Optimizes TensorFlow.js WebGPU backend, WebLLM offline inference, and implements memory safety for heavy ML models
GitHub
maverick-rust-performance
Rust performance optimization and zero-cost abstractions
GitHub
maverick-rust-unsafe
Rust unsafe code, FFI, and safety invariants
GitHub
extensions
Generic extension methods for strings, collections, DateTime, decimals, and entities.
GitHub
extensions
Generic extension methods for strings, collections, DateTime, decimals, and entities.
GitHub
operators-edge
Runs the Operator's Edge loop (State, Proof, Gates + adaptation checks). Use for any coding task, debugging, refactor, or system change.
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.