agency-terminal-integration-specialist
Terminal emulation, text rendering optimization, and SwiftTerm integration for modern Swift applications
Terminal emulation, text rendering optimization, and SwiftTerm integration for modern Swift applications
Bit-level optimization patterns for succinct data structures. Use when optimizing rank/select, popcount, or balanced parentheses operations. Triggers on terms like "rank", "select", "popcount", "bit manipulation", "lookup table", "optimization".
Modern C++ (C++23/C++20) development specialist covering RAII, smart pointers, concepts, ranges, modules, and CMake. Use when developing high-performance applications, games, system software, or embedded systems.
Optimize Ollama configuration for maximum performance on the current machine. Use when asked to "optimize Ollama", "configure Ollama", "speed up Ollama", "tune LLM performance", "setup local LLM", "fix Ollama performance", "Ollama running slow", or when users want to maximize inference speed, reduce memory usage, or select appropriate models for their hardware. Analyzes system hardware (GPU, RAM, CPU) and provides tailored recommendations.
Hardware-agnostic quantum ML framework with automatic differentiation. Use when training quantum circuits via gradients, building hybrid quantum-classical models, or needing device portability across IBM/Google/Rigetti/IonQ. Best for variational algorithms (VQE, QAOA), quantum neural networks, and integration with PyTorch/JAX/TensorFlow. For hardware-specific optimizations use qiskit (IBM) or cirq (Google); for open quantum systems use qutip.
Use when reading or writing Zig files (.zig, build.zig, build.zig.zon).
Plan and implement Trieste-based compiler passes and AST transformations for rego-cpp. Use when: adding new compiler passes, modifying AST structure, implementing new Rego language features, debugging pass failures, working with well-formedness definitions, or performing any multi-step implementation that touches the Trieste pass pipeline. Includes the multi-planner approach for complex features.
Designs, models, and implements Kotlin compiler extensions using K2/FIR and IR. Guides modifications to SpektGenerator (IR), ProxyGenerator (IR), and InspektChecker (FIR). Handles synthetic declaration generation, FIR status/supertype transformations, and IR backend lowerings. Use when implementing reflection features, fixing plugin bugs, or engineering compiler diagnostics.
Convert Claude Code skills to work on OpenAI Codex, Google Gemini CLI, Google Antigravity, and Cursor. Analyzes platform-specific features, generates target files (openai.yaml, AGENTS.md, GEMINI.md, .mdc rules), adapts frontmatter, converts MCP config, and produces compatibility reports. Use when user says "convert skill", "port skill", "multi-platform", "skill for codex", "skill for gemini", "skill for antigravity", "skill for cursor", "cross-platform skill", "convert to codex", "convert to gemini", "convert to antigravity", or "convert to cursor".
Integrate existing Fragno fragments into applications: install fragment packages, configure server instances (and database adapters if required), mount server handlers for each framework, create client-side integrations, and use hooks/composables. Use when asked to wire a fragment into the user's application.
Fix "Function declarations are not allowed inside blocks in strict mode when targeting ES5" in TypeScript files. Use when linter configs or TS compiler API code fail with this error.
Research and explain GPU-driven rendering techniques, find academic papers on graphics algorithms (APV, Spherical Harmonics, BVH), explain complex rendering concepts, and bridge theory to wgpu implementation for your learning project
Validate glTF files against your loader, identify missing features for each phase of compatibility, debug loading failures, and guide your 5-phase glTF progression from simple to complex models
Review Rust code for type safety, validate GPU memory layouts (bytemuck, repr(C), alignment), suggest idiomatic patterns, catch GPU-specific safety issues, and help with refactoring during buffer consolidation
Use when modifying python/src/lib.rs (PyO3 bindings), python/pegaflow/connector/ (vLLM KV connector), python/pegaflow/sglang/ (SGLang radix cache), .pyi type stubs, or building with maturin.
Multi-agent orchestration framework for Claude Code. Automatically delegates tasks to cheaper, faster sub-agents (Haiku 4.5, Sonnet 4.6) while maintaining Opus-level quality through verification. Use when working on any coding task — Hydra activates automatically to route file exploration, test running, documentation, code writing, debugging, security scanning, and git operations to the optimal agent. Saves ~50% on API costs.
Multi-agent orchestration framework for Claude Code. Automatically delegates tasks to cheaper, faster sub-agents (Haiku 4.5, Sonnet 4.6) while maintaining Opus-level quality through verification. Use when working on any coding task — Hydra activates automatically to route file exploration, test running, documentation, code writing, debugging, security scanning, and git operations to the optimal agent. Saves ~50% on API costs.
Improve code structure and readability.
This skill should be used when working with Shadertoy shaders, GLSL fragment shaders, or creating procedural graphics for the web. Use when writing .glsl files, implementing visual effects, creating generative art, or working with WebGL shader code. This skill provides GLSL ES syntax reference, common shader patterns, and Shadertoy-specific conventions.
Add or refactor a first-class Sparse-vLLM sparse method alongside vanilla, SnapKV, OmniKV, QuEST, and DeltaKV. Use when Codex needs to introduce a new `vllm_sparse_method`, move method logic out of `attention.py` or `utils/`, add method-specific cache metadata or decode-time view building, wire config and registration, and preserve the repo's cache-manager-first architecture.
Formulates problems for execution with ado by creating discoveryspace and operation YAML files. Guides through experiment selection, space creation, validation, operation configuration, and parameterization. Use when the user wants to create discoveryspace or operation YAML files, configure experiments, set up entity spaces, or formulate research, benchmarking or search problems.