obs-create-filter
OBS用のLuaフィルタープラグインを実装する。シェーダーを使った映像エフェクト(ぼかし、色調変更、歪み、モザイク等)をLuaスクリプトとして作成。「フィルター追加」「新しいフィルターを作りたい」「〇〇エフェクトを実装して」といったリクエストで使用。Luaスクリプト、シェーダーコード、READMEの全てを実装する。
OBS用のLuaフィルタープラグインを実装する。シェーダーを使った映像エフェクト(ぼかし、色調変更、歪み、モザイク等)をLuaスクリプトとして作成。「フィルター追加」「新しいフィルターを作りたい」「〇〇エフェクトを実装して」といったリクエストで使用。Luaスクリプト、シェーダーコード、READMEの全てを実装する。
Serena MCPを使った実装作業フロー。コード実装/修正タスク時に自動適用。メモリ管理とシンボルレベル操作を含む。
This skill should be used when migrating features from src.legacy/ to the new kernel implementation or removing legacy code after reaching feature parity. Use for systematic legacy code removal, updating FEATURE_COMPARISON.md, verifying feature equivalence, and ensuring safe code retirement.
Implement memory-safe programming with RAII, ownership, smart pointers, and resource management across Rust, C++, and C. Use when writing safe systems code, managing resources, or preventing memory bugs.
Guides optimal Linear operations usage with caching, performance patterns, and error handling. Auto-activates when implementing CCPM commands that interact with Linear. Prevents usage of non-existent Linear MCP tools.
OS kernel research specialist. Use when researching operating system best practices, comparing implementations to Linux/FreeBSD/XNU, evaluating kernel design patterns, or ensuring Breenix follows production kernel conventions.
Master Julia 1.10+ with modern features, performance optimization, multiple dispatch, and production-ready practices. Expert in the Julia ecosystem including package management, scientific computing, and high-performance numerical code. Use PROACTIVELY for Julia development, optimization, or advanced Julia patterns.
Building DuckDB loadable extensions with CMake, FetchContent, and proper metadata handling
Implements functions following project conventions. Applies data-first parameter order, currying patterns with *On and *With variants, and consistent universal operation names.
Use the decomp-permuter to automatically find C code variations that match target assembly. Useful when stuck at 99%+ match with stubborn register allocation issues. Invoked with /decomp-permuter <function_name> <scratch_slug> or when manual matching attempts are exhausted.
PROHIBITS placeholder code, default values that mask missing data, and silent failures. Enforces fail-fast with loud errors. Use when implementing ANY function or data structure.
Expert in optimization methods covering linear programming, convex optimization, gradient methods, and constrained optimization
Generate optimized scripts that utilize the specific hardware (cores, GPU, OS) of the execution environment.
modules/* の core と std の依存境界を守る依頼で使う。core は no_std のみに依存し、std は std/tokio などに依存できる。テストコードは例外。
Build Vela RTOS (NuttX-based) with automatic detection of NuttX and Vela-specific targets. Supports CMake+Ninja, Makefile, and Vela envsetup build system (lunch + m).
Hot-reloadable Flecs modules as Rust dylibs. Covers module architecture, component vs system modules, and inter-module dependencies.
Gradient-based approximation to activation patching for scalable circuit analysis. Use when activation patching is too slow or when analyzing many components simultaneously.
Explore how to implement a new SystemVerilog feature in the Lyra compiler. Use when investigating what changes are needed across the compilation pipeline.
Hasktorch type-safe tensor operations with categorical structure preservation. Use when implementing type-safe deep learning in Haskell, leveraging dependent types for tensor shape verification, applying categorical abstractions to neural network design, or building formally verified ML pipelines with strong type guarantees.
Delegate complex tasks to sub-agents for parallel autonomous work. Use when GPU kernel optimization, numerical correctness verification, performance profiling, or long-running validation would benefit from focused independent execution.