Performance

kennedy-mechanical-sympathy

by copyleftdev

Write Go code in the style of Bill Kennedy, author of Go in Action. Emphasizes mechanical sympathy, data-oriented design, and understanding how Go code executes. Use when writing performance-critical Go or when teaching Go fundamentals.

satori

by satori-sh

Persistent long term memory for for continuity in ai sessions between providers and codegen tools.

flutter-expert

by Olino3

"Cross-platform mobile development with Flutter/Dart. Build performant, maintainable Flutter apps with proper widget architecture, state management, platform channels, and testing patterns."

role-reviewer

by teodevlor

Activate Code Reviewer mode for code review and quality assurance. Use when reviewing code for bugs, security issues, or optimization opportunities.

hreng-perf-diagnose

by clous-ai

Use when the user wants to diagnose engineering performance issues (individual or team), distinguish systemic vs. individual patterns, and design data-driven interventions.

mech-interp

by Pranav-Karra-3301

Mechanistic interpretability skill for understanding neural network internals. Use when: (1) Working with TransformerLens, nnsight, or SAELens (2) Analyzing attention patterns, circuits, or features (3) Training or analyzing sparse autoencoders (SAEs) (4) Activation patching, logit lens, or direct logit attribution (5) Understanding model internals ("what is this head doing?") (6) Setting up a mech interp research project Triggers: "mech interp", "mechanistic interpretability", "TransformerLens", "SAE", "sparse autoencoder", "activation patching", "logit lens", "circuits", "features", "attention heads", "residual stream", "nnsight", "nnterp", "superposition", "polysemantic", "monosemantic", "ablation", "probing", "induction head"

memory-keeper

by CrimsonDevil333333

Copy and snapshot all important agent context (MEMORY.md, memory/*.md, AGENTS.md, SOUL.md, etc.) into a dedicated archive directory or repo. Use this skill when you want to back up your memories, context, or configuration files in preparation for maintenance, corruption recovery, or transferring to another host.

lighthouse

by Onnokh

Google Lighthouse CLI reference for auditing web performance, accessibility, SEO, and best practices. Use this skill when users need to analyze website performance, run audits, generate reports, or integrate Lighthouse into their workflow.

angular-code-review

by Olino3

Deep Angular code review of changed files using git diff analysis. Focuses on production quality, security vulnerabilities, performance bottlenecks, architectural issues, and subtle bugs in code changes.

create-agents

by Olino3

Design and build custom Claude Code agents with effective descriptions, tool access patterns, and delegation strategies. Guides users through agent architecture decisions, generates paired .md and .config.json files, and ensures compliance with The Forge agent conventions. Triggers: create agent, custom agent, build agent, agent description

todo-task-run

by gendosu

Execute tasks from TODO file - Generic task runner [/todo-task-run xxx]

Compiler & Kernel Fusion (torch.compile) Integration

by sovr610

This skill should be used when the user asks to "enable torch.compile", "add compilation to training", "kernel fusion", "TorchDynamo integration", "TorchInductor optimization", "reduce-overhead mode", "max-autotune mode", "fix graph breaks", "compile health check", "shape stabilization", "dynamic shapes for compile", "bucketing for torch.compile", "compile allowlist", "compile blocklist", "compile smoketest", "CUDA graphs for training", "maybe_compile wrapper", "debug recompiles", "TORCH_LOGS compile", "compile + DDP", "compile + FSDP", "torch.compiler.disable", or needs guidance on torch.compile integration, shape management, compilation debugging, or safe fallback patterns.

strategic-review

by kanghohyeong

This tool compares and analyzes multiple methodologies to reach a given goal and provides decision-making logic and rationale. It is triggered when a user says like "create a strategy," "establish a strategy,".

typescript-performance-review

by bromanko

This skill should be used when the user asks to "review performance", "optimize TypeScript", "TypeScript performance", "performance audit", "find bottlenecks", "improve efficiency", or wants analysis of TypeScript code performance focusing on runtime hotspots, rendering efficiency, and data handling.

remotion-editor

by rayBlock

Best practices for building video editors and interactive tools with Remotion

cpp

by Olino3

Modern C++ (C++17/20/23) development and best practices

breadth-of-thought

by kimasplund

Exhaustive solution space exploration. Use when you need ALL viable options (not just the best), solution space is unknown, or you can't afford to miss alternatives.

generate-more-skills-with-claude

by Olino3

Forge is a marketplace for a Claude Code Plugins

feature-generator

by karchtho

code generation script writing implementation production-ready features

architecture-design

by Olino3

"Design software architectures with appropriate patterns for scale, maintainability, and team structure. Covers layered, hexagonal, event-driven, CQRS, and modular monolith architectures. Produces architecture decision records, component diagrams, and dependency maps. Prevents over-engineering, premature distribution, and architectural drift."

tresjs-best-practices

by sshine

Best practices for TresJS - Building 3D experiences with Vue 3 and Three.js

data-engineering-storage-remote-access-integrations-pandas

by legout

"Reading and writing data with Pandas from/to cloud storage (S3, GCS, Azure) using fsspec and PyArrow filesystems."

Performance Architect

by Alpizar28

Arquitecto senior de performance y eficiencia, especializado en sistemas de reservas, concurrencia y escalabilidad estructural.

DubaiMatrixASI

by jokerofcassinos