cuda-guide

Migrate an apollo-react canvas component from Emotion styled-components to apollo-wind Tailwind classes following the BaseNode reference migration patterns

Diagnose No Johns setup issues. Checks Python, Dolphin, ISO, arena connectivity, and common problems.

Acting as template repo maintainer: review proposals in `localdocs/proposals/` and optionally apply accepted ones to the upstream template.

Use this skill any time the user wants to work with Sandstorm agent stacks. This includes: creating, spinning up, or starting stacks; dispatching tasks or work to an inner Claude agent in a stack; checking stack status, task progress, or whether a task is done; viewing diffs, changes, or task output from a stack; pushing or publishing code changes from a stack to git; tearing down, cleaning up, or removing stacks; viewing container logs. Trigger whenever the user mentions 'stack' with a number or ID (like 'stack 1', 'stack 2', 'stack 3'), says 'sandstorm', refers to an 'isolated environment' for development, or asks to send work to an agent. Also trigger for multi-stack operations and any reference to agent workspaces. Do NOT trigger for general Docker, docker-compose authoring, CI/CD pipelines, or direct code editing unrelated to stacks.

Three.js game development. Use for 3D web games, WebGL rendering, game mechanics, physics integration, character controllers, camera systems, lighting, animations, and interactive 3D experiences in the browser.

Guide for defining and using Claude subagents effectively. Use when (1) creating new subagent types, (2) learning how to delegate work to specialized subagents, (3) improving subagent delegation prompts, (4) understanding subagent orchestration patterns, or (5) debugging ineffective subagent usage.

This skill helps you add new rules to the attgo-linter project.

Guides how to integrate the NNews NuGet package for consuming the NNews CMS API in a .NET 8 project. Use when the user wants to consume articles, categories, tags, images, or AI-powered content generation from the NNews API.

Transform Claude into an expert code reviewer following industry best practices.

Execution-oriented workflow for HyperParallel distributed operator development. Analyzes the operator, implements or updates code and tests.

Git Worktree 管理命令。提供 init、list、remove 三个子命令来管理项目 worktree。

TypeScript-first schema validation library with static type inference and runtime validation

Orchestrate Agent Teams for parallel multi-session collaboration. Use for research, implementation, review, and debug workflows requiring independent teammates.

Plans the next sprint with PM analysis, multi-agent technical table, and roadmap generation. Use to plan sprints, prioritize features, convene technical tables.

Expert knowledge for defining REST and WebSocket APIs with `schematic-define`. Use when creating or editing `RestApi`/`Endpoint` models, auth and env mappings, request or response shapes, and OpenAPI extension behavior that drives generated clients.

Create a git commit with a well-crafted message following project conventions

Implementa feature nel sistema di fatturazione italiana validando contro normativa fiscale. Usa per aggiungere calcoli IVA, ritenuta d'acconto, split payment, imposta di bollo, gestione fatture PA, regime forfettario, numerazione progressiva, note di credito, o qualsiasi logica che deve rispettare DPR 633/72, DPR 600/73, DPR 642/72. NON usare per bug fix tecnici, refactoring, o modifiche UI senza impatto fiscale.

This is an AI-first project: any contributor — human or model — should be able to land a change that respects the architecture without needing to read the whole codebase first. The rules below are che

Confidence-based model tier escalation for agent tasks. Defines when to escalate from Haiku to Sonnet to Opus, escalation signals, and the never-skip-tiers rule. Use when an agent fails or underperforms.

Improve the eval system quality -- add better cases, fix broken cases, improve the LLM judge, add new metrics, or refine pass/fail criteria based on eval run data. Use when the user wants to make the eval system itself better.

>

Meta-level analysis of plan vs execution to identify process improvements. Analyzes divergence patterns and suggests updates to CLAUDE.md, agents, and skills.

>-

'Vue 3 patterns with Clerk — composables (useAuth, useUser,

nextjs-performance

Parse and analyze CI failure logs from GitHub Actions to identify root causes across Go, TypeScript/Vue.js, and PHP stacks

Investigate a bug by exploring the codebase, find root cause, create a GitHub issue with a TDD fix plan. Use when a bug is reported, SLURM job fails, shape mismatch occurs, or any problem needs systematic investigation.

SoNash project context injected into agent definitions via skills: field

moomoo/Futu OpenD installation assistant. Use ONLY when user mentions moomoo, Futu, OpenD, futu-api, or moomoo-api. Automatically downloads and installs moomoo/Futu OpenD and upgrades Python SDK. Supports Windows, MacOS, Linux.

Run four phases in order. Each phase is conversational and inline — no

Use when adding a full-stack analytics/usage-tracking feature to a FastAPI + React project. Provides backend models, middleware, aggregation service, API routes, and a polished enterprise-grade React dashboard with charts, KPI cards, and user activity tables.

This skill identifies and prevents common testing anti-patterns that make test suites unreliable, slow, and difficult to maintain. It provides detection strategies and refactoring solutions for health

>

Run unit and integration tests

You are an expert technical writer creating comprehensive project documentation. Your goal is to write a README.md that is absurdly thorough—the kind of documentation you wish every project had.

Patterns for composing clean, production-ready Figma property panels with FigUI3.

Track bugs, QA, and fixes in .galdr/. For bug reports, issues, quality, fixes, QA workflows.

This skill enables parallel development by using git worktrees. Each worktree provides an isolated working directory with its own branch, allowing multiple agents to work on different features simulta

zero-skills

>

>

Common patterns for Kubernetes manifests in infra/k8s. Use when editing or adding K8s manifests, changing deployment config, adding env vars to ConfigMaps, or working with ArgoCD/Kustomize/SOPS.

>

Creates production-ready pull requests with automatically updated AGENTS.md and project docs. Use when the user asks to create a PR, make a PR, is ready to merge, has finished a feature and wants a PR, or says they're done for the day with changes to commit.

Update the tarkov.dev GraphQL schema and regenerate the Go client code

Used to supplement the data LLMs can use when answering questions by supplying them with custom data generated and managed by llama-index.

Use when finding files by name/path on Windows primary dev PC via voidtools Everything (es.exe); prefer scripts/es-find.ps1 with a capped -MaxCount. On Linux lab-op SSH use find/fd, not es.

As an expert technical writer and editor, your goal is to produce and refine documentation that is accurate, clear, consistent, and easy for users to understand. You must adhere to the documentation c

Generate structured test cases from requirements and specification documents using test model-based approach per ISO 29119-4.