Marketplace
Find the right skill for the job.
Browse the full catalog through outcome-first channels, technical facets, rating filters, and server-side pagination built for a large public marketplace.
hugging-face-model-trainer
This skill should be used when users want to train or fine-tune language models using TRL (Transformer Reinforcement Learning) on Hugging Face Jobs infrastructure. Covers SFT, DPO, GRPO and reward modeling training methods, plus GGUF conversion for local deployment. Includes guidance on the TRL Jobs package, UV scripts with PEP 723 format, dataset preparation and validation, hardware selection, cost estimation, Trackio monitoring, Hub authentication, and model persistence. Should be invoked for tasks involving cloud GPU training, GGUF conversion, or when users mention training on Hugging Face Jobs without local GPU setup.
vercel-deploy
Deploy applications and websites to Vercel. Use this skill when the user requests deployment actions such as "Deploy my app", "Deploy this to production", "Create a preview deployment", "Deploy and give me the link", or "Push this live". No authentication required - returns preview URL and claimable deployment link.
stride-analysis-patterns
Apply STRIDE methodology to systematically identify threats. Use when analyzing system security, conducting threat modeling sessions, or creating security documentation.
create-cli-e2e
Write end-to-end tests for CLI commands using the Docker-based test framework in ts/e2e-tests/cli/.
winapp-cli
Windows App Development CLI (winapp) for building, packaging, and deploying Windows applications. Use when asked to initialize Windows app projects, create MSIX packages, generate AppxManifest.xml, manage development certificates, add package identity for debugging, sign packages, publish to the Microsoft Store, create external catalogs, or access Windows SDK build tools. Supports .NET (csproj), C++, Electron, Rust, Tauri, and cross-platform frameworks targeting Windows.
railway-projects
List, switch, and configure Railway projects. Use when user wants to list all projects, switch projects, rename a project, enable/disable PR deploys, make a project public/private, or modify project settings.
persona-it-admin
Administer IT — monitor security and configure Workspace.
gitnexus-exploring
Use when the user asks how code works, wants to understand architecture, trace execution flows, or explore unfamiliar parts of the codebase. Examples: "How does X work?", "What calls this function?", "Show me the auth flow"
compliance
Compliance expert for SOC 2, GDPR, HIPAA, PCI-DSS, and security frameworks
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance
helm
Helm chart expert for Kubernetes package management, templating, and dependency management
mcp-apps-builder
**MANDATORY for ALL MCP server work** - mcp-use framework best practices and patterns. **READ THIS FIRST** before any MCP server work, including: - Creating new MCP servers - Modifying existing MCP servers (adding/updating tools, resources, prompts, widgets) - Debugging MCP server issues or errors - Reviewing MCP server code for quality, security, or performance - Answering questions about MCP development or mcp-use patterns - Making ANY changes to server.tool(), server.resource(), server.prompt(), or widgets This skill contains critical architecture decisions, security patterns, and common pitfalls. Always consult the relevant reference files BEFORE implementing MCP features.
serving-llms-vllm
Serves LLMs with high throughput using vLLM's PagedAttention and continuous batching. Use when deploying production LLM APIs, optimizing inference latency/throughput, or serving models with limited GPU memory. Supports OpenAI-compatible endpoints, quantization (GPTQ/AWQ/FP8), and tensor parallelism.
migrate-to-vinext
Migrates Next.js projects to vinext (Vite-based Next.js reimplementation). Load when asked to migrate, convert, or switch from Next.js to vinext. Handles compatibility scanning, package replacement, Vite config generation, ESM conversion, and deployment setup (Cloudflare Workers natively, other platforms via Nitro).
context-engine
Loads and manages company context for all C-suite advisor skills. Reads ~/.claude/company-context.md, detects stale context (>90 days), enriches context during conversations, and enforces privacy/anonymization rules before external API calls.
ci-cd-pipeline-builder
CI/CD Pipeline Builder
atlassian-admin
Atlassian Administrator for managing and organizing Atlassian products (Jira, Confluence, Bitbucket, Trello), users, permissions, security, integrations, system configuration, and org-wide governance. Use when asked to add users to Jira, change Confluence permissions, configure access control, update admin settings, manage Atlassian groups, set up SSO, install marketplace apps, review security policies, or handle any org-wide Atlassian administration task.
saas-scaffolder
Generates complete, production-ready SaaS project boilerplate including authentication, database schemas, billing integration, API routes, and a working dashboard using Next.js 14+ App Router, TypeScript, Tailwind CSS, shadcn/ui, Drizzle ORM, and Stripe. Use when the user wants to create a new SaaS app, start a subscription-based web project, scaffold a Next.js application, or mentions terms like starter template, boilerplate, new project, or wiring up auth and payments.
cs-workspace-admin
Google Workspace administration agent using the gws CLI. Orchestrates workspace setup, Gmail/Drive/Sheets/Calendar automation, security audits, and recipe execution. Spawn when users need Google Workspace automation, gws CLI help, or workspace administration.
torchforge-rl-training
Provides guidance for PyTorch-native agentic RL using torchforge, Meta's library separating infra from algorithms. Use when you want clean RL abstractions, easy algorithm experimentation, or scalable training with Monarch and TorchTitan.
gguf-quantization
GGUF format and llama.cpp quantization for efficient CPU/GPU inference. Use when deploying models on consumer hardware, Apple Silicon, or when needing flexible quantization from 2-8 bit without GPU requirements.
speculative-decoding
Accelerate LLM inference using speculative decoding, Medusa multiple heads, and lookahead decoding techniques. Use when optimizing inference speed (1.5-3.6× speedup), reducing latency for real-time applications, or deploying models with limited compute. Covers draft models, tree-based attention, Jacobi iteration, parallel token generation, and production deployment strategies.
gptq
Post-training 4-bit quantization for LLMs with minimal accuracy loss. Use for deploying large models (70B, 405B) on consumer GPUs, when you need 4× memory reduction with <2% perplexity degradation, or for faster inference (3-4× speedup) vs FP16. Integrates with transformers and PEFT for QLoRA fine-tuning.
peon-ping-rename
Rename the current Claude session for peon-ping notifications and terminal tab title. Use when user wants to give this session a custom name like "/peon-ping-rename Auth Refactor". Call with no argument to reset to auto-detect.