DevOps

Provides guidance for performing causal interventions on PyTorch models using pyvene's declarative intervention framework. Use when conducting causal tracing, activation patching, interchange intervention training, or testing causal hypotheses about model behavior.

Activation-aware weight quantization for 4-bit LLM compression with 3x speedup and minimal accuracy loss. Use when deploying large models (7B-70B) on limited GPU memory, when you need faster inference than GPTQ with better accuracy preservation, or for instruction-tuned and multimodal models. MLSys 2024 Best Paper Award winner.

Autonomous AI agent platform for building and deploying continuous agents. Use when creating visual workflow agents, deploying persistent autonomous agents, or building complex multi-step AI automation systems.

Reserved and on-demand GPU cloud instances for ML training and inference. Use when you need dedicated GPU instances with simple SSH access, persistent filesystems, or high-performance multi-node clusters for large-scale training.

ONVIF device security scanner for testing authentication and brute-forcing credentials. Use when you need to assess security of IP cameras or ONVIF-enabled devices.

GitHub workflow automation using `gh` CLI. Use when creating PRs, reviewing code, managing issues, auto-replying to fixed issues, adding comments, assigning users, managing labels, merging PRs, or checking CI status. Includes auto-reply script and Vietnamese templates.

Transforms conversations and discussions into structured documentation pages in Notion. Captures insights, decisions, and knowledge from chat context, formats appropriately, and saves to wikis or databases with proper organization and linking for easy discovery.

Searches across your Notion workspace, synthesizes findings from multiple pages, and creates comprehensive research documentation saved as new Notion pages. Turns scattered information into structured reports with proper citations and actionable insights.

Performs comprehensive code reviews for Bitwarden iOS projects, verifying architecture compliance, style guidelines, compilation safety, test coverage, and security requirements. Use when reviewing pull requests, checking commits, analyzing code changes, verifying Bitwarden coding standards, evaluating unidirectional data flow pattern, checking services container dependency injection usage, reviewing security implementations, or assessing test coverage. Automatically invoked by CI pipeline or manually for interactive code reviews.

Send system notifications to specific Clawdis nodes (macOS computers) via the Gateway and CLI. Use when you need to alert a person or confirm a remote action on a particular machine, or when an agent must push a notification to another computer.

Use the mcporter CLI to list, configure, auth, and call MCP servers/tools directly (HTTP or stdio), including ad-hoc servers, config edits, and CLI/type generation.

Use when creating new skills, editing existing skills, or verifying skills work before deployment

Comprehensive testing and validation strategies for spec-driven development. Learn phase-specific validation techniques, quality gates, and testing approaches to ensure high-quality implementation.

Convert technical designs into actionable, sequenced implementation tasks. Create clear coding tasks that enable incremental progress, respect dependencies, and provide a roadmap for systematic feature development.

Create comprehensive steering documents for development projects. Generates project-specific standards, git workflows, and technology guidelines in .kiro/steering/ directory.

Estimate complexity, effort, and risks for JIRA tickets, features, or projects. Generates structured reports with time estimates, dependencies, risk analysis, and known unknowns. Use when user asks to "estimate", "size", or "analyze complexity" of work items.

Async via gask, end turn immediately; use only when user explicitly delegates to Gemini (ask/@gemini/let gemini/review); NOT for questions about Gemini itself.

Async via cask, end turn immediately; use only when user explicitly delegates to Codex (ask/@codex/let codex/review); NOT for questions about Codex itself.

Allows to interact with web pages by performing actions such as clicking buttons, filling out forms, and navigating links. It works by remote controlling Google Chrome or Chromium browsers using the Chrome DevTools Protocol (CDP). When Claude needs to browse the web, it can use this skill to do so.

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).