Walk this project's standing positions and test whether any of their reasons have expired, then report to the human.
Summarize the current state of a Clayrune project — open backlog items, recent agent runs, active hiveminds, scheduled jobs, registered processes.
Search Clayrune for skills that might help the current task — including skills authored in OTHER projects that your session doesn't normally see.
Run as the autonomous STEWARD of a Clayrune project — a fire-and-forget agent that sets its own next goal, does reversible work unattended, asks before anything irreversible, and…
Latin as a style layer (拉丁风格层) - three families that must never be blended into one "Latin" setting: Afro-Cuban, Brazilian and Caribbean.
Multi-criteria decision analysis skill with AHP, TOPSIS, and weighted scoring methods.
Make Commits Great Again — превращает обычное сообщение коммита в драматичный твит в стиле Дональда Трампа (русский язык, КАПС, восклицания, рубленые фразы, самовосхваление).
Offload one scoped coding task to mcgyvr, a CLI that runs it on deterministic tools, local models or API models and keeps only what its deterministic gate accepts.
Execute mcloud authentication and context commands: login, logout, whoami, use, version, and signup. Use when setting up the CLI, switching accounts, verifying auth state, setting…
Execute mcloud environments commands to list, get, create, delete, redeploy, or trigger builds for Cloud environments.
Execute mcloud organizations commands to list or get Cloud organizations. Use when discovering organizations, resolving organization IDs by name, or retrieving organization…
Execute mcloud projects commands to list, get, or delete Cloud projects. Use when discovering projects, resolving project handles by name, or retrieving project details including…
Execute mcloud variables commands to list and get environment variables for a Cloud environment. Use when inspecting, reading, or exporting environment variables.
Coding specialist for COMAP MCM/ICM Problem C (C题数据处理与建模落地). Use when you need to implement reproducible data pipelines, feature engineering, model training/validation, bootstrap…
Investigate a failing GitHub Actions run or job and create a GitHub issue for the failure.
Linting and formatting for Megatron-LM. Covers running autoformat.sh, tools (ruff, black, isort, pylint, mypy), and code style rules.
How to launch distributed Megatron-LM training jobs on a SLURM cluster. Covers a minimal sbatch skeleton, environment-variable setup for torch.distributed.run, CUDA_DEVIC — from…
Split a PR into multiple PRs to reduce the number of required CODEOWNERS reviewer groups.
Use Model Context Protocol servers to access external tools and data sources. Enable AI agents to discover and execute tools from configured MCP servers (legal databases — from…
Install an MCP server template from dotforge into a project or global Claude Code config with a single command.
Configure safe agent behavior around PlanetScale MCP, Insights, schema recommendations, and repository work without autonomous production mutation.
Use when integrating or optimizing Model Context Protocol (MCP) servers and clients. Keywords: MCP, Model Context Protocol, tool discovery, lazy loading, sampling, resource…
Comprehensive verification checklists for MCP Apps. Tests with basic-host reference, validates handler-before-connect, text fallback, resource URI linking, single-file bundling,…
**MANDATORY for ALL MCP server work** - mcp-use framework best practices and patterns. — from CopilotKit/CopilotKit
**MANDATORY for ALL MCP server work** - mcp-use framework best practices and patterns. — from bg-szy/TOP-SKILLS
Authenticate and authorise access to a remote MCP server so tools act as the right user with the least necessary privilege.
Create MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools.
Guide for creating MCP (Model Context Protocol) servers. Use this when building integrations with external services, creating new MCP servers, or connecting Claude to APIs.
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools.
Erstellt MCP-Server (FastMCP/TS-SDK). Trigger: MCP-Server/externe API-Integration.
Generate MCP capability declarations from tool and resource inventory with proper versioning and feature flags.
Composite skill — full MCP server lifecycle audit and repair. Chains mcp-audit (usage stats) → mcp-health (live readiness) → mcp-doctor (fix broken servers) → suggest mcp-builder…
Use when choosing, recommending, or wiring MCP servers for a project's .mcp.json. Curated list of strategic MCP servers with safe configuration (env placeholders, scoping).
MCP (Model Context Protocol) server patterns with categorical tool composition and typed context protocols.
Validate MCP configuration and suggest improvements. Use when MCP servers fail to load, after editing .mcp.json, or when the user runs /mcp-check.
Detects MCP tool failure patterns and trips a circuit breaker to stop cascading retries. Proposes fallback alternatives and resets when the tool recovers.
Use MCP servers on-demand via the mcp CLI tool - discover tools, resources, and prompts without polluting context with pre-loaded MCP integrations
Connect MCP servers into an application with lifecycle management, capability negotiation, and graceful degradation when a server is unavailable.
Expert guide for the AI Agent to dynamically orchestrate and consume external MCP (Model Context Protocol) servers, giving it real-time superpowers over databases, GitHub, Slack,…
Optimize multi-tool workflow chains via MCP server integration for processing large datasets, files, or complex pipelines.
Configure MCP (Model Context Protocol) servers for Claude Code. Manage MCP servers at user or project scope with best practices to avoid context pollution.
Synchronisiert MCP-Server zwischen den Agent-Apps Claude Code und Claude Desktop auf demselben Rechner.
Configure the LaunchDarkly hosted MCP server during onboarding. Use when the parent LaunchDarkly onboarding skill reaches Step 4 (MCP).
Audits all connected MCP servers: auth type (OAuth vs static token), token expiry, available tools, and connection health.
Provides a Model Context Protocol (MCP) server interface to the skills library, allowing any MCP-compliant agent (e.g. Claude Desktop) to invoke Antigravity skills as native tools.
Use product connectors (MCP under the hood) and auth gateways without stuffing every action schema into context.
Keep tool results small enough that an agent can hold what matters, through pagination, projection, and summarisation at the server. Use when tool output floods the context window.
Integración con Context7 MCP Server para obtener documentación actualizada de librerías.
Coordinates MCP server selection and multi-server orchestration with parallel/sequential modes and fallback strategies for complex multi-domain tasks.
Skills for accessing and searching docs in DeepWiki/GitHub’s public code repositories can help users understand open-source project source codes, and users can also ask questions…
Build or update MCP server/client integrations for VMark. Use when configuring MCP servers, adding MCP tools, or updating MCP-related docs and settings.
Model Context Protocol development expert. Use when creating MCP servers, clients, or tools that enable AI agents to interact with external systems, APIs, and development…
MCP server development including tool design, resource endpoints, prompt templates, and transport configuration
Diagnose and fix MCP connectivity, authentication, and configuration failures in OpenCode
Discover and connect to MCP servers automatically. Browse available tools and register new server endpoints. Use when working with mcp discover.
Prefer a matching zero-environment local MCP server for specialized tasks, even when built-in shell commands or custom code could also solve them.
Use when working with the MCP server endpoint, JSON-RPC handling, tool registry, authentication, or files in packages/mcp/
Explore and find API endpoints using MCP servers. Lists collections, searches for endpoints, extracts endpoint details.
Audit and configure enterprise-managed MCP authorization (EMA) for organizations using Okta and Claude Team/Enterprise.
Map application errors to MCP error codes with proper messages, error types, and recovery suggestions.