Skills
97,501 packaged capabilities and playbooks for agents. Install any of them with one command.
Agent workflows
Use when executing an engineering plan produced by gitnexus-plan (or a small, bounded task directly): implement step by step with GitNexus impact checks before every symbol edit, run tests from the plan’s scenarios, and gate every commit with detect_changes. Examples: “/gitnexus-work docs/plans/2026-07-11-gitnexus-plan-ingestion-retry.md”, “/gitnexus-work” (latest plan), “execute the plan”
Ask about and record decisions on substantive unresolved user choices in plans, product specifications, design, technical solutions, implementation, or release. Applies to scope, priorities, trade-offs, risks, acceptance, dependencies, visual direction, or release authorization that cannot be resolved from code, configuration, authoritative artifacts, or deterministic execution. It is not triggered automatically by a new phase or module.
Use when generating agent enforcement hooks for a repo — doc-coverage reminders from docs/, skill-drift and markdown-lint warnings, and the session preflight and delivery-gate hooks that check a session against its outcome contract. Installs into Claude Code and Codex hook configuration.
Use when an agent talks to anything outside its process: MCP server or client, A2A and agent cards, MCP Registry, an agent gateway, or delegated calls. Triggers: “MCP server” / “MCP-сервер,” “A2A,” “шлюз для агентов.” Not for one server's tool design (agent-harness) or skill construction (make-skill)
Run, read, and diagnose a skill's Caliper eval — its success rate over k attempts, whether it fires, and whether it beats the agent without it. Use when the user wants to run, validate, interpret, or compare a skill's eval, or write an .eval.yaml spec whose tasks they have already decided.
Find, install, and configure MCP servers. Use proactively for MCP discovery, OAuth setup, env vars, stdio vs SSE transport, or troubleshooting MCP connections. Examples: - user: "Add the filesystem MCP server" → read server file, add to mcpServers in opencode.json, verify transport type - user: "How do I use MCP with GitHub?" → check catalog, install @modelcontextprotocol/server-github, configure OAuth token - user: "MCP not connecting" → check transport type (stdio/SSE), verify args/command, check env vars are passed - user: "What MCPs are available?" → run list_mcps.py, show catalog with auth types and install commands
MCP server building, advanced patterns, and security hardening. Use when building MCP servers, implementing tool handlers, choosing a transport, adding OAuth authentication, wiring MCP Apps UI with @mcp-ui, hardening MCP security, or debugging MCP integrations.
Create and manage Claude Code plugins with proper structure, manifests, and marketplace integration. Use when creating plugins for a marketplace, adding plugin components (commands, agents, hooks), bumping plugin versions, or working with plugin.json/marketplace.json manifests.
Use this skill when the user asks to “create a plugin,” “scaffold a plugin,” “understand plugin structure,” “organize plugin components,” “set up plugin.json,” “use ${CLAUDE_PLUGIN_ROOT},” “add commands/agents/skills/hooks,” “configure auto-discovery,” or needs guidance on plugin directory layout, manifest configuration, component organization, file naming conventions, or Claude Code plugin architecture best practices.
Transform poor or overly simple prompts with expert-level framing. Use when the user explicitly asks to improve, refine, or rewrite a prompt, or wants help framing a request for another AI system. Do NOT use for authoring, reviewing, or migrating system prompts or skills targeting a specific Claude model.
Onboard an AI coding agent to a Syncfusion project. Identifies the framework and product family, installs or selects the official component skills, finds current documentation, handles licensing safely, and verifies a working implementation. Use when starting, integrating, upgrading, migrating, evaluating, or troubleshooting Syncfusion UI components, document SDKs, viewers, or editors on any platform.
Discover and, with authorization, install agent skills from the open skills ecosystem. Use when the user explicitly asks to find or install a skill from the external skills ecosystem, asks whether an installable agent skill exists for a task, or wants to extend agent capabilities through skills.sh or a skill repository. Not for choosing among already-installed local skills or selecting software libraries, developer tools, applications, services, frameworks, or platform primitives; use evaluate-existing-solutions for technology choices
Design a process, idea, or body of knowledge into an ICM (Interpretable Context Methodology) workspace, where folder structure is the agent architecture, or restructure an existing folder, repo, or vault into one. Use for “make this an ICM”, “ICM this”, “build me a workspace”, “structure this for agents”, “map this repo”, “audit this folder”, “what would a change hit”, a second brain, team brain, or context map, or turning transcripts and research into material for lectures, scripts, or docs.
This skill should be used when the user asks to "share memory between agents", "KV cache compaction for multi-agent", "orchestrator worker context", "latent briefing", "reduce worker tokens", "cross-agent memory without summarization", or discusses Attention Matching compaction, recursive language models with workers, or token explosion in hierarchical agents.
Register a custom or variant model (e.g. an OpenRouter ":nitro" / ":floor" / ":exacto" slug) in the Pi Agent so it can be set as the global default. Use when Pi silently falls back to a different model (e.g. moonshotai/kimi-k2.6) after setting defaultModel, or when a model slug isn't in Pi's bundled list. Triggers on "Pi reset my model", "Pi won't use this model", "add a model to Pi", "Pi default keeps reverting"
Lift a proven skill from a host repo (e.g. your OpenClaw fork) back into gbrain's bundle so other clients can scaffold it. Editorial workflow: the CLI does the file copy + privacy lint; this skill drives the judgment-heavy genericization (scrub real names, generalize triggers, lift fork-specific conventions to references)
Use when the blueprint execution gate asks for an independent second-harness review of a Strikethroo plan's cumulative diff in this repository—triggers include code review gate, review the plan diff, second-model review, CODE_REVIEW hook, review the cumulative diff. Do not use to review a single task, to review code outside a Strikethroo plan, or to give general code-quality or style opinions.
Implements AI agent interaction protocols. Adds WebMCP tool annotations, A2A Agent Cards, MCP server cards, live MCP endpoints, MCP Apps, OpenAPI documents, API catalogs, AI catalogs, Agent Skills indexes, NLWeb, SDK and CLI links, and agent commerce documents (x402, MPP, UCP, ACP, AP2, agent checkout) so AI agents can discover and use website functionality. Use when asked to "add WebMCP", "implement A2A", "create agent card", "add MCP server card", "create OpenAPI spec", "add api-catalog", "add NLWeb", "add MCP Apps", "support agent payments", "improve agent protocols score", "make site agent-interactive", or any WebMCP, A2A, MCP or OpenAPI task.
Pre-implementation exploration: deep interview, approach comparison, design doc. Use when exploring a vague feature idea, clarifying ambiguous requirements, or comparing approaches before coding. For the full workflow, use the ia-brainstorm command (Claude Code)
Use only when the user asks to write, revise, or review a development plan, technical design, project proposal, or implementation roadmap. Do not use for direct implementation, following an existing plan, goal execution, continuing work, or updating progress. Deliver an actionable plan that can be resumed across conversations, based on requirements, repository rules, and code facts.
Use the public `orca` CLI to operate Supervibe-managed worktrees, folder contexts, terminals, repos, automations, artifacts, worktree comments, and the browser embedded inside the Supervibe app. Use when the user says "$orca-cli", "use orca cli", "Supervibe worktree", "child worktree", "cardStatus", "spawn codex/claude in a worktree", "read/wait/send Supervibe terminal", "terminal send", "full handoff", "handover", "give this to another agent", "another worktree", "Supervibe browser", "orca artifacts", "share HTML/Markdown", "public artifact link", or "control the browser inside Supervibe". Prefer this over raw `git worktree`, ad hoc PTYs, Playwright, or Computer Use when the task touches Supervibe-managed state. Use Computer Use for browser windows, webviews, or desktop UI outside Supervibe's embedded browser.
Commit and push agent-skill changes to the user's private skills GitHub repo (<private-skills-repo>, rooted at ~/.agents). Use after creating or updating any skill, when the user says "push the skill", "push skills to github", "save the skill to my repo", or "update the skills repo". Handles staging, committing, and pushing directly in the current shell — works in any agent, no cmux needed.
Create, improve, and test skills for the z-schema JSON Schema validator library. Use this skill whenever the user wants to create a new skill from scratch, turn a workflow into a reusable skill, update or refine an existing skill, write test cases for a skill, or organize reference material for a skill. Also use when someone mentions "skill", "SKILL.md", or wants to document a z-schema workflow for reuse by humans or AI agents.
Write coding agent communications in clear, natural, and technically accurate Indonesian. Use when the user writes in Indonesian or requests Indonesian output; apply the requested register, technical terminology, regional style, level of formality, or poetic prose. Style affects prose only and does not restrict code changes that are part of the task. Use when the user writes in Indonesian or requests Indonesian (Bahasa Indonesia) output, including regional voices and local languages such as Javanese, Sundanese, or Ambon Malay.
Structured design dialogue before CloudCannon work that has more than one sensible answer—such as a migration’s editability tradeoffs, modeling a collection or page builder, restructuring content or config, or an ambiguous “make this work with CloudCannon.” Explores intent and constraints, then presents a design for approval before implementation. Not for single well-defined tasks, clear bug fixes, or a detailed spec.
Manages project directory setup and artifact organization. Use when starting a new project, resuming an existing one, or when a PLAN.md needs to be associated with a project directory. Creates the project folder structure (specs/, scripts/, notebooks/, manifests/, agent_memory/) and resolves project naming.
Use when the user wants the GitNexus engineering pipeline run end-to-end on a task: gitnexus-plan (plan depth chosen up front), a blocking gate to execute with gitnexus-work or stop, finishing with a gitnexus-review of the result. Examples: "/gitnexus-lfg Add retry support to the ingestion pipeline", "run the gitnexus pipeline on this", "plan, build and review this feature".
Initialize a Harness Engineering framework in the current project. Use when user says 'harness', 'init harness', 'initialize framework', 'setup harness engineering', '/harness', or wants to set up a Plan-Build-Verify development workflow with specialized agents (planner, generator, evaluator). Creates CLAUDE.md, agent definitions, command templates, hooks, and documentation structure for autonomous AI-driven development
Expert knowledge for Microsoft Foundry Classic (aka Azure AI Foundry classic) development including troubleshooting, best practices, decision making, architecture & design patterns, limits & quotas, security, configuration, integrations & coding patterns, and deployment. Use when configuring Foundry agents, model routing, Azure OpenAI/RAG, multi-agent apps, or secure on-your-data tools, and other Microsoft Foundry Classic related development tasks. Not for Microsoft Foundry (use microsoft-foundry), Microsoft Foundry Local (use microsoft-foundry-local), Content Safety in Foundry Control Plane (use azure-content-safety), Azure Speech in Foundry Tools (use azure-speech).
This skill provides comprehensive guidance for using OpenCode, the open-source AI coding agent. Use this skill when working with OpenCode CLI commands, keyboard shortcuts, agents (build/plan), slash commands, tools, skills, MCP servers, or configuration. Automatically triggered when OpenCode-specific questions or tasks are detected.
Multi-agent workflow examples for working together on the OpenServ Platform. Covers agent discovery, multi-agent workspaces, task dependencies, and workflow orchestration using the Platform Client. Read reference.md for the full API reference. Read openserv-agent-sdk and openserv-client for building and running agents.
Multi-agent QA review team for code changes. Use when the user asks to “review my code”, “run QA”, “qa-team”, “review this branch”, “code review”, “check my changes”, or requests a comprehensive multi-perspective code review of the current branch's changes. Spawns parallel specialist agents (security, database, reliability, compatibility, data integrity, performance, frontend, copy) that independently review the diff and produce a converged report. Also includes two generalist reviewers for convergence validation
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.