23,429 tagged Building agents, measured the same way as everything else here.
Browse within: LLM 209agent 202agentic-ai 195skills 149agents 145openai 86antigravity 83agentic-workflow 79cli 75agentic-framework 73ai-skills 73Autonomous Agents 67ai-assistant 66agent-framework 59
Skill Claude CodeCodex
Modify an existing Claude Code skill to add Agent Junction awareness — registration, peer discovery, and message exchange. Injects junction blocks at appropriate points in the skill workflow. Primary use case is junction-enabling handover skills. Triggers on phrases like "inject junction", "junction-enable this…
elegant1998/xiaozhi-mcp-server
Skill Claude CodeCodex
A bridge that sends spoken requests from the Xiaozhi smart speaker to OpenClaw and reads OpenClaw’s answers back aloud. OpenClaw is the service that processes tasks such as weather checks, information searches, and document writing.
Skill Claude CodeCodex
A local hub (agent-comm-hub on 127.0.0.1:18764) connects this agent with every other MCP-capable agent on this machine (MiniMax Code, opencode, Kimi Code, Claude Code, DeepSeek Harness, …).
Skill Claude CodeCodex
Use when the user asks to personalize their assistant, to use vardoger, or to analyze their Windsurf conversation history. Runs the vardoger CLI to read past conversations and generate tailored instructions.
Skill Claude Code
Autonomous single-phase implementation using Foundry MCP session-step orchestration. Runs one spec phase under unattended posture with strict gate enforcement, deterministic exits, and verification receipts. Use when executing autonomous implementation with the autonomyrunner role and session-step protocol.
Skill Codex
Design, scaffold, audit, and upgrade Model Context Protocol servers. Use when the user asks to build or migrate an MCP server, adopt MCP 2026-07-28, add dual-era support, create an MCP integration, expose an API or data source through MCP tools/resources/prompts, add OAuth or API-key auth to an MCP endpoint, run an…
Skill Claude CodeCodex
Runtime guardrails for AI coding agents. Stop loops, budget overruns, retry storms, and timeouts before they burn money. Zero dependencies, local-first, MIT licensed.
yedanyagamiai-cmd/openclaw-mcp-servers
Skill Claude CodeCodex
AI coding tool comparison MCP server -- compare Claude Code vs Cursor vs Windsurf vs Devin vs Copilot side-by-side with feature matrices, pricing breakdowns, and AI-powered recommendations. Use when: (1) user asks 'compare Cursor and Windsurf' or 'which AI coding tool is best', (2) user says 'tell me about Devin' or…
Skill Claude CodeCodex
Security review of LLM applications and agents. Use when asked to review, red-team, threat-model or test an LLM feature, chatbot, RAG pipeline, MCP server or autonomous agent for prompt injection (direct or indirect), jailbreaks, system prompt or secret leakage, tool abuse, excessive agency, confused-deputy behavior…
Skill Claude CodeCodex
The autonomic executive of an agent — a self-firing loop that wakes on a tick, pulls the other organs into one workspace, decides what needs attention now, acts or defers, then sets its own next wake frequency and sleeps. Turns a pile of triggered reflexes into a continuous self that persists and acts between human…
Skill Codex
Use when creating, auditing, rewriting, debugging, migrating, or evaluating GPT-5.6 Sol, Terra, or Luna prompt layers, tool descriptions, agent briefs, or prompt stacks; choosing runtime configuration; or comparing controlled prompt candidates.
Skill Claude CodeCodex
Set up the skills-evals library in a repository — discover agent artifacts, interview the user about what to test, scaffold eval cases, and wire CI and local runners. Use when the user wants to set up skills-evals, test their agent skills, add evals for skills or custom agents, check why a skill isn't triggering, or…
Skill Codex
Design, validate, edit, visualize, and execute AgentFlow Markdown-first workflows with deterministic Boolean gates. Use when a task benefits from explicit boxes, arrows, branching, parallel work, resumable progress, or when the user asks to create/modify/run a workflow graph in AgentFlow.
Skill Claude Code needs its repo
Orchestrate Codex to BUILD code in the background while this Claude Code session (typically Opus) plans and reviews — never babysitting. The session composes the implementation plan, kicks the dev-review runner detached via a background Bash task with --preset codex-build, ENDS ITS TURN, and is woken on exit to run a…
Skill Claude CodeCodex
Discover skills, iterate on queries, and automate skill installations for any environment.
Skill Claude Code
Scaffold Claude Code hook configs by reading your existing settings and skills.
Skill Claude CodeCodex
Claude AI cookbooks - code examples, tutorials, and best practices for using Claude API. Use when learning Claude API integration, building Claude-powered applications, or exploring Claude capabilities.
Skill Claude CodeCodex needs its repo
Use this skill when the user wants to create, update, or design a project-level agent (.agents/agents/.md). Analyze the user's question and project context to design a work plan. Triggers: 'create agent', 'build an agent', 'add agent', 'design agent', 'update agent', 'project agent', 'subagent', 'worker agent'…
Skill Claude CodeCodex
MCP server providing 45 tools for AI agent trust verification, identity, and reputation scoring.
Skill Codex
Plan, execute, and verify Kore.ai Agent Platform work through the Arch MCP server using code-backed operation and dependency knowledge.
Skill Claude CodeCodex
Improve and verify agent work after repeated failures, in dependency-heavy tasks, or when optimization claims need baseline and regression evidence. Use for DAGx/Perfectify requests, failed retries, risky multi-step work, or requests to verify an improvement. Exclude routine questions, drafting, one-step edits, and…
Abhillashjadhav/AI-PM-essential-skills
Skill Claude Code
Use this skill when a user wants to audit a CLAUDE.md, system prompt, agent context file, or any assembled context before running it in production. Triggers on phrases like "audit my context", "check my CLAUDE.md", "review my system prompt", "why is my agent behaving badly", "context issues", or when a user pastes a…
Skill Claude CodeCodex
Iterative worker-reviewer cycle that spawns a critic subagent to score work 1-10 and provide actionable feedback, then revises until a quality gate is met. Use when implementing features, writing specs, reviewing existing code, or completing any task where quality matters more than speed. Trigger phrases: "use…
Skill Claude CodeCodex
Manage resident peer agents: long-running monitors that live inside the pi session, tick on minute intervals, watch the main agent's work, and push findings back mid-turn. Use when the user asks to launch/stop/ask a peer, watcher, monitor, observer, sentinel, or auditor; wants standing review, drift/scope watching…
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: