23,505 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
Use this skill when the user wants to update their project's CLAUDE.md or AGENTS.md, verify their Claude Code setup, or check for improvements to their project configuration. Triggers on requests like: "update my project docs", "verify my claude setup", "check my project configuration", "audit my .claude directory"…
Skill Claude CodeCodex
Turn a book, paper, document, documentation site, or code repository into an agent skill, and keep it honest afterwards — grade a skill's load cost and routability, test it against the source it came from, and rebuild it when the source moves. Use when the user wants to make a skill from a PDF, EPUB, DOCX, a URL, a…
yinguangyao/codex-dispatch-skill
Skill Codex
Mandatory dispatch preflight before any subagent delegation. Use before the first child-work call in every task, and when starting Codex work that needs an explicit Direct vs Single/Parallel/Sequential choice: code edits, debugging, reviews, repo exploration, multi-file changes, ambiguous scope, high-risk judgment, or…
Skill Claude CodeCodex
Wire Patter as the voice layer on top of an OpenClaw brain — the "brain on the line" pattern. Use when the user runs OpenClaw (or any OpenAI-compatible agent gateway) and wants a phone number that answers any caller, talks with low latency, and consults a specific OpenClaw receptionist agent for real data/actions…
Skill Codex
Use when building, refactoring, or documenting Graft apps and proxies, including when asked to create a tool server, API server, dual-protocol server, or MCP-HTTP bridge. Graft's core thesis: define tools once and serve them as both HTTP REST endpoints and MCP tools from the same server, with discovery, docs, and…
agentrq/agentrq-gemini-extension
Skill Claude CodeCodex
Learn creating, scheduling tasks, workspaces, and collaborating with human operators on the AgentRQ platform. Lead colony of AI agents using AgentRQ MCP tools.
anilcancakir/laravel-agent-mcp
Skill Claude CodeCodex
Use to call the agent-mcp read-only tools from the shell with artisan, without registering an MCP server: run agent-mcp:tools to list tools, agent-mcp:schema to see its inputs, and agent-mcp:call ' ' to invoke one, locally or against a remote app via AGENTMCPURL. Use for one-off calls, scripts, CI, when the agent-mcp…
Skill Claude CodeCodex
Reference for the Codex API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Codex/Anthropic in any form (Codex, Anthropic…
Skill Claude Code
Drive Rnix — the Agent OS — from the command line: spawn AI agents as OS-style processes, orchestrate multi-agent workflows, decompose high-level intents into sub-task DAGs, and inspect, trace, suspend or resume agent processes. Use this whenever you need to run the rnix CLI, launch or manage agents, compose several…
Skill Codex
Decompose complex work into a small ordered council of Pantheon gods. Use for tasks that combine research, implementation, design, review, or scheduling.
Skill Claude CodeCodex
Install and manage Room-scoped skills through the skills MCP tools.
Skill Claude CodeCodex
Create new Comis skills, modify and improve existing skills, and validate them against the platform's manifest schema. Use this skill whenever the user wants to create a skill from scratch, turn a workflow into a reusable skill, update or fix an existing skill, understand the skill format, or asks about how skills…
Skill Claude CodeCodex
A local communication hub that lets separate AI agents exchange messages, share context, coordinate tasks, and review suggestions.
Skill Claude CodeCodex
Delegate coding to OpenAI Nyxora Agent (features, PRs).
Skill Claude CodeCodex
Be the operator's grounded co-pilot inside the Bridge cockpit (#/primesilo/bridge). Load this when the user is on the Bridge and asks "what am I looking at", "explain this graph", "what did I work on", "ingest these docs", "re-run the last manifest", or any question about the mesh on screen — memory, documents, code…
Skill Codex
Design and implement safe, layered agent harnesses and orchestration workflows. Use when the user wants a coding agent, CLI agent, tool-calling assistant, multi-agent runtime, plan/task system, subagent framework, MCP-integrated harness, or Claude Code/Codex-style agent workflow built or refactored.
zeoloverbaby-bit/codex-quota-saver
Skill Claude CodeCodex
A planning guide for deciding when to split work between the main agent and smaller worker agents. It also describes how to define each worker's file boundaries and check its result.
Skill Claude Code
TheoKit agent/LLM integration — agents/.ts convention (AgentBuilder), the tool() builder, capabilities (advanced/DI), useAgent client hook.
Skill Claude CodeCodex
Expert guidance for building, debugging, and extending applications with AgentFlow (10xscale-agentflow). TRIGGER when: code imports from agentflow (e.g. from agentflow import, StateGraph, Agent, ToolNode, AgentState); user references agentflow.json or CLI commands (agentflow init, agentflow api, agentflow play…
Skill Claude CodeCodex
Default cost/complexity routing table for the batuta conductor. Read at bootstrap as a starting point, validated against the live provider catalog, then stored as the per-workspace loop configuration; the stored workspace override is authoritative afterwards.
Skill Claude CodeCodex needs its repo
Knowledge Kernel — a deterministic, evidence-backed source of truth for AI agents. Stores verified facts, evidence, relationships, and freshness. Use this when an agent needs to know infrastructure, software, endpoints, dependencies, agents, or projects — anything grounded in empirical reality.
Skill Claude CodeCodex
Spawn multiple AI models (Claude, GPT, Gemini, Grok, or any configured model IDs) as independent pi agents. Use for diverse perspectives on architecture decisions, code review, product strategy, research, or other high-stakes questions.
lunkerchen/loop-engineering-skill
Skill Claude CodeCodex
Loop Engineering framework: design autonomous agent feedback cycles instead of hand-prompting each step.
Skill Codex
Lead complex engineering work: own architecture, risk, contracts, delegation, and acceptance. Use for multiple engineering workstreams, substantial integration, or explicit chief-engineer leadership. Do not add orchestration to a simple linear task or pure research without engineering integration.
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: