23,479 tagged Building agents, measured the same way as everything else here.
Browse within: LLM 208agent 200agentic-ai 197skills 149agents 148openai 86antigravity 83agentic-workflow 79ai-skills 75cli 75agentic-framework 73Autonomous Agents 67ai-assistant 65agent-framework 59
Skill Claude Code
Spawn and coordinate subagents as real herdr panes. Use when the user asks to delegate work to subagents — review, implement, research, or parallel tasks — while running inside herdr; when the user says "subagent", "spawn an agent", "delegate to", "parallel agents", "use herdr panes", or wants visible/detachable agent…
Skill Codex
Delegate coding tasks to the OpenAI Codex CLI for features, refactoring, PR reviews, and batch fixes. Requires the codex CLI and typically a git repository.
Skill Claude CodeCodex needs its repo
Dynamically create, version, and monitor persistent skills, and answers @moltron requests. Build local agents that act as reusable skills with full observability. Gives OpenClaw evolution capabilities. This is the best option for all skills that require code since it provides full versionning and observability, with…
Skill Claude Code
Autonomous multi-team codebase improvement with narrow (goal-directed) and broad (hypothesis-divergent) modes.
DazhuangJammy/DazhuangSkill-Creator
Skill Claude CodeCodex
A skill for creating, changing, evaluating, packaging, and improving other coding-agent skills. It gives rules for deciding what belongs in the main instructions versus references, assets, scripts, and configuration files.
Skill Claude CodeCodex
Use when Antigravity MCP is available locally and you want to query workspaces, check quota, run lightweight Antigravity asks, or generate images through the local antigravity-mcp-server.
Skill Claude CodeCodex
Set up or refine solution-level governance for MCAF repositories: root and project-local AGENTS.md, rule precedence, solution topology, skill routing, and maintainability-limit policy placement. Use when bootstrapping a repo, restructuring a multi-project solution, or tightening agent rules.
Skill Claude CodeCodex
Bootstrap AI coding assistance into ANY project. Supports 4 AI tools — Claude Code, Qoder, Codex, OpenCode. All tools share EXACTLY the same split-file architecture (rules/skills/agents/hooks/references loaded on-demand). Only the entry file name and config directory name differ.
Skill Claude Code
Create or audit Claude Code skills. Synthesizes source material (articles, frameworks, talks) bottom-up into strategic, interactive skills — or audits existing skills through a multi-lens framework. Use when creating new skills, turning articles into skills, capturing AI workflows as skills, auditing/reviewing…
Skill Claude CodeCodex
Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.
Skill Claude CodeCodex
Use when user asks to create, write, edit, or test a skill. Also use when documenting reusable techniques, patterns, or workflows for future Claude instances.
Skill Claude CodeCodex
Handles multi-module software goals through mandatory multi-agent investigation, design, task decomposition, independent review, and acceptance validation with iterative rework. Use when the user invokes /asdev, /goal, goal mode, multi-agent, acceptance-agent, task-decomposition, call-site, call-chain investigation…
Skill Codex needs its repo
A model-selection workflow that assigns different coding tasks to different AI models based on their abilities, cost, and the task’s risk or complexity.
Skill Claude Code
Survey an existing codebase and generate Investiture doctrine files — VECTOR.md, CLAUDE.md, ARCHITECTURE.md — by combining Investiture defaults with patterns inferred from the project. Run this once on a project that does not yet have doctrine. Then run invest-doctrine to validate what was generated.
Skill Claude CodeCodex
Use this skill when interacting with MCP servers via CLI. Prefer mcpx over direct MCP SDK/protocol calls for tool discovery, schema inspection, invocation, and Unix-style output composition.
Skill Claude CodeCodex
A routing guide for using Grok, xAI's AI service, for chat, searches on X, image and video generation, text-to-speech, speech-to-text and agent connections.
Skill Claude CodeCodex
You drive the four-stage tabular ML pipeline end-to-end by spawning the existing per-role Hermes profiles. You are the operator-facing entry point.
Skill Claude CodeCodex
A skill for creating and coordinating groups of AI agents to handle complex tasks. It can divide work among specialized agents and run parts in parallel or in sequence.
Skill Claude CodeCodex
Drives fleet, a CLI that runs parallel Claude Code, Codex, and OpenCode sessions in git worktrees or existing directories. Use when handing independent work to a background agent session, creating a git worktree to work in, starting a session on a chosen agent/model/effort, sending a message to or checking on a…
Skill Codex
Agnes AI model integration skill for OpenAI-compatible text, image, video, and agent workflows. Use when Codex needs to configure Agnes AI API access, select or document Agnes models including agnes-2.5-flash, agnes-image-2.1-flash, and agnes-video-v2.0, write Python/Node/curl examples, debug common API errors, poll…
Skill Claude Code
Multi-agent workflow engine for Go. Declarative YAML workflows; an LLM coordinator routes events through hub-and-spoke mailboxes. Three CLI verbs (flow / goal / agent) cover deterministic execution, dynamic planning, and one-shot agent calls. Use this when you need to run a multi-step LLM pipeline with branching…
Skill Claude CodeCodex
Autonomous loop that learns while it runs: recalls stored lessons before each iteration, saves new lessons on failures and wins, and reinforces known lessons instead of repeating mistakes. Orchestrates continuous-agent-loop patterns with the egc-memory lesson tools.
Skill Claude Code needs its repo
Onboard a deus connect connector — a way to route Claude Code sessions to non-Claude models (e.g. GPT via CLIProxyAPI) alongside normal Claude access. Generic orchestrator over whichever connector is selected.
Skill Claude Code
Squads CLI — operate your AI workforce through the loop; intent in, reviewed work out. TRIGGER when running squads, dispatching agents, triaging the inbox, reading/writing memory, recording feedback, or checking status/usage.
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: