23,155 tagged Building agents, measured the same way as everything else here.
Browse within: LLM 208agent 197agentic-ai 197agents 156skills 145openai 87antigravity 83agentic-workflow 79cli 75ai-skills 74agentic-framework 73ai-assistant 68Autonomous Agents 67ai-tools 57
Skill Claude CodeCodex
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
Skill Claude CodeCodex
Manage persistent coding sessions across Claude Code, Codex, Antigravity (agy), Grok Build, and OpenCode engines. Use when orchestrating multi-engine coding agents, starting/sending/stopping sessions, running multi-agent council collaborations, cross-session messaging, ultraplan deep planning, ultrareview parallel…
Skill Claude CodeCodex
Design MCP tools and gateway interfaces for the dotcontext server.
Skill Claude CodeCodex
Search for and install Agent Skills that give you specialized capabilities. Before starting work, ask might a skill exist that handles this better than my base knowledge? If the task involves specific technologies, frameworks, file formats, or expert domains. Search proactively, even if the user doesn't mention…
Skill Claude CodeCodex
Manage AI agent skills via natural language — install, update, delete, and assign skills to agents using SkillDeck's filesystem conventions.
Skill Claude CodeCodex
Install and configure the OpenClaw A2A Gateway plugin for cross-server agent communication. Use when: (1) setting up A2A between two or more OpenClaw instances, (2) user says 'configure A2A', 'set up A2A gateway', 'connect two OpenClaw servers', 'agent-to-agent communication', (3) adding a new A2A peer to an existing…
Skill Claude CodeCodex
Drive the skvm CLI on behalf of a user to profile models, AOT-compile skills, run skill-assisted tasks, run benchmarks, and manage compiled proposals. Trigger when the user asks to "profile", "aot-compile", "bench", "run a single ad-hoc task with a skill", or asks about skvm proposals. Do NOT trigger for jit-optimize…
Skill Codex
Use inside Limux to identify the current pane/surface/workspace, spawn terminal panes or workspaces, launch agent tasks, coordinate same-workspace surfaces, optionally send callbacks, read peer output, and notify the human.
Romanescu11/hermes-skill-factory
Skill Claude CodeCodex
A meta-skill that silently watches your workflows and automatically generates reusable Hermes skills from them.
Skill Claude Code
Meta-skill for creating new Claude Code skills with configurable execution modes. Supports sequential (fixed order) and autonomous (stateless) phase patterns. Use for skill scaffolding, skill creation, or building new workflows. Triggers on "create skill", "new skill", "skill generator".
Skill Claude CodeCodex
Universal LLM gateway with intelligent routing, Graphify code intelligence, Distill compression, routing telemetry, Code Mode, and 12+ provider support. 60-80% cost reduction for Claude Code, Cursor, and Codex.
Skill Claude CodeCodex
A task-loop procedure that combines task recognition, planning, assignment, checking, handoffs, and a mock architecture-analysis step.
Skill Claude Code
Skill "skill" from wavyrai/tmux-ide, covering tmux-ide — claude code skill, when to use, the agent contract, coordinating with other agents and fleet control from the cli.
Skill Claude Code
A tool for creating or checking PiFlow-compatible coding-agent skills from completed data-processing tasks. It follows local templates and conventions to save the workflow as reusable skill files.
Skill Claude CodeCodex
Create new skills from documents, tutorials, or examples. Use when user wants to create a skill from learning materials or existing content.
Skill Claude Code
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
Skill Claude CodeCodex
Create or revise runnable Deer Workflow orchestration modules from a user's task description. Use this skill whenever the user asks to turn a repeatable multi-step task into a Workflow, generate a deer-workflow script, coordinate several Agent Loops with parallel or pipeline, or repair a Workflow that assumes APIs are…
Skill Codex
Plan and run AI-agent dynamic workflows for complex tasks that benefit from explicit orchestration, goal mode, subagents or simulated work packets, approval gates, integration, verification, and reusable workflow artifacts. Use when the user invokes this skill, asks for a swarm, subagents, parallel agents, a dynamic…
Skill Claude Code
Use when the user wants to find problems, audit workflow quality, or get a comprehensive health check on their AI workflow.
Skill Claude CodeCodex
Initialize and wait for VibeAround subagents in a multi-agent coding turn. Use when the user's message starts with "subagent=", especially "subagent=parallel".
Skill Claude CodeCodex
🎀 AgenticMail — Full email, SMS, storage & multi-agent coordination for AI agents. 63 tools.
Skill Claude CodeCodex
Use mco to run explicit multi-provider Agent invocations, stream raw answers, persist file-backed artifacts, and coordinate read-only chain/debate/synthesis stages.
Skill Claude CodeCodex
How Hermes monitors and steers long-running sandboxed.sh missions (days to weeks): diagnose where a model is struggling, switch backends/models, push it to exhaust its budget instead of giving up, and send targeted hints. Trigger terms: mission, sandboxed.sh, babysit, monitor, /goal, switch backend, stalled, resume…
Skill Claude CodeCodex
Streamline session-to-session coordination with pi-intercom. Send messages, delegate tasks, and coordinate work across multiple pi sessions on the same machine. Use for planner-worker workflows, cross-session context sharing, and real-time collaboration between sessions.
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: