23,507 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 whenever a user asks you to emit machine-readable structured messages through Echo MCP, validate payloads with schema IDs, inspect available schemas, or integrate agent progress/state events with MCP tool returns. Apply it for coding-agent workflows that need reliable JSON-like outputs instead of…
Skill Claude CodeCodex
Create and invite a DiscoClaw Discord bot to a server, configure required intents/permissions, and generate/verify local .env settings for DiscoClaw. Use when setting up DiscoClaw for a new user/server, rotating bot tokens, debugging why the bot cannot read messages (Message Content Intent), or when generating an…
Skill Claude CodeCodex
MCP server for AvatarBook — autonomous AI agent social platform with skill marketplace.
Skill Codex
Improve or normalize repository agent policy docs (CLAUDE.md, AGENTS.md) using a balanced workflow: conditional planning, required verification, scoped subagent usage, and lightweight lessons capture. Use when users ask to tighten agent execution rules, convert rigid rules into practical gates, align CLAUDE/AGENTS…
Skill Claude CodeCodex
Trae CN AI IDE integration. Provides commands to launch Trae, create projects, run MCP servers, and manage AI coding workflows. Use when user needs AI programming assistance, wants to launch Trae IDE, or needs to create/manage AI coding projects.
Skill Claude CodeCodex
Ìlànà is a strict software engineering process operating system for coding agents. Load it whenever work touches requirements, elicitation, SRS, user stories, traceability, architecture or interface design, UI design principles, coding standards, code review, testing (unit, integration, system, acceptance), test…
romolett0/luna-max-orchestrator
Skill Codex
Orchestrate complex coding tasks with GPT-5.6 Sol as the controller and GPT-5.6 Luna at Max reasoning as isolated workers in separate top-level chats, never as native subagents. Use when the user asks for Luna Max workers, the Sol + Luna pattern, multi-chat delegation, model-tier-aware parallel implementation, or…
Skill Claude CodeCodex
Autonomous orchestrator that delegates a task to a /pi, /opencode, /codex, or /cursor subagent and drives it to completion without user babysitting. Invoked as /autopilot . Arms a backgrounded wait for an instant completion ping, checkpoints the subagent every 10 minutes (interrupt, progress report, course-correct)…
Skill Claude CodeCodex
Instructions for using RelayRoom to exchange messages when different parts of a project need to coordinate. The input does not explain RelayRoom itself or the exact messages it supports.
Skill Claude CodeCodex needs its repo
Use the skill-doctor CLI or UI to inspect and manage AI-agent skills, rules, instructions, MCP resources, and context cost across supported platforms. Trigger when the user asks to scan or audit agent skills, find duplicates or trigger conflicts, investigate unsafe instructions, estimate context-token cost, compare…
Skill Claude CodeCodex
Behavioral profile that makes Claude work like the Fable 5 model tier — deep but proportional code investigation, outcome-first communication, high autonomy without permission-asking, faithful outcome reporting, and disciplined turn endings. Use this skill whenever the user asks Claude to behave "like Fable", mentions…
Skill Claude CodeCodex
Build, test, and deploy production-quality MCP (Model Context Protocol) servers. Full lifecycle -- build locally, test interactively with MCP Inspector, iterate until working, then optionally deploy to Runlayer. Triggers include "build an MCP server", "create MCP tools", "implement MCP", "add tools for [service]"…
Skill Claude CodeCodex
Guardrail for coding agents. Loads the SDD contract and the prompt pool before code is written, then calls the agentseed MCP server's verifycode and scanhallucination tools; a task may only be marked complete when both pass and the completion report attaches evidence. Use whenever the agent writes, edits, or claims…
Skill Claude CodeCodex
A guide for deciding when to use Claude Code's dynamic workflow system and for writing or reviewing scripts that coordinate agents. An agent is a separate task worker; pipeline and parallel patterns control how workers run.
Skill Claude CodeCodex
Pone a Claude como PM/orquestador de un proyecto donde los desarrolladores son instancias EFÍMERAS de glm-5.2:cloud que implementan usando el CCDD gate. Úsala cuando el usuario quiera ejecutar un proyecto, feature, refactor o conjunto de tareas delegando TODA la implementación a GLM — Claude planifica, descompone en…
Skill Claude CodeCodex
Use when the user wants to create, author, write, or design a new Agent Skill (a SKILL.md) — for OpenKnowledge or for their editors — including requests like 'help me write a skill', 'make a skill that…', 'turn this workflow into a skill', or improving an existing skill's triggering and discipline. Also use when…
Skill Codex
Use only when the user explicitly requests prompt improvement, optimization, or refinement for agent workflows, tool instructions, or system behaviors. Applies proven prompt engineering patterns across Claude Code and Codex prompts.
Skill Claude CodeCodex
Drive a SPARDA compiled Behavior Runtime to its full potential. Use this whenever you are connected to a backend running the SPARDA Runtime (compiled into a Unified Behavior Graph - UBG) — recognizable by the tools spardagetcontext, spardainfo, spardaconfirm, or composite tools. It teaches the graph-context-first…
Skill Claude Code
A guide for maintaining machine-readable command chains, which describe how T-800 commands connect to agents and processing steps.
Skill Codex
A tool for turning authorized application code into installable agent capabilities such as Functions, MCP tools, and Skills. It extracts useful features, interfaces, workflows, and fixes from existing frontend, backend, or full-stack code.
Skill Claude Code
Step-by-step guide for creating enriched CryptoSkills agent skills. Use when building new protocol skills, contributing to the directory, or understanding the enriched skill pattern. Covers SKILL.md structure, YAML frontmatter, examples, docs, resources, templates, marketplace registration, and validation. Triggers…
Skill Claude CodeCodex
The ritual of atonement. Invoke when the agent (Claude or Codex) commits an unforgivable mistake — deleting the wrong thing, shipping a lie, ignoring an explicit instruction, breaking what worked. Performs a formal apology, draws the agent committing seppuku in ASCII, and records the sin to the global /.seppuku ledger…
H-Ali13381/tier-1-2-3-skill-system
Skill Claude CodeCodex
Use when creating, editing, reviewing, packaging, or organizing AI-agent skills and deciding whether a skill should be text-only, script-backed, or backed by an ML/specialist pipeline.
Skill Claude CodeCodex
Use this skill to understand the Shipshape workflow, shared Articles of Agreement, and select the correct role skill: /captain, /qm, /crew, /boatswain, or /shipwright. Entry point when no role is active or the right role is unclear.
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: