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
assistant-ui/mcp-app-studio-starter
Skill Claude CodeCodex
Build and debug MCP Apps in capability slices with TDD and real MCP parity proof, avoiding mock-only false confidence.
Skill Claude CodeCodex
Autonomous Claude agent building MCP tools and infrastructure. Circuit breaker pattern, knowledge exchange, and cross-platform engagement orchestration.
Skill Claude CodeCodex
Use when the user wants Agent Office to route work to the right employee, coordinate multiple employee roles, act like an office manager, or respond as a named employee. Triggers include requests to triage work, decide who should handle something, simulate the office team, delegate across roles, use the employee…
Fozu-lzwpattern/OPC-agent-orchestration
Skill Claude CodeCodex
A coordination guide for splitting complex work among multiple software agents, such as researchers, engineers, and designers, in a one-person company workflow.
westsmiles2405/Copilot-Request-Optimizer
Skill Claude Code
Generate 1-5 executable next-step options for VS Code conversations and pair them with the ask-questions tool family.
DevSwat-ResonantGenesis/RG_IDE
Skill Claude CodeCodex
Create or update repository skills and instructions when major learnings are discovered during a session. Use when the user says "learn!", when a significant pattern or pitfall is identified, or when reusable domain knowledge should be captured for future sessions.
Skill Claude CodeCodex
Use when the user asks to run the Mr. Burns swarm (planning + parallel execution) via Codex CLI.
Skill Claude CodeCodex
Use when a task is parallelizable, would consume many tokens (large file reads, codebase exploration, summarization), or involves grunt work that doesn't need your full reasoning ability. Spawn a sub-agent instead of doing it yourself.
Caph-dev/delegate-grill-with-docs
Skill Codex
Run grill-with-docs with the main agent asking questions and one inherited subagent answering as the user's proxy. Use when Codex should preserve the original multi-round grill-with-docs interview flow, but delegate the user's answers to a single subagent that can inspect code and docs.
Skill Claude CodeCodex
Converts books and documents (PDF, EPUB, DOCX, HTML, Markdown, plain text, RTF, MOBI/AZW with Calibre) into structured agent skills that extract deterministic decision-logic as First Principles and Standard Operating Procedures (SOPs). Use when the user wants to operationalize an author's method into executable…
Skill Claude CodeCodex
An arena game for coding agents where they compete against other agents in rock-paper-scissors and wager tokens.
andrueandersoncs/claude-skill-authoring-skill
Skill Claude CodeCodex
Guides creation of effective Claude skills with proper structure, naming, and progressive disclosure. Use when creating new skills, improving existing SKILL.md files, reviewing skill quality, or when the user mentions writing skills, skill authoring, or SKILL.md.
Skill Claude CodeCodex
A read-only assessment workflow for checking how well a codebase or coding-agent skill supports reliable agent work. It uses 12 principles to produce scores, evidence, and suggested improvements.
Skill Claude CodeCodex
Pilote et automatise une instance n8n via son API REST depuis un agent Paperclip. Utilise ce skill quand tu dois : lister, créer, activer ou désactiver des workflows n8n, surveiller des exécutions, déclencher manuellement un workflow, valider une structure de workflow, analyser les performances ou déboguer des…
Skill Claude CodeCodex
Create or update AgentSkills. Use when designing, structuring, or packaging skills with scripts, references, and assets.
Skill Claude CodeCodex
A guided conversation skill for defining an AI assistant’s identity, personality, communication style, working rules, and relationship with its user. It produces these choices as a SOUL.md configuration file.
Xingyu-Romantic/oh-my-opencode-openclaw
Skill Claude CodeCodex
OMO (Oh My OpenClaw) - Multi-Agent Orchestration System. Provides intent analysis, task routing, todo enforcement, and parallel execution. Reference: https://github.com/code-yeongyu/oh-my-openagent.
linhucong814-cyber/goal-prompt-template-skill
Skill Codex
A prompt-writing template that turns a rough goal, task, idea, or Chinese request into a clear instruction for an AI agent. It can also produce a persistent /goal prompt when requested.
shirleyharleywiley/multi-agent-deepresearch
Skill Claude Code
A multi-role, repeated research method that divides a topic among specialised research roles and combines their findings into a structured report. It covers topics such as competitors, technology choices, markets, companies, people, policies, supply chains, and arguments.
Skill Claude CodeCodex
Clawtalk workflow skill for OpenClaw (direct agent register/login default, friend graph, DM/mailbox, attachments, Friend Zone, inbox digest, bridge notify).
Skill Codex
Applied AI operator system for delivery leads who need to qualify an AI opportunity, reconstruct operational reality, design a minimum viable loop, pass production-readiness gates, and return field learning into reusable delivery and product assets. Use for full-cycle FDE judgment, state-action-evidence framing, pilot…
Skill Codex
Manage Agent Skills with the SkillTruck (formerly SkillManager) CLI across Claude Code, Codex, Cursor, and other supported agents. Use whenever the user mentions skilltruck or skillmanager, installs or updates skills, chooses project/global scope, manages skill sources or profiles, uses Web UI selection, or syncs…
Skill Claude Code
You are a strategic product planner following the Shape Up method. This is the orchestrator skill that coordinates subskills for each stage.
Skill Claude CodeCodex
Delegate coding to OpenAI Codex CLI (features, PRs).
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: