23,498 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 Codex
Use when the user asks to migrate, upgrade, or port prompts, agents, tools, or codebases from one LLM model or provider version to another. Also use when auditing or continuing migration work started by another agent. Covers API calls, prompt assets, agent configs, tool definitions, tests, docs, runtime settings…
Skill Claude CodeCodex
Equilibrium-Native Reasoning for OpenClaw.
DefaultHQ/build-support-agent-skill
Skill Claude Code
Plan and build a production customer-support agent — a RAG product-Q&A bot that drafts replies, posts them for human review, and graduates to controlled autonomy. Use when someone wants to build an in-house support agent, a Slack-native or support-platform AI bot, a ticket-answering / customer-Q&A agent, or wants to…
wu736139669/agent-taskgraph-protocol
Skill Codex
A workflow for coordinating multiple coding-agent sessions in Codex or Claude Code. A main session breaks work into tasks, assigns them to separate agents, and uses shared documents for handoffs.
Skill Codex
Orchestrate OpenPlan-style skills in auto or YOLO mode while preserving human decision boundaries. Use when Codex, Claude Code, or another agent should automatically inspect, align enough to proceed, research, test, review, garden, summarize, hand off, or generate temporary HTML without silently approving, changing…
Frontier-Intelligence-Lab/loop-architect
Skill Codex
Design a safe, verifier-first loop for an AI coding agent — or refuse when a task should not be looped. Use when someone asks "can I automate this with an agent?" or wants to create, audit, or improve a loop for coding agents, scheduled agent work, autonomous repo maintenance, CI/QA loops, refactoring loops…
Skill Claude CodeCodex
Run a decision through 5 independent AI advisors (Contrarian, First Principles, Expansionist, Outsider, Executor) that peer-review anonymously and synthesize a verdict. Trigger on 'council this', 'pressure-test this', 'war room this', or any high-stakes either/or choice. Skip for factual lookups, summaries, or simple…
JadeYingWah/gpt-5-6-sol-reasoning-style
Skill Codex
Use when another model with weaker reasoning is asked to plan, review, or implement non-trivial work and needs GPT-5.6 Sol-like rigor instead of jumping to implementation.
Skill Claude CodeCodex
Bring in an external model (Codex) to co-develop a plan — both models draft independently, align on disagreements, and merge into one plan. Load this only when the user explicitly names Codex (e.g. "let's discuss this with Codex," "what does Codex think about this approach") — don't auto-trigger just because a plan…
AILiteracyLab/Claude-Build-Test-Loop
Skill Claude CodeCodex
Spec-Build-Test loop — the user defines a spec, then three agents iterate (Builder implements, Tester validates, Supervisor monitors for freezes) until the result matches. Works for any digital function — UI, APIs, CLI tools, conversational AI, data pipelines, and more.
Skill Claude CodeCodex
A read-only audit checklist for Hermit and Claude Code setups, covering how they are structured, used, checked, and improved, including token use and model selection.
Skill Claude CodeCodex
An expert role that manages an AI agent through its full lifecycle, from defining its requirements and abilities to packaging, testing, deploying, upgrading, and retiring it. It also designs how multiple agents work together.
Skill Claude CodeCodex
Author runnable OpenExpertise experience files — heterogeneous executable graphs (agent / skill / tool / dataset / experience nodes) backed by a persistent blackboard. Use this skill whenever the user wants to create, write, build, scaffold, or design an OpenExpertise experience: "make an experience for X", "create an…
Skill Claude CodeCodex
Cage, run, and audit MCP servers with mcpvessel: install an MCP server into an isolated container, serve it to Claude Code, and watch what it does with the network and the user's secrets. Use this whenever the user mentions mcpvessel by name, or wants to add, install, set up, try, run, or sandbox an MCP server, or…
Skill Claude CodeCodex
Search, scan, install, and manage Claude Code skills with built-in security scanning. Every installation is gated behind a 60+ pattern threat scan.
Skill Claude CodeCodex
Build or change a backend with stitchkit — the contract-first framework where one defineContract() becomes an HTTP API, MCP tools, AI-agent tools, a CLI and a typed client. Use this whenever working in a project that depends on stitchkit: defining or editing a contract, implementing handlers, exposing endpoints as MCP…
Skill Claude CodeCodex
Operator guide for MCPLab config authoring, Test Case Assistant workflows, execution, and result analysis. Use when users need to create or refine test cases from runs/traces, suggest deterministic checks or value capture, write or debug MCPLab eval YAML, run or queue evaluations, troubleshoot failures, or compare…
Skill Codex
CostMarshal v5.1 internal policy/runtime for the Codex plugin: two-level native Codex attempt teams plus scheduler-first, cost-aware low/medium/high API routing. It governs repository-bound Workstreams, report-only proposals and multimodal inputs, Provider drift, mTLS gateway leases, hard budgets, production…
Skill Claude CodeCodex needs its repo
Produce a Codex multitask worker plan without executing workers.
SpillwaveSolutions/mastering-gemini-cli-agentic-skill
Skill Claude CodeCodex
Build headless automation and agentic workflows with Google's Gemini CLI. Covers approval modes (default, autoedit, yolo), file permission model, Edit vs WriteFile tool selection, smartEdit configuration, GEMINI.md context files, settings.json hierarchy, and MCP server integration. Use when building CI/CD pipelines…
Skill Claude CodeCodex
Dual-agent development workflow - Claude Code plans and reviews, Codex implements headlessly, git automated. ONLY runs when the user explicitly types /pair. NEVER activate automatically, no matter how well a task seems to match this workflow.
Skill Claude CodeCodex
Run bounded, resumable OpenAI-native coding loops with shell and applypatch, similar to Claude Code agent loops. Use when the user asks for a loop, autonomous iteration, or a persistent inspect-edit-test cycle with a turn cap.
Skill Claude CodeCodex
Makes a repository AI-native by creating AGENTS.md, .cursorrules, and documentation that helps any AI agent understand the codebase. Follows the WHAT/WHY/HOW framework from best practices. Use when the user asks to "make repo AI-ready", "add cursor rules", "create AGENTS.md", "set up for AI coding", or "make agents…
netgrade-digital/shared-agents
Skill Claude CodeCodex needs its repo
Complete guide to the shared-agents shell CLI (sa). Use when the user asks how to run sa, sa help, install, sync, review, pending, unapprove, check, uninstall, status, or any shared-agents terminal command. Also use when explaining setup, wizard, or troubleshooting the CLI after sa install.
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: