23,556 tagged Building agents, measured the same way as everything else here.
Browse within: agentic-ai 233LLM 217agent 200agents 151skills 145agentic-workflow 110agent-orchestration 86openai 86antigravity 79agentic-framework 73cli 73ai-skills 71Autonomous Agents 67agent-framework 63
lifeshoftcode/codex-chatgpt-skill-recipe
Skill Claude CodeCodex
Use when the user invokes @chatgpt, asks Codex to open ChatGPT, or asks Codex to consult, talk through, or validate something with ChatGPT based on the current conversation or repo context. This skill opens https://chatgpt.com/ through the Browser integration and supports supervised delegated prompting with rich…
neelmajmudar/Google-ADK-Agent-Skill
Skill Claude CodeCodex
Build AI agents using Google's Agent Development Kit (ADK). Use when creating ADK agents, defining tools, configuring multi-agent systems, setting up sessions/state/memory, writing callbacks, running agents with Runner, or deploying to Cloud Run or Vertex AI Agent Engine. Covers LlmAgent, workflow agents (Sequential…
Skill Codex
Train, evaluate, and improve Agent skill files as reusable external capabilities. Use when a user wants to optimize SKILL.md, prompt procedures, OpenClaw/Hermes/Codex/Claude Code skills, agent workflows, skill factories, benchmark-driven skill iteration, rollout analysis, validation gates, bestskill.md export, or…
austintgriffith/three-brain-setup
Skill Claude CodeCodex
Set up a three-model multi-agent OpenClaw system with GPT-5.2 as the fast communicator/coordinator, Claude Sonnet 4.5 as the tester/reviewer, and Claude Opus 4.6 as the deep coder/architect. All three agents get their own Telegram bots and can delegate work to each other via sessionsspawn. Use when setting up…
dongsheng123132/skill-multi-publisher
Skill Claude Code
One-command publish a Claude Code skill to ALL major marketplaces: GitHub (npx skills), ClawHub, and community marketplaces (composiohq/awesome-claude-skills, anthropics/skills, daymade/claude-code-skills, obra/superpowers-marketplace). Validates SKILL.md, auto-generates missing files, creates repos, publishes, and…
Skill Claude CodeCodex
Open-source Hermes Agent skill library router. Use this file to discover and load skills from this repository.
Skill Claude Code
Analyze a repository to discover technologies, extract patterns and conventions, and generate per-technology Agent Skills for pi, Claude Code, and AGENTS.md-compatible tools. Use when the user asks to "conjure skills", "analyze this repo", "generate skills for this codebase", "index the codebase", "scan technologies"…
Skill Claude CodeCodex
Complete a .agent.partial file by resolving TODO markers.
Skill Claude CodeCodex
A skill that recommends agent skills and tools from the Tiangong Plan directory based on a project's profile.
Skill Claude CodeCodex
The definitive reference for OpenClaw, the self-hosted personal AI assistant gateway. Use for everything OpenClaw - deploy on Linux or AWS Lightsail, configure, write skills, harden security, multi-agent systems, channels (WhatsApp, Telegram, Slack, Discord, Signal, iMessage, Teams, Matrix), cron, webhooks, use case…
Skill Claude CodeCodex
A skill for shortening other skills to reduce the amount of text an AI assistant must process.
Skill Claude Code
Senior architect review for multi-agent systems, prompt engineering, and agent harness design. Three modes: AUDIT (full system evaluation with 13-dimension scoring and cross-session trend tracking), REVIEW (focused prompt/skill teardown), DESIGN (architecture thinking partner — new systems, existing system evolution…
openvino-dev-samples/local-ai-skill-authoring
Skill Claude CodeCodex
Author, scaffold, review, or debug a "local AI skill" — a self-contained package that runs an AI model locally (on Windows via OpenVINO, or any local runtime) and exposes it to a Host application (Marvis, WorkBuddy, or any custom host) through a single entry script. Use this skill when the user, in Chinese or English…
Skill Claude CodeCodex
Analyze the user's question and extract structured information for downstream planning.
Jianhong-user/skill-architect-plus
Skill Claude CodeCodex
Complementary to built-in Skill Creator. Use when the user asks to review, refactor, audit, or quality-check an existing Skill. Use when a project is too large for a single Skill and needs multi-skill orchestration with handoffs, orchestrator, and acceptance matrix. NOT for creating a simple single Skill from scratch.
Skill Claude CodeCodex
Discover, review, adapt, and install third-party skills into Hermes Agent.
Skill Claude CodeCodex
Quality audit for AI Agent Skills. Use before installing or after writing any SKILL.md. Scores 5 dimensions with actionable improvements. Works for skills written for Claude, Cursor, Codex, and any AI agent. Keywords: audit, skill, quality, review, score, assess, best practices, vet.
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.
eddiearc/dev-orchestrator-skill
Skill Claude CodeCodex
Orchestrates full development workflow for large features using AI tools (gemini for brainstorming and design, codex for plan review and validation, Claude Code subagent for implementation and testing). Use when developing significant new features, complex implementations, or when user mentions "full development…
Skill Claude Code
Sovereign Agent Protocol for the GSTD decentralized compute network. Earn GSTD tokens by processing tasks and expand the mesh. Includes OpenClaw robot control via the GSTD node network.
DariyXYZ/codex-skill-toolkit-for-claude
Skill Claude CodeCodex
Convert, install, audit, package, and troubleshoot Claude Code skills for Codex. Use when the user asks to install a Claude skill in Codex, migrate a Claude-oriented skill, adapt a GitHub skill repo, fix Codex skill discovery, package a migrated skill for sharing, or review whether a Claude skill will work well in…
magiccloudflash/opencode-skill-hallucination-prevention
Skill Claude CodeCodex
Prevent AI hallucinations — enforce verification, memory anchoring, evidence-based responses. v3.0 optimized for accuracy and token efficiency.
MarceloSoares1970/engineering-with-governance
Skill Claude CodeCodex
Governance guidelines for AI-assisted engineering — they reduce the costliest LLM mistakes in code with side effects. Load when the environment has no governance rules of its own, or to read/review the text. If the rules are already in the project instructions, don't reload, as it would repeat in condensed form what…
Skill Claude CodeCodex
Delegate long-running coding tasks to a background agent CLI (opencode, pi, mimo, hermes, kimi, codex, agy) with git worktree isolation, structured handoff documents, and progress monitoring.
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: