23,505 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 Code
On-demand tool loader — reads catalog, resolves category conflicts, loads tool context. Modes: scan (plan-aware), load (reactive), status (check loaded). Saves tokens by never preloading.
Skill Claude CodeCodex needs its repo
Create cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn…
Skill Claude CodeCodex
This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development…
Skill Claude CodeCodex
Lord skill for governing AI coding agents at runtime — gateway interception, agent/flow/model allowlisting, and MCP-server-as-securable. The control layer between an agent's decision and its real-world action.
Skill Claude CodeCodex
Set up Cortex by discovering the user's existing systems and generating a personalized Workflow Registry from them. Use when the user runs /cortex-init, says "set up cortex", "adopt my tools into cortex", "build my registry", or right after installing Cortex for the first time.
steerlabs/agent-harness-templates
Skill Claude CodeCodex
Build specialized agent harnesses from a user's prompt. Use when the user wants to create, scaffold, improve, or productize an agent harness with fat Markdown skills, thin deterministic actions, setup flow, local or cloud state, routines, and verification.
Skill Claude CodeCodex
A multi-agent framework for writing serial novels, where separate agents handle story setup, chapter planning, drafting, checking, and publication.
Skill Claude CodeCodex
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
Skill Codex
One source of truth for local AI agent skills: audit Codex, Claude, Hermes, OpenClaw, OpenCode, workspace skills, and shared roots; score hygiene, diff conflicting installs, classify drift as pristine/dirty/local-only against recorded baselines, deduplicate into one canonical source with symlinks, and migrate the same…
smartcontractkit/chainlink-for-agents
Skill Claude CodeCodex
Register an agent, create chain wallets, discover available workflows, sign Chainlink for Agents requests, handle x402 USDC payments, and sign EIP-712 operation data locally. Use for the Chainlink for Agents /v1 API, agent wallets, workflow execution, EIP-712 signing, and x402 payments. Do NOT use for generic REST…
Skill Claude CodeCodex
Autonomously implement a planned feature end-to-end as a senior engineer, drive it to a clean state through an iterative QA + Design/Product + Engineer review loop, prove it actually runs with /verify, take it to a green reviewed PR with /thor, and finish with a standup-style session log. Use this when the user hands…
Skill Claude CodeCodex
Pipeline completo de desenvolvimento de software com IA — PRD → Arquitetura → Tasks → Código → Review → Testes → Docs → CI/CD → Iteração. Baseado nas práticas de Harness Engineering da Anthropic, OpenAI e Thoughtworks/Martin Fowler: guias (feedforward) + sensores (feedback) que se auto-corrigem antes de chegar ao…
Skill Claude CodeCodex
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
TheSylvester/agentic-coding-tools
Skill Claude CodeCodex
Synthesize self-contained implementation prompt(s) that hand a task to a fresh coding agent with an empty context window, decomposing into a phased chain or parallel set when the task is too large for one. Use when the user says "write a handoff prompt", "generate a prompt", "distill this for a fresh agent", or asks…
Skill Claude CodeCodex
Orchestrate pi coding agents with DAG-aware dependency resolution, git worktree isolation, automatic retry, and structured JSON output. Use this skill when: - spawning pi agents for any subtask - tasks have dependency ordering (A must finish before B starts) - parallel agents need isolated git workspaces - you need…
JustinGastby/Hermes-Mind-Skill
Skill Claude CodeCodex
Review the project's accumulated Skills and propose archiving long-unused ones or merging near-duplicate ones into a single broader skill. Use when nudged by the Stop hook's curator sweep (mentions skills that haven't been used in a while), when the user asks to clean up / compress / prune skills, or when creating a…
Skill Claude CodeCodex
Use when installing rulesagents into a Bazel repo, verifying the setup, discovering skills from registries or custom repos, adding local skills, and configuring agent profiles and runners.
Skill Codex
A proposal process for improving a reusable coding skill or the rules that decide when an agent uses it. It uses repeated failures, user feedback, and test results to suggest bounded improvements without applying them.
Skill Claude CodeCodex
Build, configure, and extend HermesPet — a native macOS AI companion living in the Dynamic Island with multi-engine support, desktop pets, and advanced system integration.
dungnotnull/pro-gamer-eye-hand-training-agent-skill
Skill Claude CodeCodex
The pro-gamer-eye-hand-training system uses a centralized skill registry pattern for managing skill lifecycle, discovery, execution, and validation. This document defines how skills are registered, resolved, executed, and validated using JSON schemas for type safety.
4ier/openclaw-feishu-group-chat
Skill Claude CodeCodex
Teach OpenClaw how to work in Feishu (Lark) group chats — recognize who's talking, behave properly in groups vs DMs, respect multi-user privacy, and format messages for the platform. Use when connecting OpenClaw to Feishu and you want your agent to be a competent group participant, not just a responder.
dungnotnull/fighting-game-combo-optimizer-agent-skill
Skill Claude CodeCodex
The fighting-game-combo-optimizer uses a dynamic skill registry that provides.
dungnotnull/portable-emergency-water-filter-agent-skill
Skill Claude CodeCodex
Skill "portable-emergency-water-filter-agent-skill" from dungnotnull/portable-emergency-water-filter-agent-skill, covering skill.md -- skill registry documentation, 1. skill registration, discovery, frontmatter (the registration contract) and validation.
Skill Claude CodeCodex
Use when doing AI product management on an AI system itself — writing or debugging evals, prompts, agent/RAG/tool design, model selection and routing, the data flywheel, eval-gated shipping, online quality/groundedness/drift monitoring, safety/red-teaming, or inference cost and unit economics. Triggers: AI PM, AIDLC…
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: