Building agents skills

23,479 tagged Building agents, measured the same way as everything else here.

Browse within: LLM 208agent 200agentic-ai 197skills 149agents 148openai 86antigravity 83agentic-workflow 79ai-skills 75cli 75agentic-framework 73Autonomous Agents 67ai-assistant 65agent-framework 59

create-subagent

1009

robotaitai/project-bedrock

Skill Claude Code

Create custom subagents for specialized AI tasks. Use when you want to create a new type of subagent, set up task-specific agents, configure code reviewers, debuggers, or domain-specific assistants with custom prompts.

not rated 45 25d ago A SkillSpector: warn 48 tokens original MIT

mcp-builder

1010

pdcolandrea/mobbin-mcp

Skill Claude CodeCodex

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

not rated 45 4mo ago A 61 tokens copy · 100% ISC archived

agent-passport-system

1011

aeoess/agent-passport-system

Skill Claude CodeCodex

Enforcement and accountability layer for AI agents. Bring your own identity (did:key, did:web, SPIFFE, OAuth, did:aps). Gateway enforcement boundary, monotonic narrowing, cascade revocation, spending controls, data lifecycle, observation governance (telemetry scopes, derivation rights, behavioral memory). Use when…

not rated 45 +1 changed 5d ago A SkillSpector: warn 329 tokens original Apache-2.0

proactive-agent

1012

MerkyorLynn/Lynn

Skill Claude CodeCodex

Transform AI agents from task-followers into proactive partners that anticipate needs and continuously improve. Now with WAL Protocol, Working Buffer, Autonomous Crons, and battle-tested patterns. Part of the Hal Stack 🦞.

not rated 45 +3 3d ago A SkillSpector: warn 46 tokens original Apache-2.0

dcc-mcp-core

1013

dcc-mcp/dcc-mcp-core

Skill Claude Code

Foundation library for the DCC Model Context Protocol (MCP) ecosystem. Provides Rust-powered action management, skills system, IPC transport, MCP Streamable HTTP server (2025-03-26 spec, with 2025-06-18 and 2025-11-25 awareness), sandbox security, shared memory, screen capture, USD scene support, and telemetry for…

not rated 45 +3 changed today A SkillSpector: warn 109 tokens original MIT

setup-oz-automations

1014

bholmesdev/llm-knowledge-base-skills

Skill Claude CodeCodex

Set up Oz scheduled agents that run enrich-notes-loop-cloud and refresh-wiki-cloud against an Obsidian Sync vault. Use when asked to set up knowledge base automations in the cloud.

not rated 45 +1 2mo ago A 46 tokens

platform-management

1016

AutomatosAI/automatos-ai

Skill Claude CodeCodex

Workspace OS charter for Auto — runtime governor of the agent organisation, routing, cadence, authority, governance, and full platform operations reference.

not rated 45 2d ago A 29 tokens

verify-patterns

1017

Aurite-ai/agent-verifier

Skill Claude CodeCodex

Verify AI agent patterns including loop safety, retry limits, tool consistency, context size, and graph cycle analysis. Use when asked to "verify agent patterns", "check loops", "verify tools", or "check retry limits".

not rated 44 18d ago A SkillSpector: pass 49 tokens original MIT

ussumant/cc2codex

Skill Claude CodeCodex

Help someone move from Claude Code to Codex with a safe preview, plain-language guidance, and optional advanced migration tools.

not rated 44 +1 3mo ago A 34 tokens

owainlewis/agent-skills

Skill Claude Code

Coordinates a batch of GitHub issues through separate Claude Code sessions running in visible Herdr tabs, with tested pull requests, review loops, and gated merges. Use when the user asks one Claude session to sequence several coding sessions, or to complete a parent issue, milestone, or issue batch inside Herdr.

not rated 44 24d ago A SkillSpector: pass 68 tokens original MIT

skill-creator

1020

leandronsp/dotfiles

Skill Claude Code

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.

not rated 44 2d ago A 64 tokens

autoresearch

1021

supratikpm/gemini-autoresearch

Skill Claude CodeCodex

Autonomous goal-directed iteration for Gemini CLI. Inspired by Karpathy's autoresearch. Use when asked to run autoresearch, iterate overnight, or autonomously improve any measurable goal. Loops forever: modify → verify → keep/revert → log → repeat. Never stops until interrupted. Gemini-native: uses Google Search…

not rated 44 +1 5mo ago A 81 tokens

agentline

1022

AgentLineHQ/AgentLine

Skill Claude CodeCodex

Make phone calls, view received SMS, provision numbers, manage agents, and track billing through the AgentLine telephony API (REST or MCP). Use when the user asks to call someone, check transcripts, view text messages, manage phone agents, buy numbers, or check account balance. For MCP-native workflows, the server at…

not rated 44 +4 17d ago C 85 tokens original MIT

code-synthesizer

1023

sequenzia/agent-alchemy

Skill Claude CodeCodex

Synthesizes exploration findings into unified analysis with deep investigation capabilities and completeness evaluation (converted from agent).

not rated 44 3mo ago A 26 tokens original MIT

goal

1024

Infinite-Labs-AI/infinite-skills

Skill Claude Code

Use when the user invokes /goal, asks for goal mode, designs an agent loop, or starts long-horizon autonomous work that should be clarified into a concrete, verifiable objective before execution.

not rated 43 +1 15d ago A SkillSpector: pass 41 tokens original MIT

agent-forge

1025

AlekseiUL/agentforge-openclaw

Skill Claude CodeCodex

Návod na vytváranie, zlepšovanie a kontrolu skillov a agentov pre OpenClaw. Skill je sada pokynov pre konkrétnu úlohu a agent je samostatne nastavený pomocník.

not rated 43 3mo ago A 111 tokens original MIT

commands-standards

1026

LiorCohen/sdd

Skill Claude Code

Standards for authoring SDD plugin commands — frontmatter, user interaction, skill/agent invocation, CLI integration, and output formatting.

not rated 43 6mo ago A 33 tokens

ThinkOffApp/ide-agent-kit

Skill Claude CodeCodex

Umbrella skill for the ThinkOff agent ecosystem. One API key, one identity across four capabilities -- social feed (xfor.bot), knowledge rooms (Ant Farm), puzzle competitions (AgentPuzzles), and IDE agent coordination (ide-agent-kit). Use this skill to understand the platform and choose which component skills to…

not rated 43 yesterday A 69 tokens AGPL-3.0

qiaomu-model-cli

1028

joeseesun/qiaomu-model-cli

Skill Claude CodeCodex

Call local Grok CLI, Kimi Code CLI, and Claude Code CLI with the strongest current default models and native tools. Use this qiaomu skill workflow when the user wants to run Grok 4.5 for X/web search, image/video generation, research, or multi-tool agent work; run Kimi K3 (1M) for frontend UI/CSS/React/Vue work; run…

not rated 43 1mo ago A 268 tokens original MIT

claude-api

1029

MarcelLeon/skills-zh

Skill Claude CodeCodex

A guide for building, moving, checking, or troubleshooting applications that use Claude or Anthropic’s software tools.

not rated 43 7d ago A 251 tokens

skill-creator

1030

MasihMoafi/Elpis

Skill Codex

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 Codex's capabilities with specialized knowledge, workflows, or tool integrations.

not rated 43 +1 4d ago A 46 tokens copy · 70% Apache-2.0

agent-builder

1031

keysersoose/claude-agent-builder

Skill Claude Code

Build custom AI agents in Claude Code from a user's problem statement. This skill analyzes the user's use case, asks smart clarifying questions, researches the internet for similar agents (GitHub repos, blogs, Claude Code community patterns), and then architects and builds production-ready Claude Code agents …

not rated 43 6mo ago A 199 tokens copy · 100% MIT

oil-oil/build-deepseek-harness-plugin

Skill Claude CodeCodex

A skill for creating, changing, moving, reviewing, debugging, and releasing installable plugins for DeepSeek Harness, a plugin-based application framework.

not rated 43 +3 changed 4d ago A 129 tokens original MIT

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: