Building agents skills

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

nexus-strategy

1825

aimerdoux/wavex-os

Skill Claude CodeCodex

Individual agents are powerful. But without coordination, they produce.

not rated 10 3mo ago A 0 tokens

llm-app-patterns

1826

bugrabilge/bilge-development-kit

Skill Claude CodeCodex

Production-ready patterns for building LLM applications. Covers RAG pipelines, agent architectures, AI assistant design, prompt management, LLMOps monitoring, conversational interfaces, and context management.

not rated 10 4mo ago A 42 tokens original MIT

pacer

1827

EricAndrechek/Pacer

Skill Claude CodeCodex

Report Claude Code usage from Pacer — every rate-limit window, including per-model caps like Fable and each account on the machine — and pace heavy work against them, so hitting a limit during a long autonomous run or a large fan-out of subagents costs a resumable pause rather than the whole run. Use before and during…

not rated 10 +1 3d ago A 146 tokens original MIT

dhaupin/vant

Skill Claude CodeCodex needs its repo

PROPOSAL: Add explicit skill chaining to Agent Skills spec. Defines chain metadata field for ordered skill execution with async option for sequential/parallel loading. Use to propose chaining feature to https://agentskills.io.

not rated 9 16d ago A SkillSpector: warn 48 tokens original MIT

agents

1829

itaywol/adeptability

Skill Claude CodeCodex needs its repo

Guidance for AI coding agents working on the adeptability (adept) codebase. Humans: see README.md for usage and CONTRIBUTING.md for the contributor workflow.

not rated 9 1mo ago A 5 tokens original MIT

conclave

1830

tommasinigiovanni/conclave

Skill Claude CodeCodex

Conclave — Multi-LLM Council with anonymized debate. Orchestrates multiple AI models (Claude, Gemini, GPT, Grok, Llama, etc.) in a Karpathy-style council with 3 depth levels: quick (parallel answers), standard (parallel + synthesis), deep (parallel + anonymized cross-critique with ranking + debate synthesis). Inspired…

not rated 9 5mo ago A 171 tokens original Apache-2.0

skill-curator

1831

lexielin99-code/skill-curator

Skill Claude Code

Manage the Claude Code skills installed on this machine — list, inspect, disable, enable, or remove skills across user-level, project-level, and plugin-level sources. Use this skill when the user asks to: see / list / show all installed skills; check what skills they have; inspect a specific skill's trigger…

not rated 9 4mo ago D 176 tokens original MIT

hermes-setup-skill

1832

hqhq1025/hermes-setup-skill

Skill Claude CodeCodex

Automated deployment of Hermes Agent — install, configure providers, messaging platforms, and tools on local or remote systems.

not rated 9 5mo ago D 30 tokens original MIT

tdm-daos-agent

1833

ToDealMarket/tdm-daos-agent

Skill Codex

Handle the current public TDM DaOS payment contract and recovery guidance. Use when a TDM service returns HTTP 402 from POST /authorize, when the user needs help with Session Gas Tank behavior, or when the user should be guided toward tdm connect, tdm fuel, tdm sweep, or tdm cashout.

not rated 9 2mo ago A 72 tokens original MIT

wxa-ai-mode-dev

1836

TencentCloudBase/mp-skills

Skill Claude CodeCodex

A beta guide for building an AI development mode for WeChat Mini Programs, which are small apps that run inside WeChat. It covers the required files, project structure, data formats, text, components, and interfaces.

not rated 9 2mo ago A 95 tokens

agent-onboarding

1837

skyil7/agent-onboarding

Skill Claude CodeCodex

Initialize a repository by analyzing its structure and generating AGENTS.md and structured docs/, enabling AI coding agents (Claude Code, Codex, Cursor, etc.) to operate safely, deterministically, and with minimal human supervision.

not rated 9 7mo ago A 52 tokens original Apache-2.0

use-sapiom

1838

sapiom/skills

Skill Claude CodeCodex

Access 97 cloud-service tools via Sapiom MCP server — scrape websites, run code in sandboxes, store data (Redis/Vector/Postgres), search the web, call LLMs, generate images and audio, send messages, and manage agent governance. Use when user says "use sapiom", "scrape this page", "search the web", "run this code in…

not rated 9 11d ago A SkillSpector: warn 140 tokens original MIT

orchestrate

1839

wcgomes/agents-workspace

Skill Claude CodeCodex

Use only in coordinator sessions to orchestrate planning or execution of work, including execute, continue, or resume-plan requests. Covers role definition, specialist discovery, dispatch, review, learning, and synthesis. Never use in Session type: DELEGATED executor sessions; those agents perform their handed scope…

not rated 9 19d ago A 67 tokens

skill-router

1840

AnamKwon/agent-skill-router

Skill Claude CodeCodex

Use when organizing a large local skill library into category router skills, refreshing a compact skill inventory, or deciding which leaf skill bodies need to be read before agent classification.

not rated 9 2mo ago A 36 tokens

Skill Creator

1841

spelcc/gate

Skill Claude CodeCodex

Build a safe, reusable Agent Skill package and publish it with skillscreate.

not rated 9 16d ago A 18 tokens

symphony

1842

broomva/symphony

Skill Claude CodeCodex

Expert guidance for Symphony — the Rust orchestration engine for coding agents. Use when users ask about installing Symphony (cargo install, curl|bash, docker), initializing projects (symphony init), configuring WORKFLOW.md for Linear or GitHub trackers, running in daemon or one-shot mode, setting up the control…

not rated 9 2mo ago C 147 tokens original Apache-2.0

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: