Skip to content
#

Agent Skills

Agent skills are self-contained bundles of instructions, reference material, and scripts that an AI agent loads only when a task calls for them. A skill declares what it covers and when it applies, so the agent decides for itself whether to pull it into context instead of carrying every instruction at all times.

The pattern lets an agent’s capabilities grow without its working context growing with them. Authors publish skills as plain files in a repository, and users install the ones they need. Agent skills are commonly paired with agent harnesses and the Model Context Protocol, and are used to capture coding conventions, design systems, domain workflows, and organization-specific procedures.

Here are 3,029 public repositories matching this topic...

archify

Agent skill for beautiful, verifiable architecture, workflow, sequence, data-flow, and lifecycle diagrams—self-contained HTML with motion and crisp export.

  • Updated Sep 30, 2026
  • JavaScript

🦸 AI 编程��能力 · 中文增强版 — superpowers(250k+ ⭐)完整汉化 + 4 个中国原创 skills,让 Claude Code / Copilot CLI / Hermes Agent / Cursor / Windsurf / Kiro / Gemini CLI / Qoder 等 26 款 AI 编程工具真正会干活

  • Updated Sep 29, 2026
  • JavaScript

Stop That Shit(别再造史了)|面向 Codex/GPT 场景的多平台 Hook + Skill Guard:拦截 AI coding agent 无需求的哈希、校验和与任务范围膨胀。 A multi-platform Hook + Skill Guard for AI coding agents in Codex/GPT workflows: stop unrequested hashes, checksums, and task-scope creep.

  • Updated Oct 1, 2026
  • JavaScript
pilot-shell

Professional context and harness engineering for Claude Code and OpenAI Codex. Build production-grade software with spec-driven development, TDD, persistent memory, quality gates, code intelligence, human oversight, and end-to-end verification.

  • Updated Sep 29, 2026
  • JavaScript
babysitter

Babysitter enforces obedience on agentic workforces and enables them to manage extremely complex tasks and workflows through deterministic, hallucination-free self-orchestration

  • Updated Sep 16, 2026
  • JavaScript