技能目录

为 AI Agent 发现可复用技能。

按任务搜索真实的 GitHub 技能,并在使用前查看 Stars、信任、审计、分类和安装路径。

每个推荐都保留与其仓库、审计和安装路径的明确关联。

搜索结果: directories

英文目录

:octocat: Github action to retrieve all (added, copied, modified, deleted, renamed, type changed, unmerged, unknown) files and directories.

2.7K
Stars
84/100
信任
分类: github-automation审计

Obelisk indexes past agent sessions (Claude Code, Codex, Kimi Code, Pi) into a queryable SQLite database with a CLI skill for agents and an Electron app for humans.

313
Stars
72/100
信任
分类: utility审计

A cross-platform desktop app to manage Agent Skills in one place and sync them to multiple AI coding tools’ global skills directories — “Install once, sync everywhere”.

1.1K
Stars
85/100
信任
分类: agent-skills审计

A plugin for OpenCode that provides dynamic skill loading, context injection, and other tools for using reusable AI agent skills.

262
Stars
77/100
信任
分类: coding-agents审计

Skillset optimized for solo, bootstrapped, and non-technical founders building SaaS applications with AI tools (Lovable, Replit, Claude Code).

227
Stars
76/100
信任
分类: utility审计

A collection of reusable AI agent skills for Flux CD and GitOps, enabling agents to generate manifests, audit repos, and debug clusters.

198
Stars
72/100
信任
分类: coding-agents审计

Install, manage, and share skills across every major coding agent — Claude Code, Cursor, Copilot, and more.

253
Stars
69/100
信任
分类: coding-agents审计

Find web directories without bruteforce

2.0K
Stars
70/100
信任
分类: web-automation审计

Local-only web GUI for inspecting agent skills (SKILL.md) across user, project, plugin, cache, and marketplace sources

65
Stars
69/100
信任
分类: utility审计

Mandatory iPolloWork code-change gate for modern, minimal, performant, reuse-first implementation and clean repository ownership. Use whenever AI creates, edits, deletes, or refactors application code, server code, packages, scripts, tests, dependencies, schemas, routes, UI, or generated-file workflows. Reuse existing code before creating files, keep one source of truth, prevent parallel implementations and junk directories, justify every new file or dependency, and audit the current change before completion.

4.5K
Stars
67/100
信任
分类: security审计

Read when the user asks what OpenKnowledge is, wants to install it on a repository, wants to open or preview a single markdown file that is not part of an OpenKnowledge project, wants to share an OpenKnowledge project with collaborators, asks whether OpenKnowledge supports a particular capability, or asks how `ok init` / `ok cowork` / OK Desktop set up a project. Do NOT load to perform OpenKnowledge reads/writes — the runtime guidance for editing markdown inside an initialized OK project ships as a separate project-local skill installed into each detected agent's skills dir (for example `.claude/skills/open-knowledge/`) whenever `ok init` runs.

3.6K
Stars
70/100
信任
分类: design-creative审计