Skip to main content
Home · 首页/Rankings · 排行榜/Agent & Skill Building
Category ranking· 品类排行

The best AI skills for agent & skill building做Agent 与 Skill 开发最好用的

Author skills, build MCP servers, orchestrate agents — tools for making AI tools.写 Skill、建 MCP、编排多 Agent:打造和优化你自己的 AI 工具。

Task shortcuts按用途继续找

Open the matching picks in the full catalog.这些入口会带你去完整目录里看对应用途。

Editor's picks编辑精选榜单

2026-06-09 last re-ranked · 上次重排
#1Gold · 金

Anthropic Skill Creator

Editor's Choice· 编辑首选
by Anthropic✓ verified·updated 3mo ago

Create, test, and improve skills in an eval loop.

用评估循环创建、测试并改进技能。

An official Anthropic workflow for drafting new skills, benchmarking them against baselines, and iterating with human review.

Anthropic 官方技能创作流程,用于起草新技能、构建测试提示词、对比基线,并在人类评审下持续迭代。

Claude CodeSkill repositoriesPython eval toolingMedium risk · 中风险$/skill-creator
4.9
rating · 评分
163k
stars · 星标
View看详情 →
#2Silver · 银

engineering advanced skills

Runner-up· 次选
by alirezarezvani·updated 2mo ago

25 advanced engineering agent skills and plugins for Claude Code, Codex, Gemini CLI, Cursor, OpenClaw. Agent design, RA…

25 advanced engineering agent skills and plugins for Claude Code, Codex, Gemini CLI, Cursor, OpenClaw. Agent design, RAG, MCP servers, CI/CD, database design, observability, security auditing, release management, platform ops.

Claude CodeMedium risk · 中风险$
rating · 评分
14k
stars · 星标
View看详情 →
#3Bronze · 铜

pm skills

Pair with #1· 推荐配套
by alirezarezvani·updated 2mo ago

6 project management agent skills and plugins for Claude Code, Codex, Gemini CLI, Cursor, OpenClaw. Senior PM, scrum ma…

6 project management agent skills and plugins for Claude Code, Codex, Gemini CLI, Cursor, OpenClaw. Senior PM, scrum master, Jira expert (JQL), Confluence expert, Atlassian admin, template creator. MCP integration for live Jira/Confluence automation.

Claude CodeMedium risk · 中风险$
rating · 评分
14k
stars · 星标
View看详情 →
#4

board meeting

by alirezarezvani·updated 2mo ago

Multi-agent board meeting protocol for strategic decisions. Runs a structured 6-phase deliberation: context loading, in…

Multi-agent board meeting protocol for strategic decisions. Runs a structured 6-phase deliberation: context loading, independent C-suite contributions (isolated, no cross-pollination), critic analysis, synthesis, founder review, and decision extraction. Use when the user invokes…

Claude CodeMedium risk · 中风险$
rating · 评分
14k
stars · 星标
View看详情 →
#5

README

by alirezarezvani·updated 2mo ago

313 production-ready Claude Code skills, plugins, and agent skills for 12 AI coding tools.

313 production-ready Claude Code skills, plugins, and agent skills for 12 AI coding tools.

Claude CodeCodexAutomated screen · 自动筛查$
rating · 评分
14k
stars · 星标
View看详情 →
#6

hf mcp

by huggingface·updated 2mo ago

Use Hugging Face Hub via MCP server tools. Search models, datasets, Spaces, papers. Get repo details, fetch documentati…

Use Hugging Face Hub via MCP server tools. Search models, datasets, Spaces, papers. Get repo details, fetch documentation, run compute jobs, and use Gradio Spaces as AI tools. Available when connected to the HF MCP server.

Claude CodeMedium risk · 中风险$
rating · 评分
10k
stars · 星标
View看详情 →
#7

memos-local

by MemTensor·updated 2mo ago

Persistent local memory for OpenClaw agents. Use when users say: - "install memos" - "install MemOS" - "setup memory" -

Persistent local memory for OpenClaw agents. Use when users say: - "install memos" - "install MemOS" - "setup memory" - "add memory plugin" - "openclaw memory" - "memos onboarding" - "memory not working" - "configure memory" - "enable memory" - "upgrade MemOS" - "update memory plugin"

Claude CodeCodexMedium risk · 中风险$
rating · 评分
9.0k
stars · 星标
View看详情 →
#8

autoresearch

by Orchestra-Research·updated 2mo ago

Orchestrates end-to-end autonomous AI research projects using a two-loop architecture. The inner loop runs rapid experim

Orchestrates end-to-end autonomous AI research projects using a two-loop architecture. The inner loop runs rapid experiment iterations with clear optimization targets. The outer loop synthesizes results, identifies patterns, and steers research direction. Routes to domain-specific skills for execution, supports continuous agent operation via Claude Code /loop and OpenClaw heartbeat, and produces research presentations and papers. Use when starting a research project, running autonomous experiments, or managing a multi-hypothesis research effort.

Claude CodeCodexAutomated screen · 自动筛查$
rating · 评分
8.2k
stars · 星标
View看详情 →
#9

refly

by refly-ai·updated 2mo ago

Base skill for Refly ecosystem: creates, discovers, and runs domain-specific skills bound to workflows. Routes user inte

Base skill for Refly ecosystem: creates, discovers, and runs domain-specific skills bound to workflows. Routes user intent to matching domain skills via symlinks, delegates execution to Refly backend. Use when user asks to: create skills, run workflows, automate multi-step tasks, or manage pipelines. Triggers: refly, skill, workflow, run skill, create skill, automation, pipeline. Requires: @refly/cli installed and authenticated.

Claude CodeCodexAutomated screen · 自动筛查$
rating · 评分
7.3k
stars · 星标
View看详情 →
#10

alloydb-basics

by google·updated 2mo ago

Manages clusters, instances, and backups for AlloyDB for PostgreSQL, and integrates with AlloyDB model context protocol

Manages clusters, instances, and backups for AlloyDB for PostgreSQL, and integrates with AlloyDB model context protocol (MCP) tools for automated database operations.

Claude CodeCodexAutomated screen · 自动筛查$
rating · 评分
6.9k
stars · 星标
View看详情 →

Why we didn't pick these为什么没选这些

Also common, but didn't make the picks同样常见,但未入精选
  • dot-skill

    Workflows that require stronger human review than this catalog entry documents.

    需要比当前目录条目更严格人工复核的工作流。

  • mama

    Workflows that require stronger human review than this catalog entry documents.

    需要比当前目录条目更严格人工复核的工作流。

  • latent briefing

    Workflows that require stronger human review than this catalog entry documents.

    需要比当前目录条目更严格人工复核的工作流。

Didn't find what you need?没看到合适的 skill?

Tell us your pain points and we'll go look.把你的痛点告诉我们,我们会去找。

Skill Market
Find the best AI skills for the job·按品类找最好用的 AI 技能
v0.4 · 1306 skills indexed · last review 2026-06-09