Agents, skills and MCP radar: unclassified entries

Momentum based on available 7-day snapshots for Agents, skills and MCP: measured with two snapshots, estimated otherwise. Each value shows its own source window. This page reads stored snapshots only.

Radar filters

Tool ranking

Ranked by measured growth, normalized across sources. Raw values keep their source-specific window, shown under each tool; a change requires at least two snapshots from the last 7 days.

  1. 1
    Active

    Redteam / Pentest Skill Pack — semi-automated workflow + on-demand module selection + real-world attack chains | Kali + Claude Code 红队/渗透/技能包 - 半自动工作流 + 按需点选模块 + 实战利用链 | 基于 Kali 与 Claude Code

    githubmeasured growthOpen source ↗

    41GitHub stars+14 (+51.9 %)
  2. 2
    Active

    🥗 陈石(Mars)运动营养师 Claude Code Skill — 营养矩阵40课体系、瘦素/皮质醇/胰岛素抵抗深度解析、麦克唐拉德增肌模型、可执行行动协议

    githubmeasured growthOpen source ↗

    5GitHub stars+3 (+150.0 %)
  3. 3
    Active

    Candid reviews of Claude Code skills. File:line citations. Ranked actions. No filler.

    githubmeasured growthOpen source ↗

    49GitHub stars+10 (+25.6 %)
  4. 4
    Active

    A2A agent server that provides Context7-style documentation capabilities for your agents

    githubmeasured growthOpen source ↗

    2GitHub stars+1 (+100.0 %)
  5. 5
    Active

    An Agent Development Kit (ADK) allowing for seamless creation of A2A-compatible agents written in TypeScript

    githubmeasured growthOpen source ↗

    2GitHub stars+1 (+100.0 %)
  6. 6
    Active

    Doc-driven multi-agent dev workflow for Claude Code (Conductor/Executor/Reviewer) · 文档驱动的多代理开发工作流

    githubmeasured growthOpen source ↗

    2GitHub stars+1 (+100.0 %)
  7. 7

    Other
    Active

    A2A agent server for mocking and testing

    githubmeasured growthOpen source ↗

    2GitHub stars+1 (+100.0 %)
  8. 8

    Other
    Active

    A zero-runtime-dependency GitHub Action for running Infer CLI agents with multi-provider AI support, GitFirst workflows, issue automation, progress comments, and PR creation.

    githubmeasured growthOpen source ↗

    2GitHub stars+1 (+100.0 %)
  9. 9

    Other
    Active

    A terminal-native agentic coding harness built from scratch — streaming ReAct loop with reflection and planning, MCP/A2A protocols, cross-session semantic memory, subagent orchestration, YAML skills and agent roles, shell lifecycle hooks,…

    githubmeasured growthOpen source ↗

    2GitHub stars+1 (+100.0 %)
  10. 10
    Active

    A2A agent server for grafana dashboards automation tasks

    githubmeasured growthOpen source ↗

    1GitHub stars+1
  11. 11
    Dormant

    GENESIS UI/UX Gold Standard — The ultimate Claude Code UI/UX skill. 28 award-winning techniques, 5 engines, 24 databases, 1,334+ entries. Built by Miguel Jiminez.

    githubmeasured growthOpen source ↗

    8GitHub stars+2 (+33.3 %)
  12. 12
    Active

    Claude Code Skill:B站/小红书/抖音/快手/微博/贴吧/知乎 多平台社媒评论采集爬虫。扫码登录,自动生成 HTML 报告+CSV,支持关键词搜索/指定链接/创作者主页三种模式

    githubmeasured growthOpen source ↗

    8GitHub stars+2 (+33.3 %)
  13. 13

    Other
    Active

    Rust multi-protocol agent-ingress gateway (MCP, A2A, REST, and chat-channel adapters) for the Hetzner agent substrate.

    githubmeasured growthOpen source ↗

    3GitHub stars+1 (+50.0 %)
  14. 14
    Dormant

    Deep SEO Audit is an a claude code skill created by Anant Mendiratta that performs expert-level technical SEO audits for any URL — from a 2-minute focused check to a full 7-phase deep audit.

    githubmeasured growthOpen source ↗

    3GitHub stars+1 (+50.0 %)
  15. 15

    Other
    Dormant

    Open-source readiness scanner for agent-facing websites, merchants, APIs, docs, and support surfaces.

    githubmeasured growthOpen source ↗

    3GitHub stars+1 (+50.0 %)
  16. 16
    Active

    基于 Claude Code Skill 的智能网文写作助手,支持大纲生成、章节撰写、人物管理、世界观设定,覆盖玄幻/仙侠、都市/现实、科幻/未来等六大类型,可以理解上下文、埋伏笔等宏大事件

    githubmeasured growthOpen source ↗

    3GitHub stars+1 (+50.0 %)
  17. 17
    Active

    🎯 Anna 跨境品牌出海陪跑教练 | 15年跨境实战 · 10大心智模型 · 全渠道增长策略 | by @me 品牌出海陪跑

    githubmeasured growthOpen source ↗

    3GitHub stars+1 (+50.0 %)
  18. 18

    Other
    Active

    A2A agent server specialized in generating and automating n8n workflows

    githubmeasured growthOpen source ↗

    3GitHub stars+1 (+50.0 %)
  19. 19

    Other
    Dormant

    The open-source event bus for AI agents. Webhooks in. Agent actions out.

    githubmeasured growthOpen source ↗

    3GitHub stars+1 (+50.0 %)
  20. 20

    Other
    Active

    A Claude Code skill — single source of truth for deferred work. Don't lose track of what you've punted.

    githubmeasured growthOpen source ↗

    31GitHub stars+4 (+14.8 %)
  21. 21
    Dormant

    Claude Code skill: zero-dependency full-page screenshot via Chrome DevTools Protocol

    githubmeasured growthOpen source ↗

    20GitHub stars+3 (+17.6 %)

Learning resources

Ranked by measured growth, normalized across sources. These resources remain available separately and do not take part in the main tool ranking.

  1. 1
    ActiveOpen source ↗

    Knowledge-, capability-, and trust-aware framework for discovering, validating, selecting, and orchestrating heterogeneous AI agents across cloud, marketplace, enterprise, and edge environments, with A2A interoperability and outcome-driven…

    githubResourcemeasured growth
    11GitHub stars+11
  2. 2
    ActiveOpen source ↗

    Generate personalized coding lessons from your own codebase. A Claude Code skill: three surfaces (tutorial / vocab / status), six writing-to-learn entries, audience-facing path with six venue templates. v2.0.0 released 2026-05-10.

    githubResourcemeasured growth
    40GitHub stars+14 (+53.8 %)
  3. 3
    ActiveOpen source ↗

    本项目是 Socratopia(破卷)生态的衍生项目,是其"造书"环节的方法论沉淀,已固化为一个可复用的 skill。 让你具备亲手为自己造一本教材的能力——把一本教材(或一个领域的知识)加工成 AI 老师能拿去上课的教学蓝本。有教师用书时,造出来的书还能直接针对应试(见第四节)。

    githubResourcemeasured growth
    14GitHub stars+5 (+55.6 %)
  4. 4
    ActiveOpen source ↗

    A curated list of A2A-compatible agents that are tested and fully operational

    githubResourcemeasured growth
    3GitHub stars+1 (+50.0 %)