工具说明为英文。
技术工具雷达: Agents, skills and MCP
雷达筛选条件
工具排名
混合排名:实测增长优先。 原始值保留各自的数据窗口;计算变化需要 7 天内至少两次测量。
- 1活跃
把 Markdown 一键排成可直接粘进公众号编辑器的精致 HTML —— 6 套精选主题 + 主题生成器 + 双关卡校验。An AI-agent skill that turns Markdown into paste-ready WeChat article HTML.
github实测增长打开来源 ↗
安装
git clone https://github.com/isjiamu/gzh-design-skill ~/.claude/skills/gzh-design-skill3 536GitHub 星标+104 (+3.0 %) - 2活跃
Build tested agent skills and govern their lifecycle through a user-defined marketplace: evidence, discovery, updates, rollback, quarantine, and 17-platform distribution.
github估算动量打开来源 ↗
安装
git clone https://github.com/FrancyJGLisboa/agent-skill-creator ~/.claude/skills/agent-skill-creator2 367GitHub 星标· - 3活跃
DeepSeek V4 × J-Space capability realization report — benchmark evidence that J-Space reduces capability-realization loss on DeepSeek V4.
github估算动量打开来源 ↗
安装
git clone https://github.com/Tiger3807861189/DeepSeek-V4-J-Space-Capability-Realization-Report ~/.claude/skills/DeepSeek-V4-J-Space-Capability-Realization-Report1 032GitHub 星标· - 4活跃
skulto
技能Offline and security-first tool for syncing and managing agent skills
github估算动量打开来源 ↗
安装
git clone https://github.com/asteroid-belt/skulto ~/.claude/skills/skulto50GitHub 星标· - 5活跃
Agent skill for better research loops
github估算动量打开来源 ↗
安装
git clone https://github.com/nik1t7n/research-craft-skill ~/.claude/skills/research-craft-skill50GitHub 星标· - 6活跃
A LangGraph-powered multi-agent deep research system featuring task planning, human-in-the-loop review, multi-source retrieval, evidence-grounded report generation, full tracing and reproducible evaluation.
github估算动量打开来源 ↗
安装
git clone https://github.com/hwfengcs/SDYJ_Multi_Agents ~/.claude/skills/SDYJ_Multi_Agents50GitHub 星标· - 7休眠
vowline
技能A compact operating covenant for AI agents.
github估算动量打开来源 ↗
安装
git clone https://github.com/chojondocho/vowline ~/.claude/skills/vowline50GitHub 星标· - 8活跃
A light-weight and straightforward system for spec-driven development with Claude Code or OpenAI Codex. Written in Rust 🦀
github估算动量打开来源 ↗
安装
git clone https://github.com/marconae/speq-skill ~/.claude/skills/speq-skill50GitHub 星标· - 9活跃
Inspect, build, or extend Figma design systems from Claude Code. Read-only audits with WCAG checks and component scoring, build mode with variable bindings and slots, optional Phase 6 sync to tokens.css + AI rules.
github估算动量打开来源 ↗
安装
git clone https://github.com/natdexterra/work-with-design-systems ~/.claude/skills/work-with-design-systems50GitHub 星标· - 10活跃
205 production GTM agent skills for Claude Code — sales, outbound, prospecting, RevOps, ABM, PLG, CS, automation. Framework-cited playbooks with artifacts + QA scripts.
github估算动量打开来源 ↗
安装
/plugin marketplace add LeadMagic/gtm-skills46GitHub 星标· - 11活跃
Claude Desktop 的一站式中文补丁、字体补丁、会话管理、提示词研究
github估算动量打开来源 ↗
安装
/plugin marketplace add YX-hueimie/claude-omni13GitHub 星标· - 12活跃
Fan out heavy-lifting tasks from Claude Code (or other AI coding agents) to parallel Gemini sessions via the Antigravity CLI, then integrate the results.
github估算动量打开来源 ↗
安装
/plugin marketplace add Vallykrie/gemini-swarm-skill6GitHub 星标· - 13休眠
architor
技能Structured, phase-gated architecture design powered by Claude Code. Enforces decision gates, challenges assumptions, and produces documented architecture decisions.
github估算动量打开来源 ↗
安装
/plugin marketplace add AhmedHabiba/architor6GitHub 星标· - 14活跃
sonmat
技能sonmat (손맛) — Claude Code plugin that builds verification habits into AI-human collaboration
github估算动量打开来源 ↗
安装
/plugin marketplace add jun0-ds/sonmat6GitHub 星标· - 15休眠
Turns your coding agent into a loud vulgar gym-bro chad.
github估算动量打开来源 ↗
安装
/plugin marketplace add Stronger197/douchebag6GitHub 星标· - 16休眠
🎮 Arcade games for Claude Code — auto-playing pixel games driven by your live session's tokens, prompts, tool calls & context pressure. Single-plugin marketplace. Currently ships 🍄 Super Mario Runner.
github估算动量打开来源 ↗
安装
/plugin marketplace add jaipatel248/claude-arcade6GitHub 星标· - 17活跃
Claude Code skill: Chinese video model generation — Wan, PixVerse, Kling, Vidu, HappyHorse, Jimeng, MiniMax, Hunyuan. Text-to-video, image-to-video, first+last frame, reference-to-video.
github估算动量打开来源 ↗
安装
git clone https://github.com/Agents365-ai/videogencn ~/.claude/skills/videogencn4GitHub 星标· - 18休眠
Seurat v5 single-cell analysis skill for Claude Code, OpenClaw, and Codex
github估算动量打开来源 ↗
安装
git clone https://github.com/Agents365-ai/seurat-skill ~/.claude/skills/seurat-skill4GitHub 星标· - 19活跃
Lookup journal/magazine name abbreviation lookup (ISO 4 / MEDLINE)
github估算动量打开来源 ↗
安装
git clone https://github.com/Agents365-ai/journal-abbrev ~/.claude/skills/journal-abbrev3GitHub 星标· - 20活跃
Multi-source drug-target due-diligence: ranked gene list → per-gene dossier across UniProt, OpenTargets, PubMed + cross-lineage DE scan + composite re-ranking. Claude Code / OpenClaw / SkillsMP skill.
github估算动量打开来源 ↗
安装
git clone https://github.com/Agents365-ai/target-prioritization ~/.claude/skills/target-prioritization3GitHub 星标· - 21活跃
ocrCN
技能Multi-platform Chinese OCR skill — PaddleOCR/Baidu/Tencent/Alibaba/EasyOCR, all work in China
github估算动量打开来源 ↗
安装
git clone https://github.com/Agents365-ai/ocrCN ~/.claude/skills/ocrCN2GitHub 星标· - 22活跃
OFFICINA
技能Method and tools for systematic work with an AI development assistant — curated skills, subagents, CLI, and a working methodology, plus a VS Code setup for macOS.
github估算动量打开来源 ↗
安装
git clone https://github.com/KirKruglov/OFFICINA ~/.claude/skills/OFFICINA1GitHub 星标· - 23活跃
Evidence-first, Fact/Evidence/Assumption/Unknown teardown of a startup or app idea — solo-build screen or VC-scale investment teardown
github估算动量打开来源 ↗
安装
git clone https://github.com/sakshi-gupta-1/idea-teardown-skill ~/.claude/skills/idea-teardown-skill1GitHub 星标· - 24活跃
Catches the exact security mistakes that have actually breached real AI-built apps, before you deploy.
github估算动量打开来源 ↗
安装
git clone https://github.com/AmirHosein-Lotfi/Seaworthy ~/.claude/skills/Seaworthy1GitHub 星标·
学习与参考资源
估算排名:至少需要两次每日测量才能计算增长。 这些资源可单独访问,不参与主要排名。
- 1活跃打开来源 ↗
tunelab
技能Claude Code plugin for LLM fine-tuning, distillation, and evaluation — decide whether you need fine-tuning at all, distill your LLM logs into small local models (MLX/LoRA), evaluate with held-out discipline, and learn the why at every step.
github安装
资源估算动量/plugin marketplace add rchaz/tunelab6GitHub 星标·