Die Werkzeugbeschreibungen sind auf Englisch.

Programmierassistenten

Programmierassistenten und Werkzeuge zur Codegenerierung.

Anwendungsfall

Aktivität

Sortieren nach

189

Werkzeug-Rangliste

Nach gemessenem Wachstum und quellenübergreifend normalisiert sortiert. Rohwerte behalten ihr eigenes Zeitfenster; eine Änderung erfordert mindestens zwei Messungen in 7 Tagen.

  1. 1
    Aktiv

    The meta-skill that builds and improves all your skills, including itself. Watches your work sessions (autonomous or human-led), captures patterns, corrections and judgement calls, and turns them into skill improvements and new skill…

    githubgemessenes WachstumQuelle öffnen ↗

    Installieren git clone https://github.com/rebelytics/one-skill-to-rule-them-all ~/.claude/skills/one-skill-to-rule-them-all

    2 257GitHub-Sterne+173 (+8.3 %)
  2. 2
    Aktiv

    A Claude Code skill bundle for bug hunting and external red-team work - 82 skills, 15 slash commands, 681 disclosed-report patterns curated across 24 core vulnerability classes, plus enterprise identity + infrastructure attack matrices.

    githubgemessenes WachstumQuelle öffnen ↗

    Installieren git clone https://github.com/elementalsouls/Claude-BugHunter ~/.claude/skills/Claude-BugHunter

    4 022GitHub-Sterne+215 (+5.6 %)
  3. 3

    Skill
    Aktiv

    Production-grade engineering skills for AI coding agents.

    githubgemessenes WachstumQuelle öffnen ↗

    Installieren git clone https://github.com/addyosmani/agent-skills ~/.claude/skills/agent-skills

    91 500GitHub-Sterne+1 416 (+1.6 %)
  4. 4

    Sonstige
    Aktiv

    Where people and agents build in tune.

    githubgemessenes WachstumQuelle öffnen ↗

    3 666GitHub-Sterne+204 (+5.9 %)
  5. 5

    Agent
    Aktiv

    Taste-Skill - gives your AI good taste. stops the AI from generating boring, generic slop

    githubgemessenes WachstumQuelle öffnen ↗

    82 205GitHub-Sterne+1 096 (+1.4 %)
  6. 6
    Aktiv

    数学建模技能 - 面向 CUMCM、MCM/ICM 等数学建模竞赛的三阶段工作流:建模分析、Python/MATLAB 编程与 DOCX 论文生成。包含丰富的算法资源库(优化/预测/评价/图论/机器学习等)、角色指导文档、论文模板和实用工具脚本

    githubgemessenes WachstumQuelle öffnen ↗

    Installieren git clone https://github.com/XiaoMaColtAI/math-modeling-skill ~/.claude/skills/math-modeling-skill

    1 009GitHub-Sterne+107 (+11.9 %)
  7. 7

    CLI
    Aktiv

    DSH 官方公众号收录的 TUI 补位插件:Claude Code 风,鲸鱼顶栏/实时状态/流式思考/双击 Esc 回滚/上下文进度+TPS。npm 一键装。 DSH official WeChat featured TUI plugin — Claude Code style: whale bar, live status, streaming thoughts, double-Esc rollback, context bar + TPS. npm one-click.

    githubgemessenes WachstumQuelle öffnen ↗

    2 774GitHub-Sterne+170 (+6.5 %)
  8. 8

    Skill
    Aktiv

    Open-source, local-first conversational AI video editor with a professional multi-track timeline, Agent Skills, MCP integration, and Remotion rendering.

    githubgemessenes WachstumQuelle öffnen ↗

    Installieren git clone https://github.com/0xsline/OpenChatCut ~/.claude/skills/OpenChatCut

    1 527GitHub-Sterne+129 (+9.2 %)
  9. 9

    Sonstige
    Aktiv

    Find the ghost tokens. Fix them. Survive compaction. Avoid context quality decay.

    githubgemessenes WachstumQuelle öffnen ↗

    2 122GitHub-Sterne+149 (+7.6 %)
  10. 10
    Aktiv

    A curated list of awesome Claude Skills, resources, and tools for customizing Claude AI workflows

    githubgemessenes WachstumQuelle öffnen ↗

    Installieren git clone https://github.com/ComposioHQ/awesome-claude-skills ~/.claude/skills/awesome-claude-skills

    74 240GitHub-Sterne+863 (+1.2 %)
  11. 11

    Agent
    Aktiv

    Omnigent is an open-source AI agent framework and meta-harness: orchestrate Claude Code, Codex, Cursor, Pi, and custom agents — swap harnesses without rewriting, enforce policies and sandboxing, and collaborate in real time from any device.

    githubgemessenes WachstumQuelle öffnen ↗

    9 598GitHub-Sterne+282 (+3.0 %)
  12. 12

    Agent
    Aktiv

    The agent that grows with you

    githubgemessenes WachstumQuelle öffnen ↗

    239 583GitHub-Sterne+2 635 (+1.1 %)
  13. 13

    Skill
    Aktiv

    Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini,…

    githubgemessenes WachstumQuelle öffnen ↗

    Installieren /plugin marketplace add thedotmack/claude-mem

    92 932GitHub-Sterne+965 (+1.0 %)
  14. 14

    Sonstige
    Aktiv

    🪨 why use many token when few token do trick — Claude Code skill that cuts 65% of tokens by talking like caveman

    githubgemessenes WachstumQuelle öffnen ↗

    102 292GitHub-Sterne+1 057 (+1.0 %)
  15. 15
    Aktiv

    Multi-tier framework for evaluating AI agent skills with quality gates, semantic overlap detection, synthetic evaluation dataset generation, and live agent evaluation that measures how skills affect agent behavior.

    githubgemessenes WachstumQuelle öffnen ↗

    Installieren git clone https://github.com/NVIDIA/SkillEvaluator ~/.claude/skills/SkillEvaluator

    389GitHub-Sterne+63 (+19.3 %)
  16. 16
    Aktiv

    GPT-Image-2 PPT Generator Skill for Creating Image-Based PowerPoint Presentations in Codex and Other Skill-Compatible Agents

    githubgemessenes WachstumQuelle öffnen ↗

    Installieren git clone https://github.com/ningzimu/codex-ppt-skill ~/.claude/skills/codex-ppt-skill

    5 466GitHub-Sterne+216 (+4.1 %)
  17. 17

    Agent
    Aktiv

    The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

    githubgemessenes WachstumQuelle öffnen ↗

    245 821GitHub-Sterne+2 265 (+0.93 %)
  18. 18

    MCP
    Aktiv

    Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.

    githubgemessenes WachstumQuelle öffnen ↗

    68 350GitHub-Sterne+630 (+0.93 %)
  19. 19

    Skill
    Aktiv

    Active Directory pentest methodology for Claude Code: skills, agents and slash commands for internal AD red-team work (Kerberoasting, ADCS ESC1-17, DCSync, ACL abuse, NTLM relay, delegation), with per-technique OPSEC/telemetry notes. Drives…

    githubgemessenes WachstumQuelle öffnen ↗

    Installieren /plugin marketplace add ADScanPro/Claude-AD

    141GitHub-Sterne+36 (+34.3 %)
  20. 20

    CLI
    Aktiv

    CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies

    githubgemessenes WachstumQuelle öffnen ↗

    78 241GitHub-Sterne+697 (+0.90 %)
  21. 21

    Sonstige
    Aktiv

    💫 Toolkit to help you get started with Spec-Driven Development

    githubgemessenes WachstumQuelle öffnen ↗

    132 929GitHub-Sterne+1 208 (+0.92 %)
  22. 22
    Aktiv

    AI-powered bug bounty hunting toolkit that works with or without subscription.

    githubgemessenes WachstumQuelle öffnen ↗

    4 662GitHub-Sterne+196 (+4.4 %)
  23. 23
    Aktiv

    网文/小说写作 skill 包,覆盖长篇与短篇网络小说的扫榜、拆文、写作、去AI味、封面图全流程 | An all-in-one skill pack for long- and short-form web fiction.

    githubgemessenes WachstumQuelle öffnen ↗

    Installieren git clone https://github.com/zenstory-ai/oh-story-claudecode ~/.claude/skills/oh-story-claudecode

    6 338GitHub-Sterne+221 (+3.6 %)

Lern- und Referenzressourcen

Nach gemessenem Wachstum und quellenübergreifend normalisiert sortiert. Diese Ressourcen bleiben getrennt zugänglich und fließen nicht in die Hauptwertung ein.

  1. 1
    AktivQuelle öffnen ↗

    Autoharness — a self-learning skill layer for Claude Code — distills skills from your real sessions, updates them as you work, and prunes the ones that stop getting used. No daemon, no benchmark.

    github

    Installieren /plugin marketplace add tigerless-labs/autoharness

    Ressourcegemessenes Wachstum
    1 391GitHub-Sterne+119 (+9.4 %)
  2. 2
    AktivQuelle öffnen ↗

    🌊 The original agent meta-harness. Deploy intelligent multi-player swarms, coordinate autonomous workflows, and build conversational AI systems. Features adaptive memory, self-learning intelligence, RAG integration, and native Claude Code /…

    githubRessourcegemessenes Wachstum
    70 157GitHub-Sterne+668 (+0.96 %)