Die Werkzeugbeschreibungen sind auf Englisch.

Programmierassistenten

Programmierassistenten und Werkzeuge zur Codegenerierung.

Anwendungsfall

Aktivität

Sortieren nach

199

Werkzeug-Rangliste

Ranked by creation date, newest first; undated entries come last. Rohwerte behalten ihr eigenes Zeitfenster; eine Änderung erfordert mindestens zwei Messungen in 7 Tagen.

  1. 1

    Skill
    Aktiv

    LLM agents as your hyperparameter optimizer.

    githubgemessenes WachstumQuelle öffnen ↗

    Installieren git clone https://github.com/Optim-Agent/optim-agent ~/.claude/skills/optim-agent

    936GitHub-Sterne+3 (+0.32 %)
  2. 2
    Aktiv

    Feed your agent papers and half-formed ideas — it links them into a system design you can defend. Markdown keeps the record; a visual canvas makes it readable. An Agent Skill for Claude Code & any SKILL.md-compatible agent.

    githubgemessenes WachstumQuelle öffnen ↗

    Installieren /plugin marketplace add tigerless-labs/design-harness

    213GitHub-Sterne+2 (+0.95 %)
  3. 3

    Skill
    Aktiv

    The Fable Workflow: how Claude Fable 5 worked, distilled into skills any model can run, with the eval that keeps it honest. Think / act / prove.

    githubgemessenes WachstumQuelle öffnen ↗

    Installieren git clone https://github.com/Sahir619/fable-method ~/.claude/skills/fable-method

    2 272GitHub-Sterne+16 (+0.71 %)
  4. 4
    Aktiv

    A browser inside your terminal

    githubgemessenes WachstumQuelle öffnen ↗

    Installieren git clone https://github.com/zenbu-labs/terminal-browser ~/.claude/skills/terminal-browser

    2 519GitHub-Sterne+166 (+7.1 %)
  5. 5

    Agent
    Aktiv

    A terminal workbench in pure Rust: shells, persistent sessions, SSH, coding agents. GPU-rendered on Zed's gpui, VT core from Alacritty.

    githubgemessenes WachstumQuelle öffnen ↗

    805GitHub-Sterne+11 (+1.4 %)
  6. 6
    Aktiv

    11 installable skills for Claude Code, OpenAI Codex, and Hermes, for finding your unknowns before they get expensive: blindspot pass, brainstorms, interviews, references, plans, notes, pitches, a merge quiz, plus a context audit, agent…

    githubgemessenes WachstumQuelle öffnen ↗

    Installieren git clone https://github.com/Neeeophytee/finding-unknowns-skills ~/.claude/skills/finding-unknowns-skills

    321GitHub-Sterne+4 (+1.3 %)
  7. 7

    MCP
    Aktiv

    Turbocharge Claude Code, Cursor, Codex, Gemini & every coding agent: faster, cheaper, with contextual understanding specific to your codebase.

    githubgemessenes WachstumQuelle öffnen ↗

    5 449GitHub-Sterne+435 (+8.7 %)
  8. 8

    Sonstige
    Aktiv

    OkkMax — independent review & directory for AI API relay providers: authenticity checks that catch silent model swaps, uptime monitoring, real user reviews. okkmax.com

    githubgemessenes WachstumQuelle öffnen ↗

    256GitHub-Sterne-3 (-1.2 %)
  9. 9
    Aktiv

    Turn project work into reusable knowledge — an AI-agent skill for Claude Code & Codex

    githubgemessenes WachstumQuelle öffnen ↗

    Installieren git clone https://github.com/iBlinkQ/project-cairn ~/.claude/skills/project-cairn

    219GitHub-Sterne+3 (+1.4 %)
  10. 10
    Aktiv

    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.

    githubgemessenes WachstumQuelle öffnen ↗

    Installieren git clone https://github.com/isjiamu/gzh-design-skill ~/.claude/skills/gzh-design-skill

    3 474GitHub-Sterne+120 (+3.6 %)
  11. 11

    Skill
    Aktiv

    Forward deployed engineering skills for AI coding agents.

    githubgemessenes WachstumQuelle öffnen ↗

    Installieren git clone https://github.com/suboss87/FDEOps ~/.claude/skills/FDEOps

    214GitHub-Sterne-3 (-1.4 %)
  12. 12
    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+57 (+17.2 %)
  13. 13
    Aktiv

    Living project docs for coding agents: keep guides, progress logs, change maps, and handoff context updated as your repo evolves.

    githubgemessenes WachstumQuelle öffnen ↗

    Installieren git clone https://github.com/YurunChen/repo-docs-skills ~/.claude/skills/repo-docs-skills

    456GitHub-Sterne-3 (-0.65 %)
  14. 14
    Aktiv

    A skill for AI agents: search the web with SearXNG, browse with Camofox, bypass protections with CloakBrowser. Anti-hallucination by design. Self-hosted, free, unlimited.

    githubgemessenes WachstumQuelle öffnen ↗

    Installieren git clone https://github.com/Johell1NS/browser-search ~/.claude/skills/browser-search

    512GitHub-Sterne+12 (+2.4 %)
  15. 15

    Skill
    Aktiv

    Stop wasting tokens and re-explaining your project every session. Recall gives Claude Code durable memory — entirely offline.

    githubgemessenes WachstumQuelle öffnen ↗

    Installieren /plugin marketplace add raiyanyahya/recall

    744GitHub-Sterne-1 (-0.13 %)
  16. 16

    Skill
    Aktiv

    mission control for agent skills

    githubgemessenes WachstumQuelle öffnen ↗

    Installieren git clone https://github.com/alvinunreal/lazyskills ~/.claude/skills/lazyskills

    240GitHub-Sterne-1 (-0.41 %)
  17. 17
    Aktiv

    Claude Code plugin: run the Antigravity CLI (Gemini) as a collaborating sub-agent with intelligent model routing across the SDLC. Community project; not affiliated with Google/Anthropic.

    githubgemessenes WachstumQuelle öffnen ↗

    Installieren /plugin marketplace add yuting0624/antigravity-for-claude-code

    296GitHub-Sterne+9 (+3.1 %)
  18. 18

    Sonstige
    Aktiv

    Universal provider proxy for OpenAI Codex & Claude Code — use any LLM (Claude, Gemini, Grok, DeepSeek, Ollama…) with Codex CLI, App, SDK, and Claude Code

    githubgemessenes WachstumQuelle öffnen ↗

    13 073GitHub-Sterne+716 (+5.8 %)
  19. 19

    Agent
    Aktiv

    Design visual, review-gated agent loops for Claude Code before you run them.

    githubgemessenes WachstumQuelle öffnen ↗

    707GitHub-Sterne-1 (-0.14 %)
  20. 20
    Aktiv

    Give your AI a real, persistent memory. The open-source system plus templates that turn an Obsidian vault into your AI's working memory. No vector database, just markdown.

    githubgemessenes WachstumQuelle öffnen ↗

    Installieren git clone https://github.com/jaredrhod/ai-memory-vault ~/.claude/skills/ai-memory-vault

    605GitHub-Sterne+13 (+2.2 %)
  21. 21
    Aktiv

    Teach your AI to draw correct, beautiful draw.io diagrams — declarative layout engine, ground-truth stencils, structural validator, vision self-check. AWS · Azure · GCP · Databricks · BPMN. Zero dependencies.

    githubgemessenes WachstumQuelle öffnen ↗

    Installieren git clone https://github.com/sparklabx/drawio-ai-kit ~/.claude/skills/drawio-ai-kit

    638GitHub-Sterne+3 (+0.47 %)
  22. 22

    Skill
    Aktiv

    A Boris-style agentic orchestrator TUI that supervises headless Claude Code agents through a gated software-delivery pipeline — pointed at any repository.

    githubgemessenes WachstumQuelle öffnen ↗

    Installieren git clone https://github.com/VisionForge-OU/foreman ~/.claude/skills/foreman

    447GitHub-Sternestabil
  23. 23
    Aktiv

    The trust layer for agent-to-agent commerce — natural-language mandates, ERC-7710 delegated permissions, x402 payments, escrow, and dispute resolution as one open, catch-all Agent Skill / Claude Code plugin.

    githubgemessenes WachstumQuelle öffnen ↗

    Installieren git clone https://github.com/internet-court/internet-court-skill ~/.claude/skills/internet-court-skill

    5 262GitHub-Sterne+319 (+6.5 %)

Lern- und Referenzressourcen

Ranked by creation date, newest first; undated entries come last. Diese Ressourcen bleiben getrennt zugänglich und fließen nicht in die Hauptwertung ein.

  1. 1

    engram

    Skill
    AktivQuelle öffnen ↗

    Evidence-based learning engine — first-principles curricula, free-recall verification with receipts, FSRS-scheduled memory, and explorable artifacts. Learn anything; keep it.

    github

    Installieren /plugin marketplace add nagisanzenin/engram

    Ressourcegemessenes Wachstum
    1 391GitHub-Sterne+15 (+1.1 %)
  2. 2
    AktivQuelle öffnen ↗

    67 game-dev skills for AI coding agents — Godot, Unity, Unreal, Phaser, PixiJS, three.js, Bevy, pygame, LÖVE, Roblox. Portable SKILL.md Agent Skills (the format Anthropic launched as Claude Skills), with a router that loads the right skill…

    github

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

    Ressourcegemessenes Wachstum
    788GitHub-Sterne+112 (+16.6 %)