Mit Code-Assistenten verknüpfte gemessene Katalogeinträge.
Agent skills and an AGENTS.md workflow template — isolate in worktrees, build to a service layer, prove with evidence, ship with before/after proof and Greptile review loops. For Claude Code, Cursor, and Codex.
Sterne1.382Gemessen · 25.10.2026
Momentum39,37 Tage · Gemessen · +1,69% relative Änderung
复刻网站的 Agent Skill：抓只读镜像、从压缩代码逐行还原、自动比对验收。An agent skill that mirrors a website, rebuilds it from the minified code, and verifies the result with automated diffs.
Sterne1.558Gemessen · 26.10.2026
Momentum39,27 Tage · Gemessen · +1,56% relative Änderung
Free Claude skill that audits, builds and improves other skills against Anthropic's skill-writing rules, including what changed for Opus 5.5, Sonnet 5.5 and Fable 5.
Sterne69Gemessen · 26.10.2026
Momentum39,27 Tage · Gemessen · +9,52% relative Änderung
Local-first, agent-native control plane for ComfyUI — MCP server + sidebar agent that generates images, video & audio, authors and runs workflows, and edits your live graph in natural language on ANY LLM (Claude, ChatGPT, Gemini, offline Ollama, or any hosted model). 178 tools, 36 AI skills, 55 installer packs. Local, LAN, VPS, or Comfy Cloud.
Sterne863Gemessen · 26.10.2026
Momentum39,17 Tage · Gemessen · +2,25% relative Änderung
✨ All your agents and workspaces in one place, on every device you own. Track tasks on a board, accessible from desktop, mobile, browser, or API. Self-hosted.
Sterne8.191Gemessen · 26.10.2026
Momentum397 Tage · Gemessen · +0,48% relative Änderung
公务员与事业单位 AI 备考技能：行测、申论、职测、综应、公基、公文、面试与错题复盘。免费开源，支持 Agent Skills 和单文件使用。
Sterne202Gemessen · 26.10.2026
Momentum397 Tage · Gemessen · +5,21% relative Änderung
Audits AI-generated frontend and rewrites it so it stops looking AI-made: purple-gradient slop and the "tasteful" defaults (cream + terracotta, mono chrome). Zero-dependency scanner included. The design counterpart to avoid-ai-writing.
Sterne127Gemessen · 26.10.2026
Momentum38,97 Tage · Gemessen · +6,72% relative Änderung
Spec-driven development for Claude Code, layered on OpenSpec. You read one spec; parallel agents ship it to a tested commit.
Sterne33Gemessen · 26.10.2026
Momentum38,97 Tage · Gemessen · +13,79% relative Änderung
README design skill for Claude Code & Codex. 帮你把 GitHub README 做得好看又好懂。
Sterne1.910Gemessen · 26.10.2026
Momentum38,87 Tage · Gemessen · +1,33% relative Änderung
Make your agents talk human. ADHD-friendly output styles for Claude Code, Codex, and others. So you can pay attention, not tokens.
Sterne1.501Gemessen · 26.10.2026
Momentum38,87 Tage · Gemessen · +1,56% relative Änderung