Governance framework for AI coding agents. It runs them through a five-step workflow (plan, build, review, test, ship) where no step counts as done without evidence. Drop-in rules and guardrails for Claude Code, Codex, Cursor, Copilot, and Antigravity, via AGENTS.md.
Quelle
GitHub
Sprache
Python
Letzte Aktivität
20.10.2026
Sterne218Gemessen · 26.10.2026
Momentum24,77 Tage · Gemessen · +1,87% relative Änderung
Agent skills that make AI coding assistants write production-grade robotics software. ROS1, ROS2, design patterns, SOLID principles, and testing — for Claude Code, Cursor, Copilot, and any SKILL.md-compatible agent.
Quelle
GitHub
Sprache
Python
Letzte Aktivität
12.08.2026
Sterne385Gemessen · 26.10.2026
Momentum24,67 Tage · Gemessen · +1,32% relative Änderung
Thinking partner skill for AI agents — 150+ mental models, orientation detection, cognitive operations. Works with Claude Code, Cursor, Windsurf, Cline, GitHub Copilot.
Quelle
GitHub
Letzte Aktivität
31.03.2026
Sterne219Gemessen · 26.10.2026
Momentum24,67 Tage · Gemessen · +1,86% relative Änderung
Claude Code skill for recursive research up to PhD level across any domain. Source tiering, WDM + Munger inversion for autonomous decisions, and disk checkpointing to survive context compaction.
Quelle
GitHub
Letzte Aktivität
22.04.2026
Sterne52Gemessen · 26.10.2026
Momentum24,67 Tage · Gemessen · +4% relative Änderung
⚡ Cut Claude token usage by 90%+ — free, open-source, local-first context compression for Claude Code. Hybrid RAG (BM25 + ONNX vectors), AST chunking, reranking. No API needed.
Quelle
GitHub
Sprache
Python
Letzte Aktivität
02.05.2026
Sterne52Gemessen · 26.10.2026
Momentum24,67 Tage · Gemessen · +4% relative Änderung