Self-improvement feedback loop for AI agent skills — analyzes past sessions, drafts structured improvement proposals, and gates auto-apply b...
#ai-agents
3671 posts
Branch-aware AI grilling with user-controlled follow-up ceilings and adaptive early stopping
Drive a phased implementation plan from a Claude Code session, including from your phone. Plan in markdown, one PR per phase, gated auto-mer...
Production-grade GitHub skill for AI agents to architect, audit, secure, automate, document, and maintain repositories, workflows, releases,...
Curated Claude Skills, actually tested — not just linked. Every skill is read in full, trimmed of Claude Code-only dependencies, checked aga...
Deterministic geometry diagram DSL for AI agents — text in, precise math figures out (SVG/PNG). Zero-dependency compiler + Claude/Codex/agen...
面向 Claude Code、Codex 与 WorkBuddy 的开源财务 Skill 工具集:本地、确定性地完成对账与差异复核,原始明细默认不进入模型上下文。
Local CLI that turns noisy command output into compact, redacted summaries for developers and coding agents.
Give your AI agents persistent memory and session continuity in your Obsidian vault — a conversational interview scaffolds the memory files,...
An opinionated Claude operating system for PM-led engineering. Planning, enrichment, delegated execution, staged review, ship decisions, dur...
A curated, safety-conscious collection of reusable Grok-compatible agent skills for workflow automation, research, integrations, and quality...
Official-doc-first Yocto Project and BitBake skills for AI coding agents