← All topics

Agents

Designing, evaluating, and shipping autonomous AI agents.

7613 posts

Claude Skill 2

Email-sending capability for AI agents (ships as a Claude Code skill) and humans. Gmail sending runs server-side via Apps Script: idempotent...

Python MIT Updated 4w ago
Claude Skill 4

Standalone Agent Skill for delegating coding work to Factory Droid

Python MIT Updated 2w ago
Claude Skill 2

Guardrails, skills, loops, hooks & review agents for database + website builders on Claude Code (Next.js + Supabase).

Python MIT Updated 1mo ago
Claude Skill 2

Open source agent skills for evidence-first startup ideation: capture pains, grill assumptions, design validation tests, synthesize intervie...

Ruby MIT Updated 1mo ago
Claude Skill 2

Evidence-first engineering guardrails for coding agents: audit instructions, review change scope, record execution proof, and explain reposi...

Python MIT Updated 5d ago
Claude Skill 3

给 Codex 一篇论文、作者代码仓库,或者一个实验文件夹来复现整篇论文。并且这个 skill 会提醒 Codex:先检查数据、代码、实验流程和结果证据,然后严...

Python MIT Updated 1mo ago
Claude Skill 2

Predictive permissioning and approval ledgers for Codex, Claude Code, and coding agents

Python MIT Updated 1mo ago
Claude Skill 2

Open-source agent skill: scout product growth opportunities before you write code

TypeScript MIT Updated 1mo ago
Claude Skill 2

Stop your AI agent from lying about tests. Hierarchical engineering loops with machine-checkable proof gates.

Python MIT Updated 2w ago
Claude Skill 2

Prepare image datasets for LoRA training (Ostris AI Toolkit / Z-Image Turbo): quality checks, captioning (templates / Claude Vision / Floren...

Python MIT Updated 4w ago
Claude Skill 2

Trace a skill's family tree before installing — stars reflect ancestry, not which family member is best. 装 skill 前先修谱:Star 只代表血统...

Python MIT Updated 1mo ago