← All topics

Agents

Designing, evaluating, and shipping autonomous AI agents.

9629 posts

Claude Skill 2

An evidence-driven Codex skill that fixes the defect pattern behind a GitHub review comment without expanding beyond the validated cause.

Python MIT Updated 2w ago
Claude Skill 2

Turn a research idea into a literature-grounded, tutorial-like standalone HTML essay. An Agent Skill: works in Claude Code, Codex, Cursor, G...

Python MIT Updated 3w ago
Claude Skill 2

炼金书:输入一本书,得到一位懂这本书的顾问。把任何非虚构书蒸馏成可运行的方法论Skill(Agent Skills协议,跨runtime)

Python MIT Updated 3w ago
Claude Skill 2

Auditable agent skill for resolving protein queries, selecting references, and planning reproducible phylogenetic trees.

Python MIT Updated 3w ago
Claude Skill 2

Evidence-first Codex Agent Skills for JD analysis, truthful resume tailoring, A4 delivery, and portfolio curation.|用可追溯证据连接 JD 分析...

Python MIT Updated 3w ago
Claude Skill 2

A lightweight AI coding agent that lives entirely on Cloudflare. Persistent workspace, real shell, real git. Cheap by default (MiniMax), bri...

TypeScript MIT Updated 4w ago
Claude Skill 2

Dynamically assemble dependency-aware AI teams for complex Codex tasks and decisions.

Python MIT Updated 1mo ago
Claude Skill 2

The agent-agnostic AI tutor skill that writes into your Obsidian vault — works with Claude Code, Codex, Cursor, Windsurf, pi, and 70+ agents...

TypeScript MIT Updated 2w ago
Claude Skill 2

Build agent skills that demonstrably change behaviour: a linter that rejects skills that cannot work, a scaffold that passes it, and an eval...

TypeScript MIT Updated 2w ago
Claude Skill 2

Crux is an evidence-governed AI skill and policy core for deep reading, research coaching, and consequential decisions.

Python MIT Updated 2w ago
Claude Skill 2

Modular agent skills for Jobs-to-be-Done and Outcome-Driven Innovation research.

Python MIT Updated 1mo ago