Designing, evaluating, and shipping autonomous AI agents.
9624 posts
面向 DeepSeek Harness 的可复核法律研究与法学论文工作流。
A local-first toolkit for testing agent experience in Agent-Native developer tools.
Batch-writing pipeline for academic monographs: AI-assisted, evidence-verified, script-validated. 学术专著批次化写作 AI 技能（Agent Skill）
通用中文创作与改稿 Codex Skill，先共创选题，再查材料，写出有活人感和中文韵律的作品。
A central library of reusable Lovable.dev skills
A Codex skill for evidence-grounded mathematical modeling problem interpretation.
A lean, event-driven coding skill for AI agents. Less over-engineering, zero ceremony, surgical diffs, and real evidence.
Provider-aware Agent Skill for evidence-based SaaS security audits and regression-safe hardening
HQE (/HQE) is a portable, production-grade agent skill that equips AI coding agents with the rigor, skepticism, and methodical precision of...
A bounded, hard-gated graph-engineered state machine, written as a skill — runs on any agent harness, tuned best for opencode so far： full...
Practical Agent Skill for Apple Liquid Glass design, implementation, review, and migration.
Search local Agent Skill collections without loading them all.
