MJorgin/skill-bartender

MJorgin★ 1PythonLast synced: 2026-08-17

Open on GitHub

Task-to-skill pairing for DeepSeek Harness — pours the minimal set (usually one; zero when plain tools suffice), prefers workflow skills over hand-composed atomics. Laziness ladder, quarantine → SkillSpector scan → explicit human approval, never auto-installs. 任务配技能 · 懒惰阶梯 · 安全酒窖 · 绝不自动安装

README excerpt

🍸 skill-bartender Mix the right skill cocktail for every task — and never pour an untasted bottle. Your agent already sees a catalog of skill names and descriptions — but it over-pours : loads too many skills, loads the wrong ones, or misses the one workflow skill that composes the task. skill-bartender is the meta-skill that fixes the pour: - 🪜 Laziness ladder — zero skills when plain tools suffice; one skill when one matches; workflow over hand-composed atomics; unsure → don't load. - 🍷 Routing table — a user-editable task→skill map ( references/policy.md ) that overrides the defaults. - 🔐 Safe cellar — a needed skill missing? Quarantine → SkillSpector scan → explicit human approval → install. Never auto-installs. - 🧠 Learn — loaded-but-unused skills get logged and skipped next time. - 🧪 Taste test — audit installed skills and rewrite weak descriptions into "when-to-use" sentences. Why · What you get · Quick start · See it in action · Usage · Security model · FAQ · Examples · Layout · License English · 简体中文 🤔 Why Most agents treat the skill catalog as an all-you-can-eat buffet. skill-bartender treats it as a bar with a taste test: skill-bartender Typical catalog behavior S…

View full README on GitHub →
Agentsagent-skillsclaude-codecodexdeepseek-harnessdsh-pluginprompt-injectionsecurity

Category