用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/sancovp/dinf --skill 0-3-1-loop-closure-attention-1命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
[0] dinf: in the dinf domain: frame the task, recall a proven dinf chain, choose exploit (select a golden chain) vs explore (construct a new one), execute it, record the reward
How the bandit (the default ChainSelector persona) rolls up the AC→CoR→SC algebra and CLOSES it into a domain-specific persona — a self-contained "bandit chain system" that builds its own KB and improves itself via GlyphSteer chains. Use when asked to mint a domain agent, "roll up an algebra", close a chain system, make a self-improving persona, or hierarchicalize the bandit over its own parts.
[0.2] the dinf default workflow (BanditChain) — walk it
基于 SOC 职业分类
正在显示 SKILL.md
| name | 0.3.1-loop-closure-attention-1 |
| description | ["0.3.1"] |
| loop-closure | seal the stop condition before the worker starts, then price one verified task |
This is an attention chain — an INNER template for how to think about something (a scaffold for a section or for your thinking). Not necessarily spoken.
[Stop] ⇒ [Fingerprint] ⇒ |Sealed|
Attend, in order:
(leaf — this is an actual skill.)