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/RunnerQuan/SAFE-Agent --skill narya-hatchery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。
正在显示 SKILL.md
基于 SOC 职业分类
| name | narya-hatchery |
| description | Narya Hatchery |
| version | 1.0.0 |
Narya is a proof assistant implementing Multi-Modal, Multi-Directional, Higher/Parametric/Displayed Observational Type Theory.
-- Observational identity via bridges
bridge : (A : Type) → (x y : A) → Bridge x y → x ≡ y
Narya supports higher-dimensional type theory where:
# Initialize with Narya's chromatic seed
gay_seed!(0xbfe738ce2e1c5f1f)
# P3 extension gamut learning
function loss(params, seed, target_gamut=:p3_extension)
color = forward_color(params, projection, seed)
return out_of_gamut_distance(color, target_gamut)
end
# From source
git clone https://github.com/mikeshulman/narya
cd narya
dune build
0xbfe738ce2e1c5f1fproofgeneral-narya (-1) ⊗ narya-hatchery (0) ⊗ gay-mcp (+1) = 0 ✓
proofgeneral-narya - Emacs integrationholes - Interactive proof developmentmove-narya-bridge - Move contract verificationThis skill connects to Software Design for Flexibility (Hanson & Sussman, 2021):
Concepts: eval, apply, interpreter, environment
narya-hatchery (−) + SDF.Ch5 (−) + [balancer] (−) = 0
Skill Trit: -1 (MINUS - verification)
Evaluation interprets expressions. This skill processes or generates evaluable forms.