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/majiayu000/claude-skill-registry --skill covariant-fibrations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。
LLM token logprobs and calibration. Per-decision confidence, ECE, Brier, reliability diagrams, low-confidence triage.
Analyze LLM token logprobs and calibration. Use for per-decision confidence, ECE, Brier scores, reliability diagrams, and low-confidence triage.
回顾最近 N 天的 Claude Code 使用记录——扫描原始会话数据,按主题分组汇总"我都做了什么",并从个人操作系统视角输出模式、风险与增删建议。当用户说 /recap、"看看我这几天做了什么"、"回顾一下我最近的会话"、"这两天我用 claude 干了啥"、"活动回顾" 时使用。
基于 SOC 职业分类
正在显示 SKILL.md
| name | covariant-fibrations |
| description | Riehl-Shulman covariant fibrations for dependent types over directed |
| version | 1.0.0 |
Status: ✅ Production Ready Trit: -1 (MINUS - validator/constraint) Color: #2626D8 (Blue) Principle: Type families respect directed morphisms Frame: Covariant transport along 2-arrows
Covariant Fibrations are type families B : A → U where transport goes with the direction of morphisms. In directed type theory, this ensures type families correctly propagate along the directed interval 𝟚.
For P : A → U covariant fibration:
transport_P : (f : Hom_A(a, a')) → P(a) → P(a')
Covariance: transport respects composition
transport_{g∘f} = transport_g ∘ transport_f
-- Directed type theory (Narya-style)
covariant_fibration : (A : Type) → (P : A → Type) → Type
covariant_fibration A P =
(a a' : A) → (f : Hom A a a') → P a → P a'
-- Transport along directed morphisms
cov-transport : {A : Type} {P : A → Type}
→ is-covariant P
→ {a a' : A} → Hom A a a' → P a → P a'
cov-transport cov f pa = cov.transport f pa
-- Functoriality
cov-comp : cov-transport (g ∘ f) ≡ cov-transport g ∘ cov-transport f
-- Cocartesian lift characterizes covariant fibrations
is-cocartesian : {E B : Type} (p : E → B)
→ {e : E} {b' : B} → Hom B (p e) b' → Type
is-cocartesian p {e} {b'} f =
Σ (e' : E), Σ (f̃ : Hom E e e'), (p f̃ ≡ f) × is-initial(f̃)
-- Covariant families over Segal types
covariant-segal : (A : Segal) → (P : A → Type) → Type
covariant-segal A P =
(x y z : A) → (f : Hom x y) → (g : Hom y z) →
cov-transport (g ∘ f) ≡ cov-transport g ∘ cov-transport f
# Validate covariance conditions
just covariant-check fibration.rzk
# Compute cocartesian lifts
just cocartesian-lift base-morphism.rzk
# Generate transport terms
just cov-transport source target
covariant-fibrations (-1) ⊗ directed-interval (0) ⊗ synthetic-adjunctions (+1) = 0 ✓ [Transport]
covariant-fibrations (-1) ⊗ elements-infinity-cats (0) ⊗ rezk-types (+1) = 0 ✓ [∞-Fibrations]
Skill Name: covariant-fibrations Type: Directed Transport Validator Trit: -1 (MINUS) Color: #2626D8 (Blue)
This skill connects to the K-Dense-AI/claude-scientific-skills ecosystem:
homotopy-theory: 29 citations in bib.duckdbThis skill connects to Software Design for Flexibility (Hanson & Sussman, 2021):
Concepts: propagator, cell, constraint, bidirectional, TMS
covariant-fibrations (+) + SDF.Ch7 (○) + [balancer] (−) = 0
Skill Trit: 1 (PLUS - generation)
Propagators flow constraints bidirectionally. This skill propagates information.
This skill maps to Cat# = Comod(P) as a bicomodule in the equipment structure:
Trit: 0 (ERGODIC)
Home: Prof
Poly Op: ⊗
Kan Role: Adj
Color: #26D826
The skill participates in triads satisfying:
(-1) + (0) + (+1) ≡ 0 (mod 3)
This ensures compositional coherence in the Cat# equipment structure.