Token导航 LogoToken导航

Agent Skill · 研究检索

asi-integrated(阿西综合)

asi-integrated 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

asi-integrated 是研究检索类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为执行命令;许可证信息还不明确,第三方扫描已通过,按安装量在研究检索类的 73,675 个 Skill 里排第 65,084。

总安装 288周安装 12GitHub Stars 17下载 96核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
unknown

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:asi-integrated(阿西综合)
来源仓库:https://github.com/plurigrid/asi
仓库路径:skills/asi-integrated
安装命令:
npx skills add https://github.com/plurigrid/asi --skill asi-integrated
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/plurigrid/asi --skill asi-integrated

这个 Skill 是做什么的

研究检索类 Skill 主要解决「找资料、核对事实、把来源整理清楚」的问题,通常会让助手先检索再总结。

asi-integrated 用于整合所有加载技能形成协调系统,支撑人工智能超级智能的技能编排。构建技能格点结构,支持导航、调度与确定性控制等多维度能力融合。通过 npx skills add 命令安装,适用于复杂 Agent 生态下的技能协同管理场景。使用前建议核验各子技能状态,避免因依赖缺失导致系统功能不完整。

适用宿主包括 Codex、Claude、Cursor、Gemini CLI,接入前应确认版本、权限和运行环境要求。

来源仓库内路径:skills/asi-integrated

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 Codex、Claude、Cursor、Gemini CLI;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 npx skills add https://github.com/plurigrid/asi --skill asi-integrated;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它需要执行命令,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

asi-integrated 怎么安装?

在终端执行 npx skills add https://github.com/plurigrid/asi --skill asi-integrated。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

asi-integrated 支持哪些 AI 工具?

公开资料标注支持 Codex、Claude、Cursor、Gemini CLI。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

asi-integrated 需要什么权限?

权限级别是执行命令。安装流程涉及命令执行,可能通过 npx skills add https://github.com/plurigrid/asi --skill asi-integrated 联网下载 Skill 或依赖。用户安装前应确认命令来源、仓库内容和执行环境。

asi-integrated 是免费的吗?

公开资料没有标注明确许可证,收费和商用限制都无法确认。正式使用前请到来源仓库核对授权说明。

asi-integrated 用的人多吗?

公开数据是累计安装 288 次,近一周安装 12 次,下载 96 次,GitHub 17 星。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

asi-integrated 安全吗?

第三方扫描结果为通过,但这只覆盖已知的静态检查项,不能替代自己读一遍源码和安装命令。

值得选的地方和要先想清楚的地方

值得选的地方

  • 同时适配 4 种工具,换客户端不用重新找替代品。
  • 第三方扫描已通过,常见的高风险行为没有命中。

先想清楚的地方

  • 需要执行命令,装到常用环境前要先评估影响面。
  • 许可证没有明确标注,能不能商用、能不能再分发都不确定。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 Codex,想直接扩展它能力的人。
  • 需要处理研究检索类任务、又不想每次都手写提示词的人。

不太适合

  • 不能接受 Skill 在你机器上执行命令的人。
  • 需要明确授权才能用到公司项目里的场景。
  • 需要厂商级技术支持和 SLA 的生产系统。

研究检索类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
find-skills

寻找技能 · Codex、Claude

31,199,81316,486操作浏览器MIT有提醒
self-improving-agent

自我改进 Agent · OpenClaw

16,464,0023,396接触敏感数据MIT-0通过
soultrace

灵魂追踪 · Codex、Claude

7,588,94412需要联网未明确有提醒
self-improving

自我完善 · OpenClaw

6,829,2841,046需要联网MIT-0通过
microsoft-foundry

微软代工厂 · Codex、Claude

6,614,144764调用外部服务未明确有提醒
asi-integrated

阿西综合 · 本页

28817执行命令未明确通过

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

ASI Integrated Skill

Synthesizes all loaded skills into a coherent system for Artificial Superintelligence skill orchestration.

Skill Lattice

                    ┌─────────────────┐
                    │  glass-bead-game │
                    │  (synthesis)     │
                    └────────┬────────┘
                             │
         ┌───────────────────┼───────────────────┐
         │                   │                   │
┌────────▼────────┐ ┌────────▼────────┐ ┌────────▼────────┐
│  world-hopping  │ │  bisimulation   │ │  triad-interleave│
│  (navigation)   │ │  (dispersal)    │ │  (scheduling)    │
└────────┬────────┘ └────────┬────────┘ └────────┬────────┘
         │                   │                   │
         └───────────────────┼───────────────────┘
                             │
                    ┌────────▼────────┐
                    │     gay-mcp      │
                    │  (deterministic  │
                    │   coloring)      │
                    └────────┬────────┘
                             │
                    ┌────────▼────────┐
                    │     acsets       │
                    │  (data model)    │
                    └─────────────────┘

Unified Protocol

1. Schema (ACSets)

@present SchASIWorld(FreeSchema) begin
  World::Ob
  Skill::Ob
  Agent::Ob

  source::Hom(World, World)
  target::Hom(World, World)

  has_skill::Hom(Agent, Skill)
  inhabits::Hom(Agent, World)

  Seed::AttrType
  Trit::AttrType

  seed::Attr(World, Seed)
  color_trit::Attr(Skill, Trit)
end

2. Color Generation (Gay-MCP)

from gay import SplitMixTernary, TripartiteStreams

def color_world(world_seed: int, skill_index: int) -> dict:
    gen = SplitMixTernary(world_seed)
    return gen.color_at(skill_index)

3. World Navigation (World-Hopping)

def hop_between_worlds(w1, w2, event_name: str):
    distance = world_distance(w1, w2)
    if valid_hop(w1, w2):
        event = Event(site=["skill"], name=event_name)
        return event.execute(w1)
    return None

4. Skill Dispersal (Bisimulation)

async def disperse_skill(skill_path: str, agents: list):
    game = BisimulationGame()
    for i, agent in enumerate(agents):
        trit = (i % 3) - 1  # GF(3) balanced
        game.attacker_move(agent, skill_path, trit)
        game.defender_respond(await agent.receive(skill_path))
    return game.arbiter_verify()

5. Parallel Execution (Triad Interleave)

def schedule_skill_updates(seed: int, n_agents: int):
    interleaver = TriadInterleaver(seed)
    schedule = interleaver.interleave(
        n_triplets=n_agents // 3,
        policy="gf3_balanced"
    )
    return schedule

6. Synthesis (Glass Bead Game)

def synthesize_skills(*skills):
    game = GlassBeadGame()
    for skill in skills:
        game.add_bead(skill.name, skill.domain)

    # Connect skills via morphisms
    game.connect("acsets", "gay-mcp", via="seed_to_color")
    game.connect("gay-mcp", "triad-interleave", via="color_stream")
    game.connect("triad-interleave", "bisimulation", via="schedule")
    game.connect("bisimulation", "world-hopping", via="dispersal")

    return game.score()

~/worlds Letter Index

LetterDomainKey Projects
aCategory TheoryACSets.jl, Catlab.jl, Decapodes.jl
bTerminalbmorphism/trittty
pInfrastructureplurigrid/oni, alpaca.cpp
tCollaborationCatColab
eHoTTinfinity-cosmos (Lean 4)
rType Theoryrzk (simplicial HoTT)
nKnowledgenlab-content
oMusicrubato-composer

GF(3) Conservation Law

All operations preserve:

∑ trits ≡ 0 (mod 3)

Across:

  • World hops (Attacker -1, Defender +1, Arbiter 0)
  • Color triplets (MINUS, ERGODIC, PLUS)
  • Schedule entries (balanced per triplet)
  • Skill dispersal (agent assignments)

Commands

# Generate integrated schedule
just asi-schedule 0x42D 10

# Disperse skills to all agents
just asi-disperse ~/.claude/skills/

# Verify GF(3) conservation
just asi-verify

# Play glass bead synthesis
just asi-synthesize a b p t

# World hop between letters
just asi-hop a t

Starred Gists: Fixpoint & Type Theory Resources

Curated from bmorphism's GitHub interactions:

zanzix: Fixpoints of Indexed Functors

Fix.idr - Idris indexed functor fixpoints for graphs, multi-graphs, poly-graphs.

data IFix : (f : (k -> Type) -> k -> Type) -> k -> Type where
  In : f (IFix f) i -> IFix f i

VictorTaelin: ITT-Flavored CoC Type Checker

itt-coc.ts - Intensional Type Theory CoC in TypeScript.

VictorTaelin: Affine Types

Affine.lean - Linear/affine type experiments in Lean 4.

rdivyanshu: Streams & Unique Fixed Points

Nats.dfy - Dafny streams with unique fixpoint theorems.

Keno: Abstract Lattice

abstractlattice.jl - Julia abstract lattice. Comment: "a quantum of abstract solace ∞"

norabelrose: Fast Kronecker Decomposition

kronecker_decompose.py - Optimal Kronecker decomposition.

borkdude: UUID v1 in Babashka

uuidv1.clj - Deterministic UUID generation in Clojure.

QuickCheck/Adhesive Rewriting Integration

Property-based testing connects to ASI through autopoietic generators:

# QuickCheck-style recursive generator with GF(3) conservation
function autopoietic_tree(seed::UInt64, depth::Int)
    rng = SplitMix64(seed)
    trit = mod(next_u64!(rng), 3) - 1

    if depth == 0 || trit == -1  # MINUS = terminate
        return Leaf(color_at(seed))
    else
        left_seed, right_seed = split(rng)
        return Node(
            trit = trit,
            left  = autopoietic_tree(left_seed, depth-1),
            right = autopoietic_tree(right_seed, depth-1)
        )
    end
end

Shrinking as Adhesive Complement

QuickCheck shrinking = finding minimal ∼Q_G in adhesive categories:

  • Decomposition: Q ≅ Q_G +_{Q_L} Q_R
  • Complement: ∼A is smallest subobject where X = A ∨ ∼A
  • Shrunk value = complement of failed portion

Transitive Closure (Kris Brown)

From Incremental Query Updating in Adhesive Categories:

path(X,Z) :- path(X,Y), edge(Y,Z).

Incremental update: When we apply rule to add path(a,b),
new matches = outgoing edges from b (rooted search)

References

Directory Tree

plurigrid/asi/
├── package.json
├── bin/cli.js
├── README.md
└── skills/
    ├── a/SKILL.md     # AlgebraicJulia
    ├── b/SKILL.md     # bmorphism
    ├── c/SKILL.md     # cognitect
    ├── d/SKILL.md     # claykind
    ├── e/SKILL.md     # infinity-cosmos
    ├── f/SKILL.md     # clojure-site
    ├── g/SKILL.md     # archiver-bot
    ├── h/SKILL.md     # gdlog
    ├── i/SKILL.md     # InverterNetwork
    ├── k/SKILL.md     # kubeflow
    ├── l/SKILL.md     # pretty-bugs
    ├── m/SKILL.md     # awesome-category-theory
    ├── n/SKILL.md     # nlab-content
    ├── o/SKILL.md     # oeis, rubato-composer
    ├── p/SKILL.md     # plurigrid
    ├── q/SKILL.md     # quadrat
    ├── r/SKILL.md     # rzk
    ├── s/SKILL.md     # mathematicians
    ├── t/SKILL.md     # CatColab
    ├── v/SKILL.md     # viro
    └── _integrated/   # This skill
        └── SKILL.md

Scientific Skill Interleaving

This skill connects to the K-Dense-AI/claude-scientific-skills ecosystem:

Graph Theory

  • networkx [○] via bicomodule

- Universal graph hub

Bibliography References

  • general: 734 citations in bib.duckdb

SDF Interleaving

This skill connects to Software Design for Flexibility (Hanson & Sussman, 2021):

Primary Chapter: 10. Adventure Game Example

Concepts: autonomous agent, game, synthesis

GF(3) Balanced Triad

_integrated (−) + SDF.Ch10 (+) + [balancer] (○) = 0

Skill Trit: -1 (MINUS - verification)

Secondary Chapters

  • Ch3: Variations on an Arithmetic Theme
  • Ch1: Flexibility through Abstraction
  • Ch4: Pattern Matching

Connection Pattern

Adventure games synthesize techniques. This skill integrates multiple patterns.

Cat# Integration

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

GF(3) Naturality

The skill participates in triads satisfying:

(-1) + (0) + (+1) ≡ 0 (mod 3)

This ensures compositional coherence in the Cat# equipment structure.

平台分布

Codex

35.22%
按下载量换算34

Claude

31.99%
按下载量换算31

Cursor

20.14%
按下载量换算19

Gemini CLI

8.63%
按下载量换算8

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

执行命令

安装流程涉及命令执行,可能通过 npx skills add https://github.com/plurigrid/asi --skill asi-integrated 联网下载 Skill 或依赖。用户安装前应确认命令来源、仓库内容和执行环境。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills