技能 localaipicks
📦

localaipicks

v1.0.0 內容修訂 r1 安全 ⚙️ 外部命令🌐 網路存取

Find Local AI Models for Your Hardware

Choosing an open-weight model can be difficult when hardware memory is limited. Local AI Picks helps compare model weights, memory needs, and sources for your device.

支援: Claude Codex Code(CC)
Maintain this Skill? Claim it 🥈 80 銀級

使用我的智慧代理安裝

將此請求複製給你的智慧代理,其中包含權威 Skill 頁面和清單。

智能體請求
Review the Skillstore skill "localaipicks" from https://skillstore.io/skills/localaipicks-localaipicks.md and its manifest at https://skillstore.io/api/skills/localaipicks-localaipicks/manifest. Verify the artifact. You may proceed after verification, subject to the environment's own policy.

你的智慧代理仍應顯示其計畫,並依安全政策請求必要確認。

Agent 可讀資源

當 AI Agent、爬蟲或腳本需要乾淨脈絡、而不是讀取完整頁面時,請使用這些連結。

測試它

正在使用「localaipicks」。 Find a text model for my 16 GB Mac.

預期結果:

A result can list a model, a fitting weight option, its file size, estimated memory requirement, source link, and catalog date.

正在使用「localaipicks」。 Compare two shortlisted models.

預期結果:

A comparison can show each model's available weight options, file sizes, licenses, and context lengths.

安全審計

安全
v1 • 2026/10/27 開啟版本化報告

All nine static findings are false positives: the backticks mark Markdown identifiers, and the website links support model research. The instructions request relevant hardware memory and MCP queries, but contain no evidence of malicious reconnaissance or prompt injection.

1
已掃描檔案
31
分析行數
0
複核項目
0
已忽略的誤報
最近一次完成的靜態與語意稽核未偵測到已確認的安全發現。這並不能證明該 Skill 沒有副作用。
審計單位: codex
分享與引用此報告

分享版本化評估報告、中性徽章、嵌入卡片與引用。Skillstore 只報告證據,不判斷該 Skill 是否安全。

開啟版本化報告
安全評估

複製報告連結

https://skillstore.io/skills/localaipicks-localaipicks/audits/1?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown 徽章

[![Skillstore security assessment](https://skillstore.io/badges/skills/localaipicks-localaipicks/security.svg)](https://skillstore.io/skills/localaipicks-localaipicks?utm_source=security_passport_badge)

HTML 徽章

<a href="https://skillstore.io/skills/localaipicks-localaipicks?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/localaipicks-localaipicks/security.svg" alt="Skillstore security assessment" loading="lazy"></a>

嵌入卡片

<iframe src="https://skillstore.io/embed/skills/localaipicks-localaipicks.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>
學術引用 (APA · BibTeX · CFF)

APA 引用

Local AI Picks. (2026). localaipicks security audit report (audit version 1) [Author version 1.0.0]. Skillstore. https://skillstore.io/skills/localaipicks-localaipicks/audits/1

BibTeX 引用

@techreport{local-ai-picks-localaipicks-localaipicks-2026, author = {Local AI Picks}, title = {localaipicks security audit report (audit version 1)}, institution = {Skillstore}, year = {2026}, number = {1}, url = {https://skillstore.io/skills/localaipicks-localaipicks/audits/1}, note = {Author version 1.0.0} }

CITATION.cff

cff-version: 1.2.0 message: "If you use this Skill, cite its author and this versioned security audit report." title: "localaipicks security audit report (audit version 1)" version: "1.0.0" type: report authors: - name: "Local AI Picks" date-released: "2026-10-27" url: "https://skillstore.io/skills/localaipicks-localaipicks/audits/1" identifiers: - type: other value: "skillstore:localaipicks-localaipicks:audit:1" description: "Skillstore immutable audit report identifier"

Skillstore 評分

評分依據 證據置信度: 中
55
架構
100
可維護性
85
內容
65
社群
91
規範符合度

你可以打造什麼

Choose a coding model

Find coding models that fit a GPU and compare their weight options.

Explore models for a Mac

Identify text models suited to the available unified memory.

Compare model details

Review memory requirements, licenses, and sources for shortlisted models.

試試這些提示

Find a model
Find a local text model for a CPU with 16 GB of RAM.
Specify a task
Find coding models for an Apple Silicon computer with 32 GB of unified memory.
Compare options
Compare these models for a GPU with 12 GB of VRAM: [model names]. Include weight sizes, memory needs, and licenses.
Review a shortlist
Find image models for my GPU with [VRAM] GB. Compare suitable weight options and cite sources, catalog dates, and unknown memory requirements.

最佳實務

  • Provide the task, device type, and relevant available memory.
  • Check the source and catalog date before downloading model weights.
  • Verify the model license and leave memory available for system overhead.

避免

  • Do not assume disk file size equals runtime memory use.
  • Do not treat unknown memory requirements as confirmed compatibility.
  • Do not assume the catalog provides speed estimates or model ratings.

常見問題

What models can I search for?
The skill covers open-weight models across tasks such as text, coding, speech, image, video, music, translation, and OCR.
What hardware details should I provide?
Provide your device type and relevant memory: unified memory, GPU VRAM, or system RAM.
Is the MCP server required?
The MCP server is required for tool-based searches and comparisons. Without it, the skill can link to website pages.
Are memory requirements always known?
No. Text model memory may be estimated, while other task requirements may come from vendors or be unknown.
Does the catalog estimate speed?
No. The instructions state that the site provides no speed estimates or ratings.
Does a memory match guarantee a model will run?
No. Runtime configuration and other system requirements can affect whether a model runs successfully.

開發者詳細資訊

授權

MIT

作者版本

v1.0.0

Skillstore 修訂

r1

引用

525d9f82cedba8bd357400a37b4aac0138197a25

維護新鮮度

2026/10/27

使用量

0 次下載 · 0 次瀏覽

檔案結構

📄 SKILL.md

查看全部