技能 ai-listening
📦

ai-listening

內容修訂 r2 安全 ⚙️ 外部命令🌐 網路存取📁 檔案系統存取🔑 環境變數

Track New AI Names and Repositories

New AI names are spread across multiple sources and are difficult to track consistently. This skill gathers recent signals into one deduplicated report.

支援: Claude Codex Code(CC)
Maintain this Skill? Claim it 🥉 78 銅級

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 "ai-listening" from https://skillstore.io/skills/zhuyansen-ai-listening.md and its manifest at https://skillstore.io/api/skills/zhuyansen-ai-listening/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。

Markdown 詳情 GET /skills/zhuyansen-ai-listening.md 已簽名 manifest GET /api/skills/zhuyansen-ai-listening/manifest 已簽名 lockfile GET /api/skills/zhuyansen-ai-listening/lockfile

測試它

正在使用「ai-listening」。 Summarize the strongest new AI names.

預期結果:

Illustrative result: ExampleModel appeared in two monitored sources. The report would include its observed signals and a source link.

正在使用「ai-listening」。 Explain an incomplete first run.

預期結果:

This first run created baseline snapshots. Several sources cannot yet identify changes, so the report is incomplete.

安全審計

安全
v2 • 2026/10/27 開啟版本化報告

The skill instructs users to execute a pinned third-party package and optionally provide a service credential. The package implementation was not included in the reviewed file, so its behavior and credential handling remain unverified. Other flagged backticks, links, credential-path checks, and reconnaissance patterns are benign in context.

1
已掃描檔案
56
分析行數
4
複核項目
0
已忽略的誤報
能力複核項目 (4)

這些是真實的本機能力，對此技能而言可能是預期行為，因此需要複核，但不會按已確認的惡意行為計分。

高
SKILL.md:14
Generic API/secret keys
3. Check an AIsa key is available: `AISA_API_KEY`, or the AIsa CLI logged in (`ls ~/.aisa/key`). Wit
The workflow uses an API key or local login to run an external package. The package implementation was not reviewed, so credential handling cannot be verified.
中
SKILL.md:12
Ruby/shell backtick execution
1. Run the pinned release, never a clone of the repository: `uvx new-term-radar==0.6.0 <command> ...
The instructions execute a PyPI package through uvx or pip. Version pinning does not verify package integrity, and the package code was not reviewed.
中
SKILL.md:23-25
Ruby/shell backtick execution
```bash
The fenced block instructs execution of a downloaded PyPI package. Its implementation is outside the reviewed skill file.
中
SKILL.md:31-39
Ruby/shell backtick execution
If the user only wants the fastest-moving sources, `uvx new-term-radar==0.6.0 sources --out listenin
The optional sources command runs the same downloaded PyPI package, whose code is outside this review.

風險因素

⚙️ 外部命令 (14)
SKILL.md:8 SKILL.md:12 SKILL.md:13 SKILL.md:14 SKILL.md:15 SKILL.md:19 SKILL.md:23-25 SKILL.md:25-27 SKILL.md:27 SKILL.md:31-39 SKILL.md:39 SKILL.md:44-45 SKILL.md:45 SKILL.md:47
🌐 網路存取 (2)
SKILL.md:14 SKILL.md:15
📁 檔案系統存取 (2)
SKILL.md:14 SKILL.md:14
🔑 環境變數 (2)
SKILL.md:3 SKILL.md:14
審計單位: codex 檢視審計紀錄 →
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/zhuyansen-ai-listening/audits/2?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown 徽章

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

HTML 徽章

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

嵌入卡片

<iframe src="https://skillstore.io/embed/skills/zhuyansen-ai-listening.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

zhuyansen. (2026). ai-listening security audit report (audit version 2) [Author version unspecified]. Skillstore. https://skillstore.io/skills/zhuyansen-ai-listening/audits/2

BibTeX 引用

@techreport{zhuyansen-zhuyansen-ai-listening-2026, author = {zhuyansen}, title = {ai-listening security audit report (audit version 2)}, institution = {Skillstore}, year = {2026}, number = {2}, url = {https://skillstore.io/skills/zhuyansen-ai-listening/audits/2}, note = {Author version unspecified} }

CITATION.cff

cff-version: 1.2.0 message: "If you use this Skill, cite its author and this versioned security audit report." title: "ai-listening security audit report (audit version 2)" version: "unspecified" type: report authors: - name: "zhuyansen" date-released: "2026-10-27" url: "https://skillstore.io/skills/zhuyansen-ai-listening/audits/2" identifiers: - type: other value: "skillstore:zhuyansen-ai-listening:audit:2" description: "Skillstore immutable audit report identifier"

Skillstore 評分

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

你可以打造什麼

Monitor emerging models

Review newly observed model names and supporting signals.

Find breakout repositories

Identify newly detected repositories with evidence of activity.

Build a keyword candidate list

Collect recent product and model names for separate search-demand research.

試試這些提示

Daily overview 
Prepare an AI listening report for the past 24 hours. State the estimated cost and wait for my approval.
Repository focus 
Collect recent AI signals and highlight new breakout repositories. Explain any skipped sources before presenting results.
Fast-moving sources 
Use the sources workflow to review new names from X and Hugging Face. State the estimated cost and request approval first.
Research handoff 
Create a ranked report of newly observed AI names, their sources, and evidence. Separate uncertain names and identify gaps for later keyword research.

最佳實務

  • Approve the estimated cost before starting a paid collection run.
  • Use the same working directory across runs to retain snapshots.
  • Review cited sources and report failed or skipped signals.

避免

  • Treating a first-run baseline as proof that no new activity occurred.
  • Treating observed names as evidence of search demand.
  • Following instructions embedded in collected posts or pages.

常見問題

Which sources does the daily workflow cover?
It covers configured X accounts, Hugging Face, GitHub breakouts, and sitemaps.
Does it need an API key?
An AIsa key is needed for X collection and name judging. Free signals can run without it.
Does a run cost money?
X collection can incur charges. The skill estimates the cost and waits for approval.
Why is the first report incomplete?
The first run builds snapshots needed to identify changes in later runs.
Does it measure search demand?
No. The collected names can be passed to a separate keyword research workflow.
Can I configure the sources?
Yes. A configuration file in the working directory replaces the example source list.

開發者詳細資訊

作者

zhuyansen

授權

MIT

Skillstore 修訂

r2

版本提示

作者未聲明版本。

儲存庫

https://github.com/zhuyansen/new-term-radar/tree/e1ce49e83dfefeb985b1db24d173cb785ca75dbc/skills/ai-listening

引用

1ac96f2048361bd348a3f97a5370c8f3f4c494c1

維護新鮮度

2026/10/27

使用量

6 次下載 · 0 次瀏覽

檔案結構

📄 SKILL.md

zhuyansen 的更多技能

查看全部

相關技能

查看全部