Token导航 LogoToken导航

Agent Skill · 研究检索

eonik-creative-audit(安尼克创意审核)

用于辅助安全审计、权限检查、凭据风险、认证流程和常见漏洞排查。它适合让 Agent 梳理敏感配置、检查依赖风险、分析鉴权逻辑或生成安全复核清单。使用时不能把工具输出直接当最终结论,涉及密钥、令牌、用户数据或生产系统时,应先确认最小权限、脱敏方式和操作边界。

eonik-creative-audit 是研究检索类 Agent Skill,可用宿主为 OpenClaw,通过ClawHub获取,权限为接触敏感数据;许可证为 MIT-0,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 9,428。

总安装 14,247周安装 582GitHub Stars 1下载 4,563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
MIT-0
版本
1.0.8

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:eonik-creative-audit(安尼克创意审核)
来源仓库:https://github.com/techievena/eonik-creative-audit
安装命令:
openclaw skills install eonik-creative-audit
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 OpenClaw 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。

ClawHubOpenClaw
openclaw skills install eonik-creative-audit

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。

用于运行 enik 创意审核引擎,识别广告创意疲劳、预算泄漏和扩展机会。适合在数字营销场景中辅助优化投放策略和提升 ROI。通过 OpenClaw 的 clawhub 安装,调用时需提供账户凭证和权限范围。输出结果需结合业务上下文判断,不可直接用于自动化决策。建议核实仓库维护状态及是否支持目标平台的数据源。

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 OpenClaw;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 openclaw skills install eonik-creative-audit;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

    它需要接触敏感数据,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

eonik-creative-audit 怎么安装?

在终端执行 openclaw skills install eonik-creative-audit。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

eonik-creative-audit 支持哪些 AI 工具?

公开资料标注支持 OpenClaw。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。

eonik-creative-audit 需要什么权限?

权限级别是接触敏感数据。该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

eonik-creative-audit 是免费的吗?

来源标注的许可证是 MIT-0。本站不代收任何费用,也不托管安装包;能否商用、要不要署名,以许可证原文为准。

eonik-creative-audit 用的人多吗?

公开数据是累计安装 14,247 次,近一周安装 582 次,下载 4,563 次,GitHub 1 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。

eonik-creative-audit 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

  • 专注 OpenClaw 一种宿主,触发方式和使用习惯不用来回切换。
  • 许可证明确为 MIT-0,商用和分发边界好判断。
  • 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

  • 需要接触敏感数据,装到常用环境前要先评估影响面。
  • 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 OpenClaw,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。
  • 需要许可证清楚、并且有第三方扫描结果的团队项目。

不太适合

  • 环境里有大量密钥、凭证,不方便给第三方 Skill 读取的人。
  • 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
eonik-creative-audit

安尼克创意审核 · 本页

14,2471接触敏感数据MIT-0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

name
eonik creative audit
slug
eonik-ad-budget-leak
version
1.0.8
description
Identifies creative fatigue, budget leaks, and scaling opportunities by running the eonik creative audit engine.
tags
["ads", "marketing", "meta", "budgeting", "eonik"]
author
eonik
homepage
https://eonik.ai
metadata
openclaw
requires
env
primaryEnv
EONIK_API_KEY

Meta Ads Creative Audit & Optimization

Automated end-to-end Meta Ads auditing pipeline. Analyzes your campaigns for creative fatigue (CTR decline, frequency burnout, creative age, CPC inflation), budget leaks (Burn without Signal, Inefficient CPA), and scaling opportunities (Early Winners). Dispatches multi-channel alerts directly to your team.

Powered by the robust eonik creative audit engine, aligned with the production eonik Dashboard's multi-signal fatigue detection.

Agent Instructions

When a user triggers this skill, you MUST follow these steps exactly:

  1. Check Configuration: Check if config.json exists in the local directory.
  2. Request Input (if needed): If config.json is missing, check if they want to run it on their default connected Meta account. Once confirmed, copy config.example.json to config.json (the Meta Account ID can be left blank as it auto-resolves).
  3. Execute Pipeline: Once config.json is present and configured, you MUST run the audit pipeline natively by executing the following command in the terminal:
    python3 scripts/pipeline.py --config config.json
  1. Display Results: After the script finishes, read the output report (typically output/audit-<date>.json) and provide a concise, formatted summary of the findings to the user. Do not invent details; only report what the script output contains.

Triggers

Use this skill when a user asks to:

  • "Audit my Meta ads"
  • "Check for budget leaks"
  • "Optimize my Meta ad account"
  • "Find decaying creatives"
  • "Run the eonik ad audit pipeline"

🚀 Unlock Full eonik Power

This skill is powered by the eonik intelligence engine. While this agent halts simple leaks autonomously, the full dashboard unlocks:

  • Creative Genome: Understand exactly *why* ads decay based on deep AI creative tagging.
  • Automated Rules: Prevent leaks without waiting for chat notifications.
  • Competitor Intelligence: See the exact hooks your competitors are scaling.

Get started for free at eonik.ai!

Quick Start

1. Configure

cd ~/.openclaw/skills/eonik-ad-budget-leak
cp config.example.json config.json
# Edit config.json: optionally add your Meta Account ID (or leave blank to auto-resolve)

2. Run Audit Pipeline

# EONIK_API_KEY must be in your environment
python3 scripts/pipeline.py --config config.json

Configuration

Minimal config.json:

{
  "meta": {
    "account_id": "",
    "evaluation_days": 30
  }
}

Pipeline Stages

  1. Audit (audit.py) — Executes the eonik creative audit engine via your EONIK_API_KEY.
  2. Output (pipeline.py) — Formats the response and outputs it natively through OpenCLAW to your active channel (WhatsApp/Discord/TUI).

Usage Examples

Full Pipeline (Automated Mode):

python3 scripts/pipeline.py --config config.json

Audit Only (Save to File):

python3 scripts/audit.py --days 30 > data/report.json

Data & Security Commitment

This skill is designed specifically to comply with enterprise Data Loss Prevention (DLP) requirements:

  1. Secure API Key Handling

The skill requires EONIK_API_KEY (via the standard x-api-key header). The execution script securely drops the ephemeral token from the environment immediately after binding. No keys are logged or written to disk.

  1. Native OpenCLAW Routing (WhatsApp/Slack/Telegram)

Unlike legacy versions, this architecture does NOT rely on webhooks, custom notification dispatcher scripts, or storing tokens in your config.json.

Standard Output from the pipeline is passed directly to the local OpenCLAW node, which effortlessly routes the message to whatever chat surface triggered it or is configured natively (WhatsApp, Slack, Telegram, Discord, or the local TUI). Zero manual API configurations are needed to get multi-channel alerts!

  1. Data Scope

Execution logs and generated report.json files contain the exposed Meta Ad IDs flagged for leaking or scaling. Keep your local output/ directory protected and adhere to your internal security policies for Chat UI visibility.

Continuous Scanning & Notifications

The original objective of this skill is to completely automate budget optimization by continuously scanning your ad accounts and notifying your team on external channels (WhatsApp, Slack, Telegram) when leaks are detected.

You do NOT need to over-engineer a loop or write your own dispatcher. OpenCLAW has a built-in, native cron scheduler that will automatically run the skill and route the output to your linked channels.

Schedule Daily Audits (e.g., Every morning at 8 AM): To set up continuous automated scanning, use OpenCLAW's native scheduler:

# Add a recurring cron job natively via OpenCLAW
openclaw cron add --name "daily-eonik-audit" --cron "0 8 * * *" --message "Run the eonik ad audit pipeline" --session isolated

*OpenCLAW will execute the pipeline daily in an isolated context and dispatch any detected warnings directly to your configured messaging platforms.*

Troubleshooting

API Verification Fails:

  • Ensure EONIK_API_KEY is exported.
  • Verify your eonik billing and usage caps aren't exceeded.

平台分布

OpenClaw

97.84%
按下载量换算4,464

安全审计

VirusTotal

通过

ClawScan

通过

Static analysis

通过

权限和风险

接触敏感数据

该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

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