← 返回 Skills 市场
elias-didoo

Meta Ads Audience Analysis

作者 elias-didoo · GitHub ↗ · v1.1.0 · MIT-0
cross-platform ✓ 安全检测通过
119
总下载
0
收藏
0
当前安装
2
版本数
在 OpenClaw 中安装
/install meta-ads-audience-analysis
功能描述
[Didoo AI] Analyzes Meta Ads audience efficiency across audience types, overlap, demographics, and budget allocation. Use when reviewing targeting strategy,...
安全使用建议
This skill is internally consistent and requests only the Meta token and ad account ID needed for read-only analysis. Before installing: ensure the META_ACCESS_TOKEN you provide has minimal scope (ads_read only) and is not a broad admin token; prefer short-lived or narrowly scoped credentials where possible. Be aware the SKILL will write analysis results into session context keys (budget_reallocation_plan, audience_issues) that other skills (e.g., meta-ads-recommendation) may read — review any downstream skill to ensure it is trusted. Finally, confirm your agent runtime's network policies and logging practices so your access token is not inadvertently persisted or exposed in logs.
功能分析
Type: OpenClaw Skill Name: meta-ads-audience-analysis Version: 1.1.0 The skill bundle 'meta-ads-audience-analysis' is a legitimate set of instructions for an AI agent to perform marketing data analysis. It requires standard Meta Ads API credentials (META_ACCESS_TOKEN, META_AD_ACCOUNT_ID) to fetch performance metrics and provides a structured workflow for auditing audience efficiency, overlap, and demographics. There is no evidence of malicious intent, data exfiltration, or unauthorized command execution in SKILL.md or _meta.json.
能力标签
requires-oauth-tokenrequires-sensitive-credentials
能力评估
Purpose & Capability
Name/description describe Meta Ads audience analysis and the skill only requires META_ACCESS_TOKEN and META_AD_ACCOUNT_ID, which are the expected credentials to read ads data via Meta's Graph API. No unrelated binaries, packages, or credentials are requested.
Instruction Scope
SKILL.md instructs the agent to fetch breakdowns (audience type, overlap, demographics, placements) and to produce analysis tables and a reallocation plan. It does not instruct reading unrelated files, system paths, or other environment variables. It does instruct the agent to write two keys into session context for downstream use, which is consistent with the described multi-skill workflow.
Install Mechanism
No install spec or code files are present (instruction-only skill), so nothing is written to disk or fetched during install. This minimizes supply-chain risk.
Credentials
Only META_ACCESS_TOKEN and META_AD_ACCOUNT_ID are required. The token is explicitly described as read-only (ads_read) which is proportionate. No unrelated secrets or multiple credential sets are requested.
Persistence & Privilege
always is false and the skill does not request permanent system presence. It writes transient session-context keys (budget_reallocation_plan, audience_issues) for use by meta-ads-recommendation, which is a limited and documented interaction rather than system-level modification.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install meta-ads-audience-analysis
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /meta-ads-audience-analysis 触发
  4. 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v1.1.0
Added homepage, metadata.openclaw.requires.env, OAuth scope for credential clarity
v1.0.0
Initial release
元数据
Slug meta-ads-audience-analysis
版本 1.1.0
许可证 MIT-0
累计安装 0
当前安装数 0
历史版本数 2
常见问题

Meta Ads Audience Analysis 是什么?

[Didoo AI] Analyzes Meta Ads audience efficiency across audience types, overlap, demographics, and budget allocation. Use when reviewing targeting strategy,... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 119 次。

如何安装 Meta Ads Audience Analysis?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install meta-ads-audience-analysis」即可一键安装,无需额外配置。

Meta Ads Audience Analysis 是免费的吗?

是的,Meta Ads Audience Analysis 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

Meta Ads Audience Analysis 支持哪些平台?

Meta Ads Audience Analysis 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。

谁开发了 Meta Ads Audience Analysis?

由 elias-didoo(@elias-didoo)开发并维护,当前版本 v1.1.0。

💬 留言讨论