← 返回 Skills 市场
Meta Ads Collector Adarsh
作者
Adarsh More
· GitHub ↗
· v1.0.0
279
总下载
0
收藏
1
当前安装
1
版本数
在 OpenClaw 中安装
/install meta-ads-collector-adarsh
功能描述
Collects active Meta ads for a brand, reporting total ads, formats, ad types, longest-running ad duration, and estimated spend if available.
安全使用建议
Before installing or enabling this skill: 1) Do not provide META_ACCESS_TOKEN, META_APP_ID, or META_APP_SECRET until you confirm the skill source and how secrets are handled — the registry metadata did not declare any required env vars even though the SKILL.md requires them. 2) Prefer creating an app/credentials with minimal permissions and short-lived tokens (or use a dedicated read-only token) and rotate them after testing. 3) Ask the publisher to update the registry metadata to list the exact environment variables and explain how tokens are used and stored/logged. 4) Verify where logs and any returned data are sent (the SKILL.md references Winston logging and external APIs); ensure logs do not leak tokens or PII. 5) If you cannot verify the source, test in an isolated environment and avoid providing production credentials. If the developer cannot explain the metadata mismatch, treat the skill as untrusted.
功能分析
Type: OpenClaw Skill
Name: meta-ads-collector-adarsh
Version: 1.0.0
The skill bundle describes a legitimate tool for collecting marketing data from the Meta Ad Library API. It defines clear input/output schemas, implements standard error handling, and uses environment variables (META_ACCESS_TOKEN) for authentication as expected for this type of integration. No malicious code, data exfiltration patterns, or prompt injection attempts were found in SKILL.md or _meta.json.
能力评估
Purpose & Capability
The name and description match the implementation notes: the skill queries the Meta Ad Library API and computes ad metrics. Requesting a Meta access token and app credentials is appropriate for that purpose. However, the registry metadata lists no required environment variables or primary credential while the SKILL.md explicitly requires META_ACCESS_TOKEN, META_APP_ID, and META_APP_SECRET — an inconsistency between declared requirements and the runtime instructions.
Instruction Scope
The runtime instructions are focused on the Ad Library API and metric calculation (formats, counts, durations, optional spend). They reference process.env variables and other project files (e.g., metaAdsService.ts, src/types/audit.types.ts) and instruct logging errors with Winston. The instructions do not ask for unrelated system files or other service credentials, but they do require reading secret env vars (Meta credentials). Because the registry omitted those env requirements, the instructions grant the agent access to secrets that were not declared to users/installers — this is a scope/visibility concern.
Install Mechanism
This is an instruction-only skill with no install spec and no code files. That minimizes install-time risk (nothing is downloaded or written by an installer).
Credentials
The env vars named in SKILL.md (META_ACCESS_TOKEN, META_APP_ID, META_APP_SECRET) are appropriate and proportionate for querying Meta's Ad Library. However, the skill registry metadata claims 'Required env vars: none' and 'Primary credential: none'. The absence of declared env requirements in the registry is misleading and increases risk because users may not realize they must supply sensitive credentials. No unrelated secrets are requested, but the mismatch is a serious transparency issue.
Persistence & Privilege
The skill does not request always: true, does not include an install script, and does not appear to alter other skills or system-wide settings. It relies on runtime environment variables only and does not request elevated persistence.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install meta-ads-collector-adarsh - 安装完成后，直接呼叫该 Skill 的名称或使用
/meta-ads-collector-adarsh触发 - 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
v1.0.0
Initial release of the Meta Ads Collector Skill.
- Scans Meta Ad Library API for active ads by brand, optionally filtering by domain.
- Extracts total active ads, ad formats, ad types, and longest-running ad duration.
- Returns estimated spend for political/issue ads if available.
- Implements robust error handling; never throws, always returns a typed result.
- Designed for integration with the Marketing Audit Pipeline to support Paid Ads Strategy reporting.
元数据
常见问题
Meta Ads Collector Adarsh 是什么？
Collects active Meta ads for a brand, reporting total ads, formats, ad types, longest-running ad duration, and estimated spend if available. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 279 次。
如何安装 Meta Ads Collector Adarsh？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install meta-ads-collector-adarsh」即可一键安装，无需额外配置。
Meta Ads Collector Adarsh 是免费的吗？
是的，Meta Ads Collector Adarsh 完全免费（开源免费），可自由下载、安装和使用。
Meta Ads Collector Adarsh 支持哪些平台？
Meta Ads Collector Adarsh 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 Collector Adarsh？
由 Adarsh More（@adarshvmore）开发并维护，当前版本 v1.0.0。
推荐 Skills