← 返回 Skills 市场

Instagram Analytics

Name: Instagram Analytics
Author: snoopyrain

作者 snoopyrain · GitHub ↗ · v1.0.1 · MIT-0

cross-platform ✓ 安全检测通过

275

总下载

当前安装

版本数

在 OpenClaw 中安装

/install instagram-analytics

功能描述

Track Instagram performance and analytics. Use when the user says 'Instagram analytics', 'Instagram metrics', 'how are my Reels doing', 'Instagram reach', 'I...

使用说明 (SKILL.md)

Instagram Analytics

Track your Instagram performance — reach, followers, interactions, Reels metrics, and post-level engagement. Powered by Boring.

Security & Data Handling

MCP link is a credential: Your MCP Server URL (https://boring.aiagent-me.com/mcp/t/xxxxx...) contains an embedded authentication token. Treat it like a password — do not share it publicly.
Token scope: The embedded token is read-only for analytics. It can only fetch performance metrics and account metadata. It cannot publish, delete, or modify any content on your social media accounts.
Token storage: The token is stored server-side in Boring's database (MongoDB on DigitalOcean). It is never written to your local filesystem. You can regenerate or revoke it anytime at boring.aiagent-me.com/settings.
Data flow: Analytics queries are sent from Boring's server (Google Cloud, us-central1) to the platform's API on your behalf. Only performance metrics are retrieved — no content is uploaded or modified.
No local credentials: No local API keys, environment variables, or secrets are needed. All auth is embedded in the MCP link.
Third-party service: This skill relies on Boring, an open-source social media management tool. Source code: github.com/snoopyrain.

Prerequisites

Sign up at boring.aiagent-me.com with Google
Connect Instagram — requires an Instagram Business or Creator account
Get your MCP link: Go to Settings → copy your MCP Server URL (contains your auth token — treat it like a password)
Add to Claude: Paste the MCP link as a Connector — no install, no API key needed

Available Tools

Tool	Data Source	Best For
`boring_get_performance`	Real-time platform API	Account-level overview (reach, followers, interactions)
`boring_get_video_analytics`	Real-time platform API	Per-post/Reel metrics (views, likes, comments, shares)
`boring_get_posts_performance`	Daily snapshots (collected at 2 AM)	Historical post performance over date ranges
`boring_get_publish_history`	Boring database	Publishing history and status tracking

Workflow

Step 1: List Accounts

Call boring_list_accounts and filter for instagram platform.

Step 2: Determine What the User Wants

User Request	Tool to Use
"How is my Instagram doing?"	`boring_get_performance`
"Show my best Reels"	`boring_get_video_analytics`
"Instagram performance this month"	`boring_get_posts_performance`
"What did I post on IG?"	`boring_get_publish_history`

Step 3: Fetch Data

Account-Level Performance

boring_get_performance(
  account_id="\x3Caccount_id>",
  platform="instagram",
  period="week"       // "day", "week", or "month"
)

Per-Post Analytics (Real-Time)

boring_get_video_analytics(
  account_id="\x3Caccount_id>",
  platform="instagram",
  limit=20             // max 100
)

Historical Post Performance (Snapshots)

boring_get_posts_performance(
  account_id="\x3Caccount_id>",
  since="2025-12-01",
  until="2025-12-31",
  limit=20
)

Step 4: Present Results

Format the data clearly:

Account overview: Show reach, followers, profile views in a summary table
Post analytics: Rank posts by engagement, highlight top Reels
Historical: Show trends over time, compare Reels vs Photos vs Carousels

Instagram Metrics

Metric	Description
`reach`	Accounts reached
`follower_count`	Total followers
`profile_views`	Profile visits
`total_interactions`	Likes + comments + saves + shares
`ig_reels_avg_watch_time`	Average Reels watch time
`ig_reels_video_view_total_time`	Total Reels view time

Error Handling

Error	Solution
`InvalidApiKey`	MCP link may be invalid — regenerate it at boring.aiagent-me.com Settings
`InvalidAccountId`	Run `boring_list_accounts` to get valid IDs
`TokenExpired`	Reconnect account at boring.aiagent-me.com
No data returned	Account may be newly connected — data collection runs daily at 2 AM

Documentation

Full API docs: boring-doc.aiagent-me.com

安全使用建议

This skill appears to be what it says: a connector to the Boring analytics service that uses a single MCP connector URL containing an embedded token. Before installing/using it: (1) Treat the MCP link like a password — do not publish it; if exposed, regenerate/revoke it. (2) Verify you trust boring.aiagent-me.com and the project/source (the SKILL.md lists a GitHub owner but not a clear repo); check the provider's privacy/security documentation. (3) Understand the token is embedded in a URL — ask the provider how long-lived it is and confirm the token's scope (read-only as claimed). (4) Confirm your agent platform will store/handle the connector securely (and will not leak it in logs or to third parties). (5) If you need stronger assurance, test with an account that has no sensitive data or rotate the token after testing. These precautions will reduce risk despite the skill's coherent design.

功能分析

Type: OpenClaw Skill Name: instagram-analytics Version: 1.0.1 The skill bundle provides instructions for an AI agent to interface with an external Instagram analytics service (boring.aiagent-me.com) via the Model Context Protocol (MCP). The SKILL.md file defines tools for fetching performance metrics and account metadata, with clear documentation on credential handling and data flow. There is no evidence of malicious intent, data exfiltration, or prompt injection attacks within the provided files.

能力评估

✓ Purpose & Capability

Name/description match the instructions: all calls and tools in SKILL.md target the Boring service and Instagram analytics. No unrelated binaries, env vars, or permissions are requested.

ℹ Instruction Scope

Instructions are narrowly scoped to listing accounts and calling Boring tool endpoints (boring_get_performance, boring_get_video_analytics, etc.). They do instruct the user to paste an MCP Connector link (which embeds an auth token) into the agent platform — this is sensitive but expected for a connector-based analytics integration.

✓ Install Mechanism

Instruction-only skill with no install spec and no code files, so nothing is written to disk or downloaded during install.

ℹ Credentials

No environment variables or local credentials are requested; the single required credential is the MCP connector URL (embedded token). This is proportionate for a connector-based analytics skill, but an embedded token in a URL is sensitive and the SKILL.md's claim that it is read-only and only stored server-side is a provider assertion that cannot be verified from the skill alone.

✓ Persistence & Privilege

Skill is not always-on and does not request system-level persistence or modification of other skills. It depends on a user-supplied connector link and normal autonomous invocation behavior is unchanged.

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 instagram-analytics
安装完成后，直接呼叫该 Skill 的名称或使用 /instagram-analytics 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

v1.0.1

Add detailed Security & Data Handling

v1.0.0

- Initial release of instagram-analytics skill. - Track Instagram performance metrics including reach, followers, and interactions. - View Reels and per-post analytics, as well as historical performance snapshots. - Secure, password-like MCP link required for authentication; no local API keys needed. - Simple setup: connect your Instagram Business/Creator account through Boring. - Includes clear error handling and user-focused examples for typical Instagram analytics queries.

元数据

Slug instagram-analytics

版本 1.0.1

许可证 MIT-0

累计安装 1

当前安装数 1

历史版本数 2

常见问题