Token导航 LogoToken导航

Agent Skill · 研究检索

instagram(Instagram 运营)

instagram 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

instagram 是研究检索类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为接触敏感数据;许可证为 MIT,第三方扫描有提醒项,按安装量在研究检索类的 73,675 个 Skill 里排第 53,170。

总安装 539周安装 22GitHub Stars 175下载 174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

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:instagram(Instagram 运营)
来源仓库:https://github.com/nicepkg/ai-workflow
仓库路径:skills/instagram
安装命令:
npx skills add https://github.com/nicepkg/ai-workflow --skill instagram
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。不同来源提供的安装方式可能略有差异;本站展示可直接复制的安装命令,安装前请核对来源页面。

skills.shnpx skills
npx skills add https://github.com/nicepkg/ai-workflow --skill instagram

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。

instagram 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中快速定位候选结果。适用于关键词搜索、任务场景匹配或来源线索梳理等研究检索场景。通过 npx skills add 命令从指定 GitHub 仓库安装并使用该技能。

安装前需确认权限范围、维护状态,以及是否会触发联网或文件读写操作。建议结合原始 README 和仓库路径进一步核验具体用法和功能边界。

来源仓库内路径:skills/instagram

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 Codex、Claude、Cursor、Gemini CLI;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 npx skills add https://github.com/nicepkg/ai-workflow --skill instagram;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

instagram 怎么安装?

在终端执行 npx skills add https://github.com/nicepkg/ai-workflow --skill instagram。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

instagram 支持哪些 AI 工具?

公开资料标注支持 Codex、Claude、Cursor、Gemini CLI。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。

instagram 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。

instagram 是免费的吗?

来源标注的许可证是 MIT。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。

instagram 用的人多吗?

公开数据是累计安装 539 次,近一周安装 22 次,下载 174 次,GitHub 175 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。

instagram 安全吗?

第三方扫描有提醒项,说明存在需要人工确认的行为。安装前请打开源码看清它读了什么、联网到哪里。

值得选的地方和要先想清楚的地方

值得选的地方

  • 同时适配 4 种工具,换客户端不用重新找替代品。
  • 3 个目录同时收录,说明这个 Skill 流传比较广。
  • 许可证明确为 MIT,商用和分发边界好判断。

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。
  • 第三方扫描存在提醒项或未通过项,需要人工逐条确认。
  • 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 Codex,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。

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
instagram

Instagram 运营 · 本页

539175接触敏感数据MIT有提醒

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

Instagram API (Graph API)

Use the Instagram Graph API by directly executing curl commands to read and publish Instagram content.

Official docs: https://developers.facebook.com/docs/instagram-api

When to Use

Use this skill when you need to:

  • Fetch recent media (photos / videos / Reels) from an account
  • Get detailed information about a specific media item (caption, type, link, time, etc.)
  • Search recent media by hashtag
  • Publish image posts via API (with caption)

Prerequisites

  1. You must have an Instagram Business / Creator account linked to a Facebook Page
  2. Create an app in Facebook Developers and enable Instagram Basic Display / Instagram Graph API permissions
  3. Obtain:
  • INSTAGRAM_ACCESS_TOKEN: a long-lived user access token
  • INSTAGRAM_BUSINESS_ACCOUNT_ID: your Instagram Business account ID

Set the environment variables, for example:

export INSTAGRAM_ACCESS_TOKEN="EAAG..."
export INSTAGRAM_BUSINESS_ACCOUNT_ID="1784140xxxxxxx"

These examples use Graph API version v21.0. You can replace this with the latest version if needed.

Required permissions (scopes)

Depending on which endpoints you use, make sure your app has requested and been approved for (at least):

  • instagram_basic
  • pages_show_list
  • instagram_content_publish (for publishing media)
  • instagram_manage_insights and related permissions (for insights / some hashtag use cases)

Important: When using $VAR in a command that pipes to another command, wrap the command containing $VAR in bash -c '...'. Due to a Claude Code bug, environment variables are silently cleared when pipes are used directly. ``bash bash -c 'curl -s "https://api.example.com" -H "Authorization: Bearer $API_KEY"' | jq '.' ``

How to Use

All examples below assume you have already set:

INSTAGRAM_ACCESS_TOKEN
INSTAGRAM_BUSINESS_ACCOUNT_ID

1. Fetch recent media for the account

Fetch the most recent media (photos / videos / Reels) for the account:

bash -c 'curl -s -X GET "https://graph.facebook.com/v21.0/${INSTAGRAM_BUSINESS_ACCOUNT_ID}/media?fields=id,caption,media_type,media_url,permalink,timestamp" --header "Authorization: Bearer ${INSTAGRAM_ACCESS_TOKEN}"'

Notes:

  • Each item in the returned JSON represents a media object
  • Common fields:

- id: media ID (used for details / insights later) - caption: caption text - media_type: IMAGE / VIDEO / CAROUSEL_ALBUM - media_url: direct URL to the media - permalink: Instagram permalink - timestamp: creation time


2. Get details for a single media

If you already have a media id, you can fetch more complete information. Replace <your-media-id> with the id field from the "Get User Media" response (section 1 above):

bash -c 'curl -s -X GET "https://graph.facebook.com/v21.0/<your-media-id>?fields=id,caption,media_type,media_url,permalink,thumbnail_url,timestamp,username" --header "Authorization: Bearer ${INSTAGRAM_ACCESS_TOKEN}"'

3. Search media by hashtag

Note: hashtag search requires proper business use cases and permissions as defined by Facebook/Instagram. Refer to the official docs.

This usually involves two steps:

3.1 Get the hashtag ID

Replace <hashtag-name> with any hashtag name you want to search for (without the # symbol), e.g., "travel", "food", "photography":

bash -c 'curl -s -X GET "https://graph.facebook.com/v21.0/ig_hashtag_search?user_id=${INSTAGRAM_BUSINESS_ACCOUNT_ID}&q=<hashtag-name>" --header "Authorization: Bearer ${INSTAGRAM_ACCESS_TOKEN}"'

Note the id field in the returned JSON for use in the next step.

3.2 Fetch recent media for the hashtag

Replace <hashtag-id> with the id field from the "Search Hashtag" response (section 3.1 above):

bash -c 'curl -s -X GET "https://graph.facebook.com/v21.0/<hashtag-id>/recent_media?user_id=${INSTAGRAM_BUSINESS_ACCOUNT_ID}&fields=id,caption,media_type,media_url,permalink,timestamp" --header "Authorization: Bearer ${INSTAGRAM_ACCESS_TOKEN}"'

4. Publish an image post

Publishing an image post via the Graph API usually requires two steps:

  1. Create a media container
  2. Publish the container to the feed
4.1 Create a media container

Write the request data to /tmp/request.json:

{
  "image_url": "https://example.com/image.jpg",
  "caption": "Hello from Instagram API 👋"
}

Replace https://example.com/image.jpg with any publicly accessible image URL and update the caption text as needed.

bash -c 'curl -s -X POST "https://graph.facebook.com/v21.0/${INSTAGRAM_BUSINESS_ACCOUNT_ID}/media" -H "Content-Type: application/json" -d @/tmp/request.json --header "Authorization: Bearer ${INSTAGRAM_ACCESS_TOKEN}"'

The response will contain an id (media container ID), for example:

{
  "id": "1790xxxxxxxxxxxx"
}

Note this ID for use in the next step.

4.2 Publish the media container to the feed

Write the request data to /tmp/request.json:

{
  "creation_id": "<your-creation-id>"
}

Replace <your-creation-id> with the id field from the "Create Media Container" response (section 4.1 above):

bash -c 'curl -s -X POST "https://graph.facebook.com/v21.0/${INSTAGRAM_BUSINESS_ACCOUNT_ID}/media_publish" -H "Content-Type: application/json" -d @/tmp/request.json --header "Authorization: Bearer ${INSTAGRAM_ACCESS_TOKEN}"'

If successful, the response will contain the final media id:

{
  "id": "1791yyyyyyyyyyyy"
}

You can then use the "Get details for a single media" command to fetch its permalink.


5. Common errors and troubleshooting

  1. Permissions / OAuth errors
  • Typical error message: (#10) Application does not have permission for this action
  • Check:
  • Whether the app has been reviewed / approved
  • Whether the required Instagram permissions are enabled
  • Whether INSTAGRAM_ACCESS_TOKEN is a valid long-lived token
  1. Unsupported account type
  • Most Graph API features require Business / Creator accounts
  • Make sure the Instagram account type is correct and linked to a Facebook Page
  1. Rate limits
  • Too many requests in a short period may hit rate limits; add delays for bulk operations

Guidelines

  1. Do not log tokens: INSTAGRAM_ACCESS_TOKEN is sensitive; avoid printing it in logs or chat transcripts
  2. Validate curl commands in a test environment first: confirm flows before wiring them into automation / agents
  3. Keep API version up to date: periodically check Facebook docs and update the v21.0 version in URLs to the latest
  4. Use placeholder text for IDs: all examples use placeholder text like <your-media-id> instead of shell variables in URLs to avoid dependencies and make examples self-contained

平台分布

OpenCode

27.98%
按下载量换算49

Claude Code

24.35%
按下载量换算42

Cursor

16.73%
按下载量换算29

Gemini CLI

12.78%
按下载量换算22

goose

7.53%
按下载量换算13

github-copilot

3.89%
按下载量换算7

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

可疑

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。来源安全扫描存在提醒或未通过项,安装前请自行复核。

继续浏览同类 Skills