← 返回 Skills 市场

Linkedin AI Post Builder and Publisher

Name: Linkedin AI Post Builder and Publisher
Author: yadavabhijeet4

作者 yadavabhijeet4 · GitHub ↗ · v1.0.0 · MIT-0

cross-platform ⚠ suspicious

307

总下载

当前安装

版本数

在 OpenClaw 中安装

/install linkedin-ai-optimizer

功能描述

Post updates to LinkedIn, track analytics, and optimize content.

使用说明 (SKILL.md)

LinkedIn Skill

Post updates, track performance, and optimize your content for maximum reach.

Setup & Authentication

Create an App: Go to LinkedIn Developers, create an app, and add the "Sign In with LinkedIn" and "Share on LinkedIn" products.

Generate Token: Use the included helper script to generate an OAuth 2.0 Access Token.

# Set your credentials
export LINKEDIN_CLIENT_ID="your_client_id"
export LINKEDIN_CLIENT_SECRET="your_client_secret"
export LINKEDIN_REDIRECT_URI="http://localhost:8000/callback"

# Run the auth helper
uv run /opt/homebrew/lib/node_modules/openclaw/skills/linkedin/scripts/linkedin_auth.py

Save Token: Save the generated token as LINKEDIN_ACCESS_TOKEN in your environment.

Usage

1. Optimize & Feedback Loop (New!)

Analyze your draft against top-performing posts before you publish. Requires GEMINI_API_KEY.

uv run /opt/homebrew/lib/node_modules/openclaw/skills/linkedin/scripts/linkedin_feedback.py "Your draft text here..."

2. Posting

Preview (Default):

uv run /opt/homebrew/lib/node_modules/openclaw/skills/linkedin/scripts/linkedin.py "Your post text"

Publish:

uv run /opt/homebrew/lib/node_modules/openclaw/skills/linkedin/scripts/linkedin.py "Your post text" --confirm

3. Analytics

View Stats: Reads from linkedin_history.jsonl and fetches current stats (Requires r_member_social).

uv run /opt/homebrew/lib/node_modules/openclaw/skills/linkedin/scripts/linkedin_analytics.py

Configuration

LINKEDIN_ACCESS_TOKEN: Valid OAuth 2.0 Access Token.
GEMINI_API_KEY: Required for the Feedback Loop/Optimizer.

安全使用建议

This skill appears to implement what it says (posting, analytics, optional AI feedback), but the registry metadata incorrectly claims no required credentials. Before installing: (1) Inspect and control where you store LINKEDIN_CLIENT_SECRET and LINKEDIN_ACCESS_TOKEN (prefer ephemeral tokens and minimal scopes like w_member_social only when needed); (2) If you don't want the AI feedback feature, do not set GEMINI_API_KEY or run the feedback scripts; (3) Check any .env file in the working directory—python-dotenv will load it and could surface unrelated secrets; (4) Verify the LinkedIn app scopes and confirm you trust the author (registry owner unknown); (5) Run the scripts in a safe environment (e.g., non-production account) first to confirm behavior. The metadata mismatch lowers trust—if you can, ask the publisher to update declared requirements or obtain a publisher identity before proceeding.

功能分析

Type: OpenClaw Skill Name: linkedin-ai-optimizer Version: 1.0.0 The LinkedIn AI Optimizer bundle is a legitimate tool for managing LinkedIn posts and analytics using OAuth 2.0 and the Gemini API. The scripts (e.g., linkedin.py, linkedin_auth.py) follow standard API integration patterns, and file operations are limited to the local workspace and history logging. There is no evidence of data exfiltration, credential theft, or malicious prompt injection.

能力评估

ℹ Purpose & Capability

The name/description (LinkedIn post builder, analytics, optimizer) matches the scripts and endpoints (LinkedIn API + Google Generative Language). However the skill registry metadata claims no required environment variables or primary credential, while SKILL.md and the scripts clearly require LINKEDIN_CLIENT_ID, LINKEDIN_CLIENT_SECRET, LINKEDIN_ACCESS_TOKEN and optionally GEMINI_API_KEY. That metadata omission is an incoherence and reduces trust.

ℹ Instruction Scope

SKILL.md limits actions to creating a LinkedIn app, running included helper scripts, posting previews/publishing, and reading/writing a local history file. The scripts read/write expected local files (e.g., linkedin_history.jsonl, ~/.openclaw/workspace/memory/research_notes.md) and call LinkedIn and Google generativelanguage APIs. There are no hidden external endpoints beyond those two services. Minor scope note: the scripts use python-dotenv (load_dotenv()) which will parse a .env file in the working directory and could surface any secrets present there—verify your .env contents before running.

✓ Install Mechanism

There is no install spec and no remote download: this is an instruction-only skill with included Python scripts. No external archives or URL-based installs were observed.

⚠ Credentials

The functionality legitimately needs LinkedIn credentials and (optionally) a Gemini API key, but the skill metadata did not declare these required env vars or a primary credential. Requiring LINKEDIN_CLIENT_SECRET and LINKEDIN_ACCESS_TOKEN is sensitive but proportionate to posting and analytics; requiring GEMINI_API_KEY for optimization is optional but should have been declared. Also, python-dotenv's load_dotenv() means the script may read a local .env file—ensure it doesn't contain unrelated secrets you don't want read/exposed.

✓ Persistence & Privilege

The skill does not request 'always: true', does not change other skills' configs, and does not request elevated platform-wide privileges. It reads/writes a local history file (linkedin_history.jsonl) which is expected behavior for logging posts.

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 linkedin-ai-optimizer
安装完成后，直接呼叫该 Skill 的名称或使用 /linkedin-ai-optimizer 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 LinkedIn skill. - Post updates to LinkedIn and preview before publishing. - Track performance with analytics, including stats from your post history. - Optimize draft content using a feedback loop that analyzes against top-performing posts (requires GEMINI_API_KEY). - Simple setup with OAuth 2.0 authentication instructions.

元数据

Slug linkedin-ai-optimizer

版本 1.0.0

许可证 MIT-0

累计安装 0

当前安装数 0

历史版本数 1

常见问题