Use Case
Tencent Cloud COS isn't just for solo use β teams can share skills and build consistent AI workflows across the organization. Tencent Cloud Object Storage (COS) and Data Integration (CI) integration skills. Covering the three core scenarios of file storage management, AI processing and knowledge base. Storage scenarios: Upload files to the cloud, download cloud files, manage bucket files in batches, obtain file signature links to share, and view file metainformation. Image processing scenarios: image quality assessment and scoring, AI super-resolution enlargement, AI intelligent cropping, QR code/barcode recognition, adding text watermarks, obtaining image EXI... This guide covers how to deploy Tencent Cloud COS for your team, standardize prompts, and create shared workflows that everyone can use.
Install Tencent Cloud COS in your project directory: .claude/skills/tencentcloud-cos-skill/
Commit the skill folder to your repository so the whole team has access
Document your team's standard prompts in a shared README
Use Tencent Cloud COS in code reviews, standups, and planning sessions
Iterate: collect feedback from the team and refine your prompts
Copy these prompts and use them with your AI agent after installing Tencent Cloud COS
How can my team use Tencent Cloud COS together?
Set up Tencent Cloud COS for our project so everyone can use it
Create a shared workflow using Tencent Cloud COS for our team
Select your agent
Option 1: Install via CLI (recommended)
Recommended (no pre-install needed)
npx clawhub@latest --dir ~/.claude/skills install tencentcloud-cos-skillOr via clawhub CLI (if already installed)
clawhub --dir ~/.claude/skills install tencentcloud-cos-skillβ οΈ Requires Node.js 18+. No Node? Use Option 2 below to download the ZIP instead. Install Node.js β
Option 2: Manual install (no Node required)
Download the ZIP, extract it, and place the folder at the path below. Restart your agent to activate.
Install path
~/.claude/skills/tencentcloud-cos-skill/π‘Extract and place the folder at the path above, then restart your agent.