A curated list of LLM and AI Agent Skills for customising workflows. Works with Claude Code, Codex, Gemini CLI, and custom AI Agents. Helps operations teams automate tasks and integrate AI capabilities.
git clone https://github.com/Prat011/awesome-llm-skills.githttps://github.com/user-attachments/assets/fb10b4c7-4155-4026-95b9-b4b979a14921
["Identify the data source and format you need to process (e.g., CRM, database, API, or file).","Define the transformation rules and output format required (e.g., CSV, JSON, or dashboard).","Select the appropriate tool for execution (e.g., Claude Code for Python scripts, Zapier for no-code automation, or a custom AI agent for complex workflows).","Run the automation and validate the output against your criteria (e.g., manual checks or automated tests).","Integrate the output into your workflow (e.g., email, Slack, dashboard, or shared drive).","Monitor performance and refine rules based on results (e.g., adjust priority scoring or add new data sources)."]
Automate the generation of structured documentation from chat conversations.
Create customized workflows for document processing tasks like editing and analyzing PDFs.
Integrate AI agents with various platforms to streamline project management and task tracking.
Enhance web application testing by utilizing predefined skills for automated validation.
No install command available. Check the GitHub repository for manual installation instructions.
git clone https://github.com/Prat011/awesome-llm-skillsCopy the install command above and run it in your terminal.
Launch Claude Code, Cursor, or your preferred AI coding agent.
Use the prompt template or examples below to test the skill.
Adapt the skill to your specific use case and workflow.
Automate the process of extracting [DATA_TYPE] from [SOURCE] and transforming it into a [OUTPUT_FORMAT] report. Use [TOOL_NAME] to process the raw data, apply [TRANSFORMATION_RULES], and generate a summary with [KEY_METRICS]. Validate the output against [VALIDATION_CRITERIA] to ensure accuracy. Deliver the final report to [DESTINATION].
### Automated Data Extraction & Report Generation
**Source:** CRM database (Salesforce API)
**Data Type:** Customer support tickets from Q2 2024
**Output Format:** Structured CSV with priority scoring
**Tool Used:** Claude Code with Python (pandas, requests)
**Transformation Rules:**
- Filter tickets by status='Open' and created_date >= '2024-04-01'
- Assign priority scores (1-5) based on subject keywords ('urgent', 'bug', 'payment')
- Calculate average resolution time per agent
- Aggregate by product line and region
**Validation Criteria:**
- Cross-check ticket counts against Salesforce UI (manual verification)
- Ensure no duplicate entries in the dataset
- Confirm priority scores align with predefined keyword mappings
**Generated Report:**
```csv
agent_id,product_line,region,open_tickets,priority_score,avg_resolution_hours
AGT-101,Mobile App,North America,45,3.2,12.5
AGT-203,Web Platform,EMEA,32,2.8,8.3
AGT-456,API Services,APAC,18,4.1,22.1
```
**Key Insights:**
- Mobile App team has the highest ticket volume but lowest average resolution time
- API Services team handles the most critical tickets (avg priority 4.1)
- EMEA region shows the fastest resolution times (8.3 hours)
**Delivered To:** Shared Google Drive folder with operations team (auto-synced via Zapier)
**Next Steps:**
1. Schedule a follow-up meeting to discuss priority score thresholds
2. Investigate why API Services tickets take 2.5x longer to resolve
3. Update the keyword mapping for priority scoring based on this data
*Note: This report was generated automatically on 2024-06-15 at 09:15 UTC.*Take a free 3-minute scan and get personalized AI skill recommendations.
Take free scan