update-profiles

Fetch new data from Granola, Slack, Jira, and GitHub to update engineer performance profiles.

Updated Aug 23, 2026
One-click install
npx skills add https://github.com/lzlatkin/dots --skill update-profiles
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: update-profiles
Source: https://github.com/lzlatkin/dots/tree/main/agents/skills/update-profiles
Command: npx skills add https://github.com/lzlatkin/dots --skill update-profiles

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill automates the complex and time-consuming process of updating engineer performance profiles by systematically gathering new data from multiple sources and synthesizing it into comprehensive reports.

Core Features & Use Cases

  • Data Aggregation: Pulls data from Granola, Slack, Jira, and GitHub since the last update.
  • Sub-Agent Delegation: Leverages specialized sub-agents for data extraction and observation processing.
  • Profile Synthesis: Reconstructs and updates profile documents, preserving all existing sections.
  • Cross-Engineer Feedback: Captures and routes peer observations to relevant profiles via an inbox system.
  • Use Case: Run this skill weekly to ensure all engineer performance profiles are current, reflecting recent achievements, project contributions, and feedback, making performance reviews more data-driven and efficient.

Quick Start

Use the update-profiles skill to refresh all engineer performance data for the current quarter.

Frequently Asked Questions about update-profiles

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate engineer performance profile updates from Jira and GitHub?

This workflow aggregates engineer data from Jira, GitHub, Slack, and Granola to synthesize performance profiles. It delegates data processing to specialized sub-agents, capturing project contributions and peer feedback to keep reports current.

What is the best way to aggregate cross-engineer feedback for performance reviews?

Using an inbox mechanism captures and routes peer observations to relevant engineer profiles during data synthesis. This workflow systematically integrates cross-engineer feedback alongside Jira and GitHub contributions for comprehensive reviews.

How does sub-agent delegation work for processing engineer data?

Sub-agent delegation assigns data extraction and observation processing to specialized agents while the main thread manages MCP calls. This architecture processes Granola, Slack, Jira, and GitHub data concurrently to synthesize profile updates.

Can I use workflow automation to incrementally update performance profiles since the last run?

Yes, this workflow fetches new data from Granola, Slack, Jira, and GitHub since the last run to incrementally update profiles. It preserves existing profile sections while synthesizing new observations for current performance tracking.

Does this profile synthesis approach require specific error handling for data aggregation?

Yes, robust error handling is required to manage data aggregation from Granola, Slack, Jira, and GitHub. The defined processing architecture enforces strict MCP calls and sub-agent task execution to handle source failures gracefully.

When should I not use automated profile synthesis for engineer performance management?

Avoid automated profile synthesis if your data sources lack API access or if you need real-time rather than incremental updates. This workflow is optimized for periodic execution, such as weekly performance profile refreshes across engineering teams.