learner

Extract learnings from task artifacts and merge them into project context files.

Updated Apr 28, 2026
One-click install
npx skills add https://github.com/PMKhai/claude-config --skill learner-pmkhai
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: learner
Source: https://github.com/PMKhai/claude-config/tree/main/skills/learner
Command: npx skills add https://github.com/PMKhai/claude-config --skill learner-pmkhai

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Teams often lose valuable insights from completed tasks, leading to repeated mistakes and wasted effort. The Learner Skill collects learnings from artifacts and merges them into the project's context file to preserve knowledge for future work.

Core Features & Use Cases

  • Extract learnings from artifacts such as SPEC.md, code-summary.md, and review notes.
  • Merge insights into projects/[project]/context.md without overwriting existing content, preserving history.
  • Append a Task History entry to track learning per task.

Quick Start

After a review is approved, run the learner to update the project context with the new learnings.

Frequently Asked Questions about learner

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

FAQPage Schema
How do I merge task learnings into a project context file without overwriting existing content?

The Learner extracts insights from artifacts such as SPEC.md, code-summary.md, and review notes, then appends them to projects/[project]/context.md in a structured way while preserving all existing content and history.

What is the best way to preserve knowledge from completed tasks for future project work?

The best way to preserve knowledge from completed tasks is to collect insights from project artifacts like fix-log.md and issues.md, then merge them into a central context file to prevent repeated mistakes and wasted effort.

How does artifact analysis work for extracting project context?

Artifact analysis for project context works by reading specified markdown files such as SPEC.md and code-summary.md, extracting relevant learnings, and appending a Task History entry to track learning per task.

Do I need to run a learning merge after a review is approved?

Yes, after a review is approved you should run the Learner to update the project context with new learnings, ensuring that approved insights are immediately preserved for future work.

Can I use this knowledge-management workflow with existing SPEC.md and issues.md files?

Yes, you can use this knowledge-management workflow with existing SPEC.md, issues.md, fix-log.md, and code-summary.md files, as it reads these artifacts and merges their learnings into the context file without duplication.