Draft and edit code, review changes, and run coding tasks across GitHub, the editor, and terminal.
AI SKILLS · Software engineering
Develop & review code with AI
Use a coding assistant to implement changes, then inspect and test the result.
Why this skill matters
Engineering judgment still determines whether generated code solves the right problem.
What to learn
- Give repository-specific context
- Inspect diffs and dependencies
- Test behavior beyond the generated happy path
Before you begin
Basic programming and version control
PUT IT INTO PRACTICE
Build a work sample
Implement a small feature in a practice repository. Review the diff and add a regression test that fails before the fix.
Evidence of progress
A reviewed change with meaningful tests and an explanation of tradeoffs.
This exercise is an original ToolGrail suggestion. Use public, synthetic, or approved data.
LEARNING RESOURCE
Review output from Copilot
GitHub Docs · Resource checked 2026-11-04
Open learning resource ↗This may be documentation, a framework, or a training path. Product access, accounts, or paid licenses may be needed for hands-on exercises.
Tools you could practice with
Chosen by an editor because they support this exercise. They are examples, not requirements or endorsements: use a tool you already have access to, with synthetic or approved data, and check its evidence level.
Use codebase context to generate, edit, and review software through an AI editor, terminal agent, and cloud agents.
Agentic coding tool that works in the terminal, IDE and desktop.
Bring code-aware chat, inline assistance, refactoring help, and coding agents into supported JetBrains IDEs.
Skill descriptions, exercises, and priorities are editorial. They are not professional qualifications or guarantees of employment. Read our skills methodology →
Find the right AI tools for any job, task or industry.