Skip to content

feat(skills): create user-invocable code-review skill#2099

Open
PratikWayase wants to merge 1 commit into
microsoft:mainfrom
PratikWayase:feat/code-review-skill
Open

feat(skills): create user-invocable code-review skill#2099
PratikWayase wants to merge 1 commit into
microsoft:mainfrom
PratikWayase:feat/code-review-skill

Conversation

@PratikWayase

Copy link
Copy Markdown
Contributor

Closes #2071

Pull Request

Description

Extract and migrate the durable review knowledge from existing code-review agents into a new user-invocable code-review skill. This skill serves as the shared knowledge base (canonical reference contract) for the consolidated orchestrator, owning review depth, perspective lenses, output formatting, and severity classification.

Related Issues

Type of Change

Select all that apply:

Code & Documentation

  • Bug fix (non-breaking change fixing an issue)
  • New feature (non-breaking change adding functionality)
  • Breaking change
  • Documentation update

Infrastructure & Configuration

  • GitHub Actions workflow
  • Linting configuration
  • Security configuration
  • DevContainer configuration
  • Dependency update

AI Artifacts

  • Reviewed with prompt-builder agent and addressed feedback
  • Copilot instruction (.github/instructions/*.instructions.md)
  • Copilot prompt (.github/prompts/*.prompt.md)
  • Copilot agent (.github/agents/*.agent.md)
  • Copilot skill (.github/skills/*/SKILL.md)

Other

  • Script/automation
  • Other (describe):

Sample Prompt

User Request:
Review the changes in this branch using the code-review skill.

Execution Flow:

  1. Agent invokes code-review skill
  2. Skill runs Tier 0 Context Bootstrap (scope, diff, filtering, size classification)
  3. Skill selects appropriate Depth Tier (Basic / Standard / Comprehensive)
  4. Applies Perspective Lenses (Functional, Standards, Accessibility, PR, Security)
  5. Generates structured review output

Output Includes:

  • Executive Summary
  • Changed Files Overview
  • Issues by Severity (Critical / High / Medium / Low)
  • Positive Changes
  • Testing Recommendations
  • Review Disclaimer

Success Criteria:
All validation commands pass with zero errors:

  • npm run validate:skills
  • npm run lint:frontmatter
  • npm run lint:md
  • npm run spell-check
  • npm run lint:all

Testing

All validation passed locally:

  • npm run validate:skills
  • npm run lint:frontmatter
  • npm run lint:md
  • npm run spell-check
  • npm run lint:all

Checklist

Required

  • Documentation updated
  • Naming conventions followed
  • Backward compatible changes

AI Artifacts

  • Used /prompt-analyze review
  • Addressed feedback from prompt-builder
  • Follows skill + agent standards

Automated Checks

  • Markdown linting (npm run lint:md)
  • Spell check (npm run spell-check)
  • Frontmatter validation (npm run lint:frontmatter)
  • Skill validation (npm run validate:skills)
  • Link validation (npm run lint:md-links)
  • PowerShell lint (npm run lint:ps)
  • Plugin freshness (npm run plugin:generate)
  • Docusaurus tests (npm run docs:test)

Security Considerations

  • No sensitive or NDA data included
  • Dependencies reviewed for security
  • Follows least-privilege principles

Additional Notes

This PR establishes the foundational skill layer required for parent issue #2070. After merge, it enables the unified skill-backed orchestrator agent (#2072).

@PratikWayase PratikWayase requested a review from a team as a code owner June 21, 2026 06:31
@WilliamBerryiii

Copy link
Copy Markdown
Member

@PratikWayase my apologies ... I have a PR inbound for this that's got a super comprehensive skill based redo of the work.

@WilliamBerryiii

Copy link
Copy Markdown
Member

I have created PR #2100 as the target update for this issue set. Again, @PratikWayase, my apologies for the confusion ... I didn't get to finish getting the PR out last night before I fell asleep and sorry for the duplicate work. I really appreciate all that you've done for the project, it's been amazingly helpful to have folks swing in to knock stuff out.

@codecov-commenter

Copy link
Copy Markdown

Codecov Report

✅ All modified and coverable lines are covered by tests.
✅ Project coverage is 80.59%. Comparing base (b69e34a) to head (2ddbd7b).
⚠️ Report is 7 commits behind head on main.

Additional details and impacted files

Impacted file tree graph

@@            Coverage Diff             @@
##             main    #2099      +/-   ##
==========================================
+ Coverage   80.52%   80.59%   +0.06%     
==========================================
  Files         128      118      -10     
  Lines       19260    19184      -76     
  Branches       12        0      -12     
==========================================
- Hits        15510    15462      -48     
+ Misses       3747     3722      -25     
+ Partials        3        0       -3     
Flag Coverage Δ
docusaurus ?
pester 84.23% <ø> (-0.02%) ⬇️

Flags with carried forward coverage won't be shown. Click here to find out more.
see 11 files with indirect coverage changes

🚀 New features to boost your workflow:
  • ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.
  • 📦 JS Bundle Analysis: Save yourself from yourself by tracking and limiting bundle sizes in JS merges.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

feat(skills): Create user-invocable code-review skill

3 participants