Skip to content

docs: expand AGENTS.md with actionable contributor guidance#116

Draft
Tyler-R-Kendrick wants to merge 1 commit into
mainfrom
optimize-agents-md-f3a78466667ae2c9
Draft

docs: expand AGENTS.md with actionable contributor guidance#116
Tyler-R-Kendrick wants to merge 1 commit into
mainfrom
optimize-agents-md-f3a78466667ae2c9

Conversation

@Tyler-R-Kendrick

Copy link
Copy Markdown
Owner

Overview

Optimized AGENTS.md from a minimal 21-line document into a comprehensive, actionable guide for contributors. The original document was terse and left many implementation details ambiguous.

Target File

  • Path: AGENTS.md (repository root)
  • Original size: 21 lines, 4 sections
  • Optimized size: 362 lines, 6 sections (added TOC and Visual Validation)
  • Selection reason: No existing trainer workspace; prioritized for fresh optimization

Workspace

  • Local workspace: .trainer-workspace/AGENTS/
  • Iteration: iteration-1
  • Datasets created: 3 training cases, 2 validation cases covering contributor workflows

Key Improvements

1. Git Usage Section

  • Added: Explanation of why git mv preserves file history
  • Added: What breaks if you don't (git blame, history tracking)
  • Added: Concrete bash command examples
  • Benefit: Contributors understand the WHY behind the convention

2. Agent-Skills Workflow (NEW comprehensive section)

  • Added: Full directory structure explanation
  • Added: 6-step setup guide with exact paths and commands
  • Added: Symlink rationale and cross-platform instructions
  • Benefit: New contributors can complete setup without confusion

3. Code Development & Testing (EXPANDED)

  • Added: Explicit definition of "100% coverage"
  • Added: pytest-cov tool specification and invocation
  • Added: Pre-commit checklist for code review
  • Added: Python example testing edge cases
  • Benefit: Contributors know exactly which tool and how to verify coverage

4. Scaffolding (EXPANDED)

  • Added: Project-type-specific subsections (Python/uv, Node/npm, .NET/dotnet, Skills)
  • Added: Real command examples for each
  • Added: "What NOT to do" warning list
  • Benefit: Contributors select the right tool with concrete examples

5. Visual Validation (NEW section)

  • Added: Playwright introduction and benefits
  • Added: Python and Node.js example code (fully working)
  • Added: Step-by-step PR integration instructions
  • Added: Best practices for visual testing
  • Benefit: New capability now documented with working examples

Validation

  • All 856 tests pass (baseline maintained)
  • Markdown valid (no syntax errors)
  • Five test scenarios covered: Each scenario addressing common contributor friction points now has clear, actionable answers
  • Tone preserved: Maintains professional, friendly voice while being more instructional

Test Scenarios Addressed

  1. New contributor setup: Complete paths and step-by-step instructions
  2. Git workflow: Understanding why git mv is required
  3. Test coverage: Explicit tool (pytest-cov) and verification steps
  4. Scaffolding tool selection: 4 concrete examples with real commands
  5. Visual validation: New section with Playwright examples and PR steps

Files Modified

  • AGENTS.md: Expanded from 21 to 362 lines

Artifacts in Workspace

  • Engineer prompt review: .trainer-workspace/AGENTS/engineer-prompt/review.md
  • Training/validation datasets: .trainer-workspace/AGENTS/iterations/iteration-1/synthesize/{train,val}.jsonl
  • Optimized candidate: .trainer-workspace/AGENTS/iterations/iteration-1/optimize/optimized-prompt.md
  • Decision summary: .trainer-workspace/AGENTS/decision.md
  • Validation log: .trainer-workspace/AGENTS/iterations/iteration-1/validation/pytest.txt

Why This Optimization

The expanded AGENTS.md directly addresses the most common contributor friction points identified in the engineer-prompt review. Each section now includes rationale, concrete examples, and step-by-step instructions that remove ambiguity.

Generated by Train Prompt · ● 1.3M ·

- Expand git usage section with rationale and consequences
- Add comprehensive agent-skills workflow setup guide
- Clarify 100% test coverage requirement with pytest-cov details
- Add scaffolding examples for Python, Node.js, .NET, and skills
- New: Visual Validation section with Playwright examples and PR integration
- Add table of contents for improved scannability
- Grow from 21 lines to 362 lines with concrete step-by-step guidance

Validation: All 856 tests pass. Five test scenarios covering common contributor friction points now have clear answers.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
@coderabbitai

coderabbitai Bot commented Jun 8, 2026

Copy link
Copy Markdown

Important

Review skipped

Draft detected.

Please check the settings in the CodeRabbit UI or the .coderabbit.yaml file in this repository. To trigger a single review, invoke the @coderabbitai review command.

⚙️ Run configuration

Configuration used: defaults

Review profile: CHILL

Plan: Pro Plus

Run ID: a38e0035-ab0e-4ee9-b390-a3240a8c6020

You can disable this status message by setting the reviews.review_status to false in the CodeRabbit configuration file.

Use the checkbox below for a quick retry:

  • 🔍 Trigger review
✨ Finishing Touches
🧪 Generate unit tests (beta)
  • Create PR with unit tests
  • Commit unit tests in branch optimize-agents-md-f3a78466667ae2c9

Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out.

❤️ Share

Comment @coderabbitai help to get the list of available commands and usage tips.

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.

1 participant