Skip to content

Conversation

@anchildress1
Copy link
Contributor

  • HLBPA is a high-level, big-picture architect for systems documentation
  • It can be used either in VSC as usual or dropped in coding agent for auto-updates
  • Depends on user's prompting skills to get the best results
  • Will default to a more generalist mode if not enough context is given
  • Minor updates to README and CONTRIBUTING to fix formatting errors

Assisted-by: GitHub Copilot & Verdent AI

Pull Request Checklist

  • I have read and followed the CONTRIBUTING.md guidelines.
  • My contribution adds a new instruction, prompt, or chat mode file in the correct directory.
  • The file follows the required naming convention.
  • The content is clearly structured and follows the example format.
  • I have tested my instructions, prompt, or chat mode with GitHub Copilot.
  • I have run node update-readme.js and verified that README.md is up to date.

Description

Introducing the High-Level Big Picture Architect (HLBPA) chat mode, a specialized AI persona designed for generating and reviewing high-level architectural documentation. HLBPA focuses on system-level concerns—interfaces, data flows, contracts, and failure modes—while deliberately excluding low-level implementation details.

Key capabilities:

  • Generates architectural documentation in GitHub Flavored Markdown (GFM) with Mermaid diagrams
  • Supports multiple artifact types: overviews, diagrams, use cases, gap scans, and test case documentation
  • Enforces accessibility standards (ARIA tags, alt text) for all diagrams
  • Language/stack agnostic approach using interface signatures rather than syntax
  • Operates in read-only mode, avoids modifying codebase or tests
  • Batches information requests to minimize user interruptions
  • Perfect for: Post-sprint documentation updates, legacy system exploration, onboarding materials, and architectural review sessions.
  • Depends on user's prompt for direction, but falls back to high-level generalizations if missing

Type of Contribution

  • New instruction file.
  • New prompt file.
  • New chat mode file.
  • Other (please specify):

Additional Notes

The HLBPA chat mode complements existing personas by filling a gap in architectural documentation workflows. It intentionally avoids code generation, focusing purely on documentation artifacts stored under ./docs (unless otherwise specified). All generated content includes RAI footers and follows markdownlint conventions.

Example prompts to use with this chat mode:

Generate all documentation for a repo:

this is a complicated app that I need to be brought up to speed on quickly. Your goal is to generate a comprehensive set of docs in the `/docs` folder that covers all major flows in the codebase, broken down into sensible sections per flow. 

First, this app is a part of a distributed infrastructure. Include a high level overview of where this app fits into the systems architecture, but also drill down to the flows from the time the app is first triggered until completion. Generate this information at both a sequence and flow level. 

It's also important to understand the data relationships that are used in this app and how that's different between input from other sources. Use ER diagrams to highlight this app’s primary purpose from a data standpoint in addition to the systems information. 

Next, provide a comprehensive analysis of the current state of testing for this app with a focus on any unit or integration tests. Include performance or other specialty tests, if they exist. Identify any areas of concern in the testing setup along with recommendations for improvement, if applicable. 

Fourth, provide a detailed analysis of the current state of this app versus desired best case scenarios. It should highlight both the things this app does well and include gaps in logic or design that may need attention now or could be enhanced later to provide significant benefits in the future. List these in order by impact and timeline of estimated amount of work. For any suggested improvement, include a T-shirt size amount of effort (XS, S, M, L, XLG, etc.). 

Finally the last report is a comprehensive high-level overview of all recent changes, deployments, versions/releases. Use git as needed, but only include items that have already been merged to `main` or commits explicitly included directly or squashed in a release version. Any other branches or dev work should be explicitly ignored. 

If there are any other recommendations for reports that may highlight specific edge cases not covered here then please also include them along with your analysis.

Also works with much more targeted prompt:

Your task is to research functionality related to the endpoint accessible at `/controller/endpoint`, including how this may potentially interact with other systems. Identify any potential influencers to SLAs or places in the code that could have a direct impact if modified. Start with a generalized flowchart that explains what the system is doing. Also include a sequence diagram that clearly outlines the flow of data from input to database. Include anything else you determine to be immediately relevant in thoroughly explaining this functionality and use case.

By submitting this pull request, I confirm that my contribution abides by the Code of Conduct and will be licensed under the MIT License.

- HLBPA is a high-level, big-picture architect for systems documentation
- It can be used either in VSC as usual or dropped in coding agent for auto-updates
- Depends on user's prompting skills to get the best results
- Will default to a more generalist mode if not enough context is given
- Minor updates to README and CONTRIBUTING to fix formatting errors

Assisted-by: GitHub Copilot & Verdent AI
Signed-off-by: Ashley Childress <[email protected]>
@Copilot Copilot AI review requested due to automatic review settings October 1, 2025 20:37
Copy link
Contributor

Copilot AI left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Pull Request Overview

This PR adds a new High-Level Big Picture Architect (HLBPA) chat mode designed for generating and reviewing high-level architectural documentation. The chat mode focuses on system-level concerns like interfaces, data flows, and failure modes while avoiding low-level implementation details.

Key changes:

  • Introduces a comprehensive HLBPA chat mode with structured documentation capabilities
  • Updates README.md formatting to improve consistency and readability
  • Adds HLBPA entry to the chat modes table with installation badges

Reviewed Changes

Copilot reviewed 4 out of 5 changed files in this pull request and generated 4 comments.

File Description
chatmodes/hlbpa.chatmode.md New chat mode file implementing the HLBPA architectural documentation assistant
README.md Formatting improvements including proper code block language hints and spacing
README.chatmodes.md Adds HLBPA entry to the chat modes table
CONTRIBUTING.md Minor formatting fixes for headings and link references

- Copilot complains about the copy in the md fence
- Isn't likely to be used in this context anyway

Assisted-by: GitHub Copilot
Signed-off-by: Ashley Childress <[email protected]>
@aaronpowell aaronpowell merged commit 383c9be into github:main Oct 2, 2025
2 checks passed
@anchildress1 anchildress1 deleted the add-hlbpa-chat-mode branch October 2, 2025 05:10
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.

2 participants