feat(agents): add product manager advisor and UX/UI designer agents by niksacdev · Pull Request #627 · microsoft/hve-core

niksacdev · 2026-02-16T16:57:28Z

Description

Adds two new agents to the hve-core library: Product Manager Advisor and UX/UI Designer, ported from github/awesome-copilot and restructured to align with hve-core conventions. Includes a standalone user journey template to support the UX agent's workflow.

These agents fill a gap in the project-planning collection by providing product management and UX research capabilities that complement existing agents (prd-builder, brd-builder, adr-creation).

Template Approach

Rather than creating custom GitHub/ADO issue templates (which already exist natively on both platforms), this PR takes a "Principles Over Format" approach:

The PM agent teaches story quality principles that apply across any issue template
The UX agent produces research artifacts using a standalone journey map template
Platform-specific template configuration is referenced via official documentation links

Human-in-the-Loop Guardrails

Both agents implement a three-layer approach to prevent hallucinated requirements:

Disclaimer: Clear statement that outputs are drafts requiring human validation
Core Principle: First principle explicitly requires human input validation
Active Probing: Workflow steps ask directly about user research evidence and label unvalidated inputs as assumptions

Related Issue(s)

Closes #90

Type of Change

Code & Documentation:

Bug fix (non-breaking change fixing an issue)
New feature (non-breaking change adding functionality)
Breaking change (fix or feature causing existing functionality to change)
Documentation update

AI Artifacts:

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

Sample Prompts (for AI Artifact Contributions)

Product Manager Advisor

User Request:

"I need to scope a new feature for automated build notifications. Help me structure the requirements."

Execution Flow:

Agent asks focused discovery questions: who is the user, what pain point does this solve, what measurable outcome defines success
Probes for evidence quality: has the team spoken with users about this need?
Guides story quality: scope, acceptance criteria, dependencies, boundaries
Applies prioritization framework if multiple features compete
Hands off to prd-builder or brd-builder for formal documentation

Output Artifacts:

Well-structured issues with evidence-tagged requirements
Prioritization recommendations with trade-off rationale
Handoff to PRD/BRD builders when formal documentation is needed

Success Indicators:

Each requirement has an identified evidence source (user research, analytics, or explicitly labeled as assumption)
Acceptance criteria are testable and specific
Issues are scoped to single-component, single-week deliverables

UX/UI Designer

User Request:

"We're redesigning the onboarding flow. Help me map the user journey and identify accessibility requirements."

Execution Flow:

Agent discovers user context: role, skill level, device, accessibility needs
Probes for research evidence: has the team conducted user interviews or usability studies?
Constructs JTBD analysis with evidence tagging
Maps journey stages with emotional and behavioral dimensions
Defines accessibility requirements (WCAG AA) integrated into the journey
Produces design handoff documentation

Output Artifacts:

JTBD analysis using docs/templates/user-journey-template.md
Journey map with think/feel/do dimensions per stage
Accessibility requirements integrated into journey stages
Design handoff with flow descriptions and principles

Success Indicators:

JTBD statement follows standard format (situation → action → outcome)
Each journey insight is tagged with evidence basis (observed, reported, or assumed)
Accessibility requirements cover keyboard, screen reader, and visual dimensions

Testing

Ran npm run lint:md — 0 errors
Ran npm run spell-check — 0 issues
Ran npm run lint:frontmatter — all checks passed
Ran npm run lint:md-links — all links valid
Ran npm run lint:ps — all PowerShell files passed

Checklist

Required Checks

Documentation is updated (if applicable)
Files follow existing naming conventions
Changes are backwards compatible (if applicable)
Tests added for new functionality (if applicable)

AI Artifact Contributions

Used /prompt-analyze to review contribution
Addressed all feedback from prompt-builder review
Verified contribution follows common standards and type-specific requirements

Required Automated Checks

Markdown linting: npm run lint:md
Spell checking: npm run spell-check
Frontmatter validation: npm run lint:frontmatter
Link validation: npm run lint:md-links
PowerShell analysis: npm run lint:ps

Security Considerations

This PR does not contain any sensitive or NDA information
Any new dependencies have been reviewed for security issues
Security-related scripts follow the principle of least privilege

Additional Notes

Both agents are added to project-planning.collection.yml and hve-core-all.collection.yml
Handoff prompts use plain-language instructions or existing slash commands (/task-research) — no nonexistent prompt files referenced
Attribution footers follow the standard Brought to you by microsoft/hve-core format
JTBD (Jobs-to-be-Done) added to cspell dictionary as a standard product management term

- add product-manager-advisor.agent.md with requirements discovery, story quality, and prioritization workflow - add ux-ui-designer.agent.md with JTBD analysis, user journey mapping, and accessibility requirements workflow - add docs/templates/user-journey-template.md as standalone reusable template for journey maps grounded in JTBD analysis - update CUSTOM-AGENTS.md with table entries and detail sections 🚀 - Generated by Copilot Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

codecov-commenter · 2026-02-16T16:59:11Z

Codecov Report

✅ All modified and coverable lines are covered by tests.
✅ Project coverage is 85.99%. Comparing base (0138a78) to head (93498be).
⚠️ Report is 1 commits behind head on main.

Additional details and impacted files

@@            Coverage Diff             @@
##             main     #627      +/-   ##
==========================================
- Coverage   86.01%   85.99%   -0.03%     
==========================================
  Files          24       24              
  Lines        4727     4727              
==========================================
- Hits         4066     4065       -1     
- Misses        661      662       +1

Flag	Coverage Δ
pester	`85.99% <ø> (-0.03%)`	⬇️

Flags with carried forward coverage won't be shown. Click here to find out more.
see 1 file with indirect coverage changes

🚀 New features to boost your workflow:

❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.

… agents - add prominent disclaimer that agent outputs require validation through real user interviews, stakeholder discussions, and observed behavior - add first core principle requiring human validation for both agents - flag unvalidated requirements as assumptions in discovery workflow Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

Copilot

Pull request overview

This PR ports the Product Manager Advisor and UX/UI Designer agents from the awesome-copilot repository into HVE Core, following the maintainer feedback from issue #90. The PR adds requirements discovery and UX research capabilities that integrate with existing document-building agents (prd-builder, brd-builder) by focusing on the pre-document validation phase.

Changes:

Adds product-manager-advisor agent for requirements discovery, story quality validation, and prioritization guidance
Adds ux-ui-designer agent for Jobs-to-be-Done analysis, user journey mapping, and accessibility requirements
Creates user-journey-template.md as a reusable template following existing template patterns
Updates .github/CUSTOM-AGENTS.md to document the new agents

Reviewed changes

Copilot reviewed 4 out of 4 changed files in this pull request and generated 2 comments.

File	Description
`.github/agents/product-manager-advisor.agent.md`	New agent providing requirements discovery and story quality guidance with handoffs to prd-builder, brd-builder, ux-ui-designer, and task-researcher
`.github/agents/ux-ui-designer.agent.md`	New agent for UX research artifacts including JTBD analysis and journey mapping with handoffs to product-manager-advisor and task-researcher
`docs/templates/user-journey-template.md`	New template for user journey documentation following the same structure as existing templates (brd-template.md, rca-template.md, etc.)
`.github/CUSTOM-AGENTS.md`	Added entries for both new agents in the agent catalog table and detail sections with proper workflow descriptions and handoff documentation

.github/agents/product-manager-advisor.agent.md

- add active evidence probing in Step 1 of both agents: agents now ask users directly whether they have conducted user interviews and what the source of each requirement or insight is - gate story creation on evidence quality: requirements without user evidence are labeled as unvalidated assumptions in outputs - add evidence source as a required dimension in story quality checklist - tag JTBD analysis elements with evidence basis (observed, reported, assumed) to surface confidence level in journey maps Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

- fix typo in GitHub docs URL (pull-partners → pull-requests) - add both agents to project-planning.collection.yml - add both agents to hve-core-all.collection.yml Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

niksacdev

Both review comments addressed in commit cdd8abd:

URL typo — Fixed pull-partners → pull-requests in the GitHub docs URL.
Collection manifests — Added both product-manager-advisor and ux-ui-designer to collections/project-planning.collection.yml (alongside prd-builder and brd-builder) and collections/hve-core-all.collection.yml (for broad availability).

Copilot

Pull request overview

Copilot reviewed 6 out of 6 changed files in this pull request and generated 2 comments.

.github/agents/product-manager-advisor.agent.md

.github/agents/ux-ui-designer.agent.md

WilliamBerryiii · 2026-02-16T18:02:02Z

Thank you for this PR, @niksacdev. We appreciate the thorough work porting the PM and UX agents.

Before we proceed with the review, we need a few things addressed:

Use the PR template: This repository has a pull request template that all submissions should follow. Please update your PR description to include the template sections — particularly the Type of Change checkboxes, the AI Artifact Contributions checklist, the Sample Prompts section, and Security Considerations. Since this PR adds agents and templates, the AI Artifacts checkboxes and sample prompts section are especially important.
Review the AI contributing guidelines: Please review docs/contributing/ai-artifacts-common.md for common standards (XML blocks, markdown quality, model version requirements, collection manifests) and docs/contributing/custom-agents.md for agent-specific requirements. These documents define the quality gates your contribution needs to pass.
Run the prompt-builder agent review: All AI artifact contributions should be reviewed using the prompt-builder agent (/prompt-analyze). Please run this against both agent files and address any feedback before requesting re-review.
Complete the required automated checks: The PR template lists the full set of required validation commands. Please confirm all of these pass and check them off in the template:
- npm run lint:md
- npm run spell-check
- npm run lint:frontmatter
- npm run lint:md-links
- npm run lint:ps

These steps help us maintain consistency across all AI artifact contributions. Please comment here if you have questions about any of the requirements.

- replace nonexistent slash commands in handoffs with plain-language prompts - use existing /task-research prompt for research handoffs - add attribution footer to both agent files and journey template - add JTBD to cspell dictionary 🔧 - Generated by Copilot Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

niksacdev · 2026-02-16T21:06:02Z

Thank you for the detailed onboarding checklist, @WilliamBerryiii. All items have been addressed:

1. PR template — Updated the PR description with the full template including Type of Change checkboxes, AI Artifact Contributions checklist, Sample Prompts section (with execution flows and success indicators for both agents), and Security Considerations.

2. Contributing guidelines — Reviewed docs/contributing/ai-artifacts-common.md and docs/contributing/custom-agents.md. Applied:

Attribution footers (Brought to you by microsoft/hve-core) on all three files
Collection manifest entries in project-planning.collection.yml and hve-core-all.collection.yml
Handoff prompts updated to use existing slash commands (/task-research) or plain-language instructions — no nonexistent prompt files referenced
JTBD added to cspell dictionary

3. Prompt-builder review — Reviewed both agents against prompt-builder standards. Addressed all feedback including writing style conventions, protocol patterns, and frontmatter requirements.

4. Automated checks — All five validation commands pass:

npm run lint:md — 0 errors
npm run spell-check — 0 issues
npm run lint:frontmatter — all checks passed
npm run lint:md-links — all links valid
npm run lint:ps — all PowerShell files passed

All automated review threads have been resolved as well.

Copilot

Pull request overview

Copilot reviewed 7 out of 7 changed files in this pull request and generated no new comments.

.github/agents/product-manager-advisor.agent.md

- remove language path from Azure DevOps documentation link per globalization convention - ran Link-Lang-Check.ps1 -Fix to identify locale-specific URLs 🔧 - Generated by Copilot Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

niksacdev · 2026-02-16T22:11:18Z

Fixed — stripped en-us locale from the Microsoft Learn URL on line 94. Ran Link-Lang-Check.ps1 to confirm no remaining locale-specific URLs in any files. ✅

- format table columns in user-journey-template.md per markdown-table-formatter - replace attribution footer with standard Copilot footer for docs/templates files - regenerate plugins to include new PM and UX agents 🔧 - Generated by Copilot Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

Copilot

Pull request overview

Copilot reviewed 13 out of 13 changed files in this pull request and generated no new comments.

- resolve .cspell.json conflict: move JTBD to industry-acronyms, invokable to general-technical - resolve plugins/project-planning/README.md: merge agent tables from both branches - keep all agents: agile-coach, product-manager-advisor, ux-ui-designer, subagents 🔀 - Generated by Copilot

WilliamBerryiii · 2026-02-18T00:46:55Z

@niksacdev - thanks for the contribution ... it's been merged to main. Expect the extension release 2.4.0 to happen later this week (if we can get the timing correct).

🤖 I have created a release *beep* *boop* --- ## [3.0.0](hve-core-v2.3.10...hve-core-v3.0.0) (2026-02-20) ### ⚠ BREAKING CHANGES * **skills:** migrate PR reference generation to self-contained skill ([#669](#669)) * restructure RPI collection to HVE Core naming convention ([#668](#668)) ### ✨ Features * **agents:** add agile-coach agent ([#562](#562)) ([de8d86c](de8d86c)) * **agents:** add DT coach agent with tiered instruction loading ([#656](#656)) ([206d3a7](206d3a7)) * **agents:** add product manager advisor and UX/UI designer agents ([#627](#627)) ([539eb8a](539eb8a)) * **agents:** add system architecture reviewer for design trade-offs and ADR creation ([#626](#626)) ([de5cfd6](de5cfd6)) * **build:** pin devcontainer image and align tool parity ([#704](#704)) ([6258b1c](6258b1c)) * **design-thinking:** add manufacturing industry context template ([#682](#682)) ([ce864bf](ce864bf)) * **instructions:** add DT coaching state protocol for session persistence ([#654](#654)) ([5a5be4e](5a5be4e)) * **instructions:** add dt-coaching-identity ambient instruction ([#642](#642)) ([6209a0d](6209a0d)) * **instructions:** add dt-method-01-deep for advanced scope conversation techniques ([#673](#673)) ([cc92ef9](cc92ef9)) * **instructions:** add dt-method-03-deep for advanced input synthesis techniques ([#676](#676)) ([0079a4f](0079a4f)) * **instructions:** add dt-method-09-deep instructions for Method 9 advanced coaching ([#703](#703)) ([150b2a6](150b2a6)) * **instructions:** add dt-method-sequencing ambient instruction ([#650](#650)) ([e465b2f](e465b2f)) * **instructions:** add dt-quality-constraints and design-thinking collection ([#645](#645)) ([17002bd](17002bd)) * **instructions:** add DT-to-RPI handoff contract specification ([#679](#679)) ([87f9962](87f9962)) * **instructions:** add energy industry context template ([#687](#687)) ([41088d8](41088d8)) * **instructions:** add healthcare industry context template ([#686](#686)) ([b2d5281](b2d5281)) * **instructions:** add Method 1 Scope Conversations coaching knowledge ([#651](#651)) ([93e2d48](93e2d48)) * **instructions:** add Method 2 Design Research coaching knowledge ([#652](#652)) ([30f7f3b](30f7f3b)) * **instructions:** add Method 3 Input Synthesis coaching knowledge ([#653](#653)) ([1efdb7d](1efdb7d)) * **instructions:** add Method 7 High-Fidelity Prototypes coaching instruction ([#666](#666)) ([9233eab](9233eab)) * **instructions:** add pull request instructions for PR generation workflow ([#706](#706)) ([73d23eb](73d23eb)) * **instructions:** create DT curriculum content (9 modules) ([#690](#690)) ([9f7378f](9f7378f)), closes [#617](#617) * **instructions:** create dt-method-02-deep.instructions.md ([#700](#700)) ([4d4d0ca](4d4d0ca)) * **instructions:** create dt-method-06-lofi-prototypes.instructions.md ([#684](#684)) ([4d5f757](4d5f757)) * **instructions:** create dt-method-07-deep.instructions.md ([#678](#678)) ([d3ec70d](d3ec70d)) * **instructions:** Create dt-method-08-deep.instructions.md ([#683](#683)) ([d9e1115](d9e1115)) * **instructions:** create dt-method-08-testing.instructions.md ([#681](#681)) ([3008ad8](3008ad8)) * **instructions:** create dt-method-09-iteration.instructions.md ([#685](#685)) ([9d7f4f5](9d7f4f5)) * **instructions:** create dt-rpi-research-context.instructions.md ([#689](#689)) ([34c7b89](34c7b89)) * **instructions:** create manufacturing reference learning scenario ([#692](#692)) ([1bd3994](1bd3994)) * **instructions:** Design Thinking Method 4 brainstorming instruction file ([#664](#664)) ([06f90b0](06f90b0)) * **prompts:** add DT start-project prompt for coaching initialization ([#657](#657)) ([ce583d5](ce583d5)) * **prompts:** add dt-resume-coaching prompt for session recovery ([#665](#665)) ([11b93cb](11b93cb)) * **prompts:** create dt-handoff-problem-space.prompt.md ([#688](#688)) ([277963d](277963d)) * **scripts:** add collection-level maturity field with validation, gating, and notices ([#697](#697)) ([7b1c8e8](7b1c8e8)) * **scripts:** add per-violation CI annotations and colorized console output ([#637](#637)) ([bd7d512](bd7d512)) * **skills:** edit SKILL frontmatter schema, add CI validation, and documentation ([#625](#625)) ([0138a78](0138a78)) * **skills:** mandate unit testing and document language support ([#636](#636)) ([9263617](9263617)) * **skills:** migrate PR reference generation to self-contained skill ([#669](#669)) ([cf8805f](cf8805f)) ### 🐛 Bug Fixes * **collections:** migrate artifacts into collection-based subdirectories ([#658](#658)) ([dfa5261](dfa5261)) * **instructions:** optimize Phase 1 DT token budgets and close [#564](https://github.com/microsoft/hve-core/issues/564)/[#565](https://github.com/microsoft/hve-core/issues/565) gaps ([#675](#675)) ([4f42f00](4f42f00)) * **scripts:** add CI annotations and step summary to copyright header check ([#638](#638)) ([5fa6328](5fa6328)) * **scripts:** add grouped link-lang console diagnostics and failure summary ([#661](#661)) ([4d6871f](4d6871f)) * **scripts:** add per-violation Write-Host and Write-CIAnnotation output to Test-DependencyPinning ([#640](#640)) ([9d3b71d](9d3b71d)) * **scripts:** align agent frontmatter schema with VS Code spec ([#469](#469)) ([254d445](254d445)) * **scripts:** optimize PSScriptAnalyzer linting performance in WSL2 ([#667](#667)) ([f120b93](f120b93)) * **scripts:** stabilize YAML display key ordering in collection manifest ([#701](#701)) ([73c0d2c](73c0d2c)) * **scripts:** use text stubs for plugin links when symlinks unavailable ([#695](#695)) ([d7650a3](d7650a3)) * **skills:** fix powershell test coverage in pr-reference skill ([#699](#699)) ([408e6b7](408e6b7)) ### 📚 Documentation * **dt:** add Method 5 Concepts and Method 6 Lo-Fi Prototypes instructions ([#693](#693)) ([cfdcf11](cfdcf11)) * **hve-guide:** add role-based guides and project lifecycle documentation ([#663](#663)) ([17a85da](17a85da)) ### ♻️ Refactoring * restructure RPI collection to HVE Core naming convention ([#668](#668)) ([120dde0](120dde0)) * **scripts:** consolidate duplicate logging into shared SecurityHelpers module ([#655](#655)) ([627a877](627a877)) * **scripts:** use shared SecurityHelpers and CIHelpers modules in security scripts ([#705](#705)) ([3a0baa7](3a0baa7)) ### 🔧 Maintenance * **deps-dev:** bump markdownlint-cli2 from 0.20.0 to 0.21.0 in the npm-dependencies group ([#609](#609)) ([1486dd7](1486dd7)) --- This PR was generated with [Release Please](https://github.com/googleapis/release-please). See [documentation](https://github.com/googleapis/release-please#release-please). Co-authored-by: hve-core-release-please[bot] <254602402+hve-core-release-please[bot]@users.noreply.github.com>

niksacdev requested a review from a team as a code owner February 16, 2026 16:57

Copilot AI review requested due to automatic review settings February 16, 2026 16:57

Copilot started reviewing on behalf of niksacdev February 16, 2026 16:58 View session

Copilot AI reviewed Feb 16, 2026

View reviewed changes

.github/agents/product-manager-advisor.agent.md Show resolved Hide resolved

.github/agents/product-manager-advisor.agent.md Show resolved Hide resolved

niksacdev and others added 2 commits February 16, 2026 17:03

Copilot AI review requested due to automatic review settings February 16, 2026 17:07

Copilot started reviewing on behalf of niksacdev February 16, 2026 17:07 View session

niksacdev commented Feb 16, 2026

View reviewed changes

Copilot AI reviewed Feb 16, 2026

View reviewed changes

.github/agents/product-manager-advisor.agent.md Outdated Show resolved Hide resolved

.github/agents/ux-ui-designer.agent.md Outdated Show resolved Hide resolved

This was referenced Feb 16, 2026

feat(agents): add system architecture reviewer for design trade-offs and ADR creation #626

Merged

feat(agents): Integrate Product Manager Advisor and UX/UI Designer Agents for Requirements Validation #90

Closed

Merge branch 'main' into feat/90-pm-ux-agents

9268acc

Copilot AI review requested due to automatic review settings February 16, 2026 21:09

Copilot started reviewing on behalf of niksacdev February 16, 2026 21:10 View session

Copilot AI reviewed Feb 16, 2026

View reviewed changes

WilliamBerryiii reviewed Feb 16, 2026

View reviewed changes

.github/agents/product-manager-advisor.agent.md Outdated Show resolved Hide resolved

Copilot AI review requested due to automatic review settings February 16, 2026 23:50

Copilot started reviewing on behalf of niksacdev February 16, 2026 23:50 View session

Copilot AI reviewed Feb 16, 2026

View reviewed changes

agreaves-ms approved these changes Feb 17, 2026

View reviewed changes

WilliamBerryiii merged commit 539eb8a into microsoft:main Feb 18, 2026
19 checks passed

hve-core-release-please bot mentioned this pull request Feb 18, 2026

chore(main): release hve-core 3.0.0 #644

Merged

Conversation

niksacdev commented Feb 16, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Description

Template Approach

Human-in-the-Loop Guardrails

Related Issue(s)

Type of Change

Sample Prompts (for AI Artifact Contributions)

Product Manager Advisor

UX/UI Designer

Testing

Checklist

Required Checks

AI Artifact Contributions

Required Automated Checks

Security Considerations

Additional Notes

Uh oh!

codecov-commenter commented Feb 16, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Codecov Report

Uh oh!

Copilot AI left a comment

Choose a reason for hiding this comment

Pull request overview

Reviewed changes

Uh oh!

Uh oh!

Uh oh!

niksacdev left a comment

Choose a reason for hiding this comment

Uh oh!

Copilot AI left a comment

Choose a reason for hiding this comment

Pull request overview

Uh oh!

Uh oh!

Uh oh!

WilliamBerryiii commented Feb 16, 2026

Uh oh!

niksacdev commented Feb 16, 2026

Uh oh!

Copilot AI left a comment

Choose a reason for hiding this comment

Pull request overview

Uh oh!

Uh oh!

niksacdev commented Feb 16, 2026

Uh oh!

Copilot AI left a comment

Choose a reason for hiding this comment

Pull request overview

Uh oh!

Uh oh!

WilliamBerryiii commented Feb 18, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

5 participants

niksacdev commented Feb 16, 2026 •

edited

Loading

codecov-commenter commented Feb 16, 2026 •

edited

Loading