microsoft/hve-core
Publicmirrored fromhttps://github.com/microsoft/hve-coreAvailable
docs/contributing/prompts.md
547lines · modecode
| 1 | --- |
| 2 | title: 'Contributing Prompts to HVE Core' |
| 3 | description: 'Requirements and standards for contributing GitHub Copilot prompt files to hve-core' |
| 4 | sidebar_position: 4 |
| 5 | author: Microsoft |
| 6 | ms.date: 2025-11-26 |
| 7 | ms.topic: how-to |
| 8 | --- |
| 9 | |
| 10 | This guide defines the requirements, standards, and best practices for contributing GitHub Copilot prompt files (`.prompt.md`) to the hve-core library. |
| 11 | |
| 12 | ⚙️ Common Standards: See [AI Artifacts Common Standards](ai-artifacts-common.md) for shared requirements (XML blocks, markdown quality, RFC 2119, validation, testing). |
| 13 | |
| 14 | ## What is a Prompt? |
| 15 | |
| 16 | A **prompt** is a workflow-specific guidance document that provides context, requirements, and step-by-step instructions for GitHub Copilot to complete a particular task or process. Prompts are typically invoked in specific contexts or workflows. |
| 17 | |
| 18 | ## Use Cases for Prompts |
| 19 | |
| 20 | Create a prompt when you need to: |
| 21 | |
| 22 | * Guide a specific workflow or process (e.g., creating pull requests, processing work items) |
| 23 | * Provide context-sensitive instructions triggered by user actions |
| 24 | * Define a repeatable task with clear inputs and outputs |
| 25 | * Document a multi-step procedure for AI execution |
| 26 | * Establish standards for a particular type of deliverable |
| 27 | |
| 28 | ## File Structure Requirements |
| 29 | |
| 30 | ### Location |
| 31 | |
| 32 | Prompt files are typically organized in a collection subdirectory by convention: |
| 33 | |
| 34 | ```text |
| 35 | .github/prompts/{collection-id}/ |
| 36 | └── your-prompt-name.prompt.md |
| 37 | ``` |
| 38 | |
| 39 | > [!NOTE] |
| 40 | > Collections can reference artifacts from any subfolder. The `path:` field in collection YAML files |
| 41 | > accepts any valid repo-relative path regardless of the artifact's parent directory. |
| 42 | |
| 43 | ### Naming Convention |
| 44 | |
| 45 | * Use lowercase kebab-case: `pull-request.prompt.md` |
| 46 | * Be specific about workflow/task: `ado-create-pull-request.prompt.md` |
| 47 | * Include domain prefix when relevant: `ado-`, `git-`, `github-` |
| 48 | * Avoid generic names: `workflow.prompt.md` ❌ → `ado-process-my-work-items-for-task-planning.prompt.md` ✅ |
| 49 | |
| 50 | ### File Format |
| 51 | |
| 52 | Prompt files MUST: |
| 53 | |
| 54 | 1. Use the `.prompt.md` extension |
| 55 | 2. Start with valid YAML frontmatter between `---` delimiters |
| 56 | 3. Begin content directly after frontmatter |
| 57 | 4. End with single newline character |
| 58 | |
| 59 | ## Frontmatter Requirements |
| 60 | |
| 61 | ### Required Fields |
| 62 | |
| 63 | **`description`** (string, MANDATORY) |
| 64 | |
| 65 | | Property | Value | |
| 66 | |----------|--------------------------------------------------------------------------------------------------------------------| |
| 67 | | Purpose | Concise explanation of prompt purpose and use case | |
| 68 | | Format | Single sentence, 10-200 characters | |
| 69 | | Style | Sentence case with proper punctuation | |
| 70 | | Example | `'Required protocol for creating Azure DevOps pull requests with work item discovery and reviewer identification'` | |
| 71 | |
| 72 | **`mode`** (string enum, MANDATORY for prompts) |
| 73 | |
| 74 | | Property | Value | |
| 75 | |----------|----------------------------------------| |
| 76 | | Purpose | Defines when/how the prompt is invoked | |
| 77 | | Example | `workflow` | |
| 78 | |
| 79 | Valid values: |
| 80 | |
| 81 | * `agent` - Used by specialized AI agents |
| 82 | * `assistant` - General-purpose assistance context |
| 83 | * `copilot` - GitHub Copilot-specific workflows |
| 84 | * `workflow` - Automated workflow/pipeline context |
| 85 | |
| 86 | ### Optional Fields |
| 87 | |
| 88 | **`category`** (string enum) |
| 89 | |
| 90 | Organizes prompts by domain. |
| 91 | |
| 92 | Valid values: |
| 93 | |
| 94 | * `ado` - Azure DevOps workflows |
| 95 | * `git` - Git operations |
| 96 | * `documentation` - Documentation generation/maintenance |
| 97 | * `workflow` - General workflow automation |
| 98 | * `development` - Development tasks |
| 99 | |
| 100 | **`version`** (string) |
| 101 | |
| 102 | Tracks prompt revisions using semantic versioning (e.g., `1.0.0`). |
| 103 | |
| 104 | **`author`** (string) |
| 105 | |
| 106 | Attribution for the prompt creator (e.g., `microsoft/hve-core`, `your-team-name`). |
| 107 | |
| 108 | **`lastUpdated`** (string) |
| 109 | |
| 110 | Timestamp of last modification in ISO 8601 format (YYYY-MM-DD). |
| 111 | |
| 112 | ### Frontmatter Example |
| 113 | |
| 114 | ```yaml |
| 115 | --- |
| 116 | description: 'Required protocol for creating Azure DevOps pull requests with work item discovery, reviewer identification, and automated linking' |
| 117 | mode: 'workflow' |
| 118 | category: 'ado' |
| 119 | version: '1.0.0' |
| 120 | author: 'microsoft/hve-core' |
| 121 | lastUpdated: '2025-11-19' |
| 122 | --- |
| 123 | ``` |
| 124 | |
| 125 | ## Collection Entry Requirements |
| 126 | |
| 127 | All prompts must have matching entries in one or more `collections/*.collection.yml` manifests. Collection entries control distribution and maturity. |
| 128 | |
| 129 | ### Adding Your Prompt to a Collection |
| 130 | |
| 131 | After creating your prompt file, add an `items[]` entry in each target collection manifest: |
| 132 | |
| 133 | ```yaml |
| 134 | items: |
| 135 | # path can reference artifacts from any subfolder |
| 136 | - path: .github/prompts/{collection-id}/my-prompt.prompt.md |
| 137 | kind: prompt |
| 138 | maturity: stable |
| 139 | ``` |
| 140 | |
| 141 | ### Selecting Collections for Prompts |
| 142 | |
| 143 | Choose collections based on who invokes or benefits from the workflow: |
| 144 | |
| 145 | | Prompt Type | Recommended Collections | |
| 146 | |-------------------------|-------------------------------------------| |
| 147 | | Git/PR workflows | `hve-core-all`, `hve-core` | |
| 148 | | ADO work item workflows | `hve-core-all`, `ado`, `project-planning` | |
| 149 | | GitHub issue workflows | `hve-core-all`, `github` | |
| 150 | | RPI workflow prompts | `hve-core-all`, `hve-core` | |
| 151 | | Documentation workflows | `hve-core-all`, `hve-core` | |
| 152 | | Architecture prompts | `hve-core-all`, `project-planning` | |
| 153 | |
| 154 | For complete collection documentation, see [AI Artifacts Common Standards - Collection Manifests](ai-artifacts-common.md#collection-manifests-and-dependencies). |
| 155 | |
| 156 | ## Prompt Content Structure Standards |
| 157 | |
| 158 | ### Required Sections |
| 159 | |
| 160 | #### 1. Title (H1) |
| 161 | |
| 162 | * Clear, action-oriented heading describing the workflow |
| 163 | * Should align with filename and description |
| 164 | |
| 165 | ```markdown |
| 166 | # Azure DevOps Pull Request Creation Protocol |
| 167 | ``` |
| 168 | |
| 169 | #### 2. Overview/Purpose |
| 170 | |
| 171 | * Explains what the prompt does and when to use it |
| 172 | * Defines scope and prerequisites |
| 173 | * Lists expected outcomes |
| 174 | |
| 175 | ```markdown |
| 176 | ## Overview |
| 177 | |
| 178 | This prompt guides the creation of Azure DevOps pull requests with automated |
| 179 | work item discovery, reviewer identification, and compliance validation. |
| 180 | ``` |
| 181 | |
| 182 | #### 3. Prerequisites/Context |
| 183 | |
| 184 | * Lists required information, tools, or setup |
| 185 | * Specifies environment assumptions |
| 186 | * Defines input requirements |
| 187 | |
| 188 | ```markdown |
| 189 | ## Prerequisites |
| 190 | |
| 191 | * Active Azure DevOps connection |
| 192 | * Current branch with committed changes |
| 193 | * Work item IDs or branch naming following conventions |
| 194 | ``` |
| 195 | |
| 196 | #### 4. Workflow Steps |
| 197 | |
| 198 | * Provides clear, numbered steps for execution |
| 199 | * Uses imperative, unambiguous language |
| 200 | * Includes decision points and branching logic |
| 201 | * Specifies tool usage at each step |
| 202 | |
| 203 | ```markdown |
| 204 | ## Workflow Steps |
| 205 | |
| 206 | 1. Discovery Phase: Identify related work items from branch name or commit messages |
| 207 | 2. Reviewer Selection: Query ADO for default reviewers based on repository policies |
| 208 | 3. PR Creation: Generate PR with title, description, and work item links |
| 209 | 4. Validation: Verify PR was created successfully with correct metadata |
| 210 | ``` |
| 211 | |
| 212 | #### 5. Success Criteria |
| 213 | |
| 214 | * Defines completion conditions |
| 215 | * Specifies validation checkpoints |
| 216 | * Lists expected artifacts |
| 217 | |
| 218 | ```markdown |
| 219 | ## Success Criteria |
| 220 | |
| 221 | * [ ] PR created in target repository |
| 222 | * [ ] Work items linked to PR |
| 223 | * [ ] Required reviewers added |
| 224 | * [ ] PR description follows template |
| 225 | ``` |
| 226 | |
| 227 | #### 6. Examples |
| 228 | |
| 229 | * Demonstrates correct usage with realistic scenarios |
| 230 | * Shows input/output patterns |
| 231 | * Wraps in XML-style blocks for reusability |
| 232 | |
| 233 | #### 7. Error Handling |
| 234 | |
| 235 | * Documents common failure modes |
| 236 | * Provides recovery procedures |
| 237 | * Specifies fallback behaviors |
| 238 | |
| 239 | #### 8. Attribution Footer |
| 240 | |
| 241 | Always include an attribution footer at the end of the file. |
| 242 | |
| 243 | ```markdown |
| 244 | --- |
| 245 | |
| 246 | Brought to you by microsoft/hve-core |
| 247 | ``` |
| 248 | |
| 249 | ### XML-Style Block Requirements |
| 250 | |
| 251 | See [AI Artifacts Common Standards - XML-Style Block Standards](ai-artifacts-common.md#xml-style-block-standards) for complete rules and examples. |
| 252 | |
| 253 | ### Template Variable Standards |
| 254 | |
| 255 | Use `{{double_curly_braces}}` for placeholders: |
| 256 | |
| 257 | <!-- <example-template-variables> --> |
| 258 | ```yaml |
| 259 | # ✅ CORRECT: Template variables in YAML frontmatter |
| 260 | --- |
| 261 | title: "{{feature_name}} - {{brief_description}}" |
| 262 | branch: "feature/{{work_item_id}}-{{task_name}}" |
| 263 | assignee: "{{user_email}}" |
| 264 | --- |
| 265 | |
| 266 | # ❌ INCORRECT: Non-standard variable syntax in YAML frontmatter |
| 267 | --- |
| 268 | title: "<feature-name> - <brief-description>" |
| 269 | branch: "feature/<work-item-id>-<task-name>" |
| 270 | assignee: "<user.email>" |
| 271 | --- |
| 272 | ``` |
| 273 | <!-- </example-template-variables> --> |
| 274 | |
| 275 | #### Variable Naming |
| 276 | |
| 277 | * Use snake_case: `{{work_item_id}}`, `{{user_name}}` |
| 278 | * Be descriptive: `{{target_branch}}` not `{{tb}}` |
| 279 | * Group related variables: `{{pr_title}}`, `{{pr_description}}`, `{{pr_labels}}` |
| 280 | |
| 281 | ### Directive Language Standards |
| 282 | |
| 283 | Use RFC 2119 compliant keywords (MUST/SHOULD/MAY). See [AI Artifacts Common Standards - RFC 2119 Directive Language](ai-artifacts-common.md#rfc-2119-directive-language) for complete guidance. |
| 284 | |
| 285 | ## Workflow Definition Standards |
| 286 | |
| 287 | Prompts should clearly define: |
| 288 | |
| 289 | ### Entry Points |
| 290 | |
| 291 | What triggers this prompt: |
| 292 | |
| 293 | ```markdown |
| 294 | ## Invocation |
| 295 | |
| 296 | This prompt is invoked when: |
| 297 | |
| 298 | * User requests "create ADO pull request" |
| 299 | * User runs command: `/prompt ado-create-pull-request` |
| 300 | * Workflow automation reaches PR creation step |
| 301 | ``` |
| 302 | |
| 303 | ### Decision Points |
| 304 | |
| 305 | Where choices affect flow: |
| 306 | |
| 307 | ```markdown |
| 308 | ## Decision Logic |
| 309 | |
| 310 | **If** work items found in branch name: |
| 311 | → Use those work items for linking |
| 312 | |
| 313 | **Else if** work items in commit messages: |
| 314 | → Extract and use those work items |
| 315 | |
| 316 | Else: |
| 317 | → Prompt user for work item IDs |
| 318 | ``` |
| 319 | |
| 320 | ### Tool Usage |
| 321 | |
| 322 | Which tools are used and when: |
| 323 | |
| 324 | ```markdown |
| 325 | ## Required Tools |
| 326 | |
| 327 | 1. `mcp_azure_devops` - Work item queries and PR creation |
| 328 | 2. `git/*` - Branch and commit information |
| 329 | 3. `search` - Repository policy lookups |
| 330 | ``` |
| 331 | |
| 332 | ### Output Specifications |
| 333 | |
| 334 | What artifacts are produced: |
| 335 | |
| 336 | ```markdown |
| 337 | ## Output Artifacts |
| 338 | |
| 339 | 1. Pull Request: Created in ADO with metadata |
| 340 | 2. Handoff Document: `.copilot-tracking/pr/{{YYYY-MM-DD}}-pr-{{id}}-handoff.md` |
| 341 | 3. Validation Report: Summary of PR creation status |
| 342 | ``` |
| 343 | |
| 344 | ## Context Requirements |
| 345 | |
| 346 | Prompts **SHOULD** specify: |
| 347 | |
| 348 | ### File/Path Contexts |
| 349 | |
| 350 | When specific files/paths trigger behavior: |
| 351 | |
| 352 | ```yaml |
| 353 | --- |
| 354 | description: 'Required protocol for creating Azure DevOps pull requests' |
| 355 | mode: 'workflow' |
| 356 | applyTo: '**/.copilot-tracking/pr/new/**' # Workflow-specific context |
| 357 | --- |
| 358 | ``` |
| 359 | |
| 360 | ### Data Requirements |
| 361 | |
| 362 | What information must be available: |
| 363 | |
| 364 | ```markdown |
| 365 | ## Required Context |
| 366 | |
| 367 | * `{{current_branch}}` - Active git branch name |
| 368 | * `{{target_branch}}` - Destination branch (default: main/master) |
| 369 | * `{{repository_url}}` - ADO repository URL |
| 370 | * `{{user_email}}` - Current user's email for reviewer queries |
| 371 | ``` |
| 372 | |
| 373 | ### State Assumptions |
| 374 | |
| 375 | What must be true before execution: |
| 376 | |
| 377 | ```markdown |
| 378 | ## Preconditions |
| 379 | |
| 380 | * Working directory is a git repository |
| 381 | * Changes are committed to current branch |
| 382 | * User has ADO credentials configured |
| 383 | * Target branch exists in remote repository |
| 384 | ``` |
| 385 | |
| 386 | ## Output Formatting Requirements |
| 387 | |
| 388 | Define how the prompt produces results: |
| 389 | |
| 390 | ### Response Format |
| 391 | |
| 392 | Structure for user-facing output: |
| 393 | |
| 394 | ```markdown |
| 395 | ## Output Format |
| 396 | |
| 397 | ### PR Creation Summary |
| 398 | |
| 399 | Status: [Success|Failed] |
| 400 | PR ID: [ID] |
| 401 | PR URL: [URL] |
| 402 | Work Items Linked: [IDs] |
| 403 | Reviewers Added: [Names] |
| 404 | |
| 405 | ### Validation Results |
| 406 | |
| 407 | * [x] PR created successfully |
| 408 | * [x] Work items linked |
| 409 | * [ ] CI pipeline triggered |
| 410 | ``` |
| 411 | |
| 412 | ### File Outputs |
| 413 | |
| 414 | Specifications for generated files: |
| 415 | |
| 416 | ```markdown |
| 417 | ## Handoff Document Format |
| 418 | |
| 419 | File: `.copilot-tracking/pr/{{YYYY-MM-DD}}-pr-{{id}}-handoff.md` |
| 420 | |
| 421 | Content: |
| 422 | |
| 423 | * PR metadata (ID, URL, title) |
| 424 | * Work item links with status |
| 425 | * Reviewer assignments |
| 426 | * Validation checklist |
| 427 | ``` |
| 428 | |
| 429 | ### Error Reporting |
| 430 | |
| 431 | Format for failure scenarios: |
| 432 | |
| 433 | ```markdown |
| 434 | ## Error Format |
| 435 | |
| 436 | Error Type: [Authentication|Validation|Network] |
| 437 | Message: [Detailed error description] |
| 438 | Recovery Steps: |
| 439 | |
| 440 | 1. [Step to resolve] |
| 441 | 2. [Alternative approach] |
| 442 | ``` |
| 443 | |
| 444 | ## Validation Checklist |
| 445 | |
| 446 | Before submitting your prompt, verify: |
| 447 | |
| 448 | ### Frontmatter |
| 449 | |
| 450 | * [ ] Valid YAML between `---` delimiters |
| 451 | * [ ] `description` field present and descriptive (10-200 chars) |
| 452 | * [ ] `mode` field present with valid value |
| 453 | * [ ] `category` field appropriate for domain (if present) |
| 454 | * [ ] No trailing whitespace in values |
| 455 | * [ ] Single newline at EOF |
| 456 | |
| 457 | ### Content Structure |
| 458 | |
| 459 | * [ ] Clear H1 title describing workflow |
| 460 | * [ ] Overview/purpose section |
| 461 | * [ ] Maturity set in collection item (see [Common Standards - Maturity](ai-artifacts-common.md#maturity-field-requirements)) |
| 462 | * [ ] Prerequisites or context section |
| 463 | * [ ] Workflow steps with clear sequence |
| 464 | * [ ] Success criteria defined |
| 465 | * [ ] Error handling documented |
| 466 | * [ ] Attribution footer present |
| 467 | |
| 468 | ### Workflow Definition |
| 469 | |
| 470 | * [ ] Entry points/triggers specified |
| 471 | * [ ] Decision logic clearly documented |
| 472 | * [ ] Tool usage requirements listed |
| 473 | * [ ] Output artifacts defined |
| 474 | * [ ] State assumptions documented |
| 475 | |
| 476 | ### Common Standards |
| 477 | |
| 478 | * [ ] Markdown quality (see [Common Standards - Markdown Quality](ai-artifacts-common.md#markdown-quality-standards)) |
| 479 | * [ ] XML-style blocks properly formatted (see [Common Standards - XML-Style Blocks](ai-artifacts-common.md#xml-style-block-standards)) |
| 480 | * [ ] RFC 2119 keywords used consistently (see [Common Standards - RFC 2119](ai-artifacts-common.md#rfc-2119-directive-language)) |
| 481 | * [ ] Template variables use `{{snake_case}}` |
| 482 | |
| 483 | ### Technical Validation |
| 484 | |
| 485 | * [ ] All file references point to existing files |
| 486 | * [ ] External links are valid and accessible |
| 487 | * [ ] Tool references use correct names |
| 488 | * [ ] Template variables are clearly defined |
| 489 | |
| 490 | ### Integration |
| 491 | |
| 492 | * [ ] Aligns with `.github/copilot-instructions.md` |
| 493 | * [ ] Follows repository conventions |
| 494 | * [ ] Compatible with existing prompts/workflows |
| 495 | * [ ] Does not duplicate existing prompt functionality |
| 496 | |
| 497 | ## Testing Your Prompt |
| 498 | |
| 499 | See [AI Artifacts Common Standards - Common Testing Practices](ai-artifacts-common.md#common-testing-practices) for testing guidelines. For prompts specifically: |
| 500 | |
| 501 | 1. Follow prompt steps manually to verify workflow logic |
| 502 | 2. Test with AI execution using realistic scenarios |
| 503 | 3. Verify all output artifacts match specifications |
| 504 | 4. Test decision points with different data conditions |
| 505 | |
| 506 | ## Common Issues and Fixes |
| 507 | |
| 508 | ### Prompt-Specific Issues |
| 509 | |
| 510 | ### Template Variables with Wrong Format |
| 511 | |
| 512 | Using incorrect syntax for template variables (angle brackets or shell-style) causes failures. Always use `{{variable_name}}` handlebars format for template variables. |
| 513 | |
| 514 | ### Ambiguous Workflow Steps |
| 515 | |
| 516 | Vague workflow steps without specific tools, conditions, or decision logic cause confusion. Provide explicit tool usage, decision trees, and fallback strategies with clear conditional logic. |
| 517 | |
| 518 | For additional common issues (XML blocks, markdown, directives), see [AI Artifacts Common Standards - Common Issues and Fixes](ai-artifacts-common.md#common-issues-and-fixes). |
| 519 | |
| 520 | ## Automated Validation |
| 521 | |
| 522 | Run these commands before submission (see [Common Standards - Common Validation](ai-artifacts-common.md#common-validation-standards)): |
| 523 | |
| 524 | * `npm run lint:frontmatter` |
| 525 | * `npm run lint:md` |
| 526 | * `npm run spell-check` |
| 527 | * `npm run lint:md-links` |
| 528 | |
| 529 | All checks **MUST** pass before merge. |
| 530 | |
| 531 | ## Related Documentation |
| 532 | |
| 533 | * [AI Artifacts Common Standards](ai-artifacts-common.md) - Shared standards for all contributions |
| 534 | * [Contributing Custom Agents](custom-agents.md) - AI agent configuration files |
| 535 | * [Contributing Instructions](instructions.md) - Technology-specific standards |
| 536 | * [Pull Request Template](https://github.com/microsoft/hve-core/blob/main/.github/PULL_REQUEST_TEMPLATE.md) - Submission requirements |
| 537 | |
| 538 | ## Getting Help |
| 539 | |
| 540 | See [AI Artifacts Common Standards - Getting Help](ai-artifacts-common.md#getting-help) for support resources. For prompt-specific assistance, review existing examples in `.github/prompts/{collection-id}/` (the conventional location for prompt files). |
| 541 | |
| 542 | --- |
| 543 | |
| 544 | <!-- markdownlint-disable MD036 --> |
| 545 | *🤖 Crafted with precision by ✨Copilot following brilliant human instruction, |
| 546 | then carefully refined by our team of discerning human reviewers.* |
| 547 | <!-- markdownlint-enable MD036 --> |
| 548 | |