Merge 015c74c46f into d419ac8a70

feat: add editorial review tasks for structure and prose (#1307 )
* feat: add editorial review tasks for structure and prose Add two complementary editorial review tasks: - editorial-review-structure.xml: Structural editor that proposes cuts, reorganization, and simplification. Includes 5 document archetype models (Tutorial, Reference, Explanation, Prompt, Strategic) for targeted evaluation. - editorial-review-prose.xml: Clinical copy-editor for prose improvements using Microsoft Writing Style Guide as baseline. Both tasks support humans and llm target audiences with different principles. * fix: add content-sacrosanct guardrail to editorial review tasks Both editorial review tasks (prose and structure) were missing the key constraint that reviewers should never challenge the ideas/knowledge themselves—only how clearly they are communicated. This restores the original design intent. Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> * fix: align reader_type parameter naming across editorial tasks Prose task was using 'target_audience' for the humans/llm optimization flag while structure task correctly separates 'target_audience' (who reads) from 'reader_type' (optimization mode). Aligns to reader_type. Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com> Co-authored-by: Brian <bmadcode@gmail.com>
2026-01-12 17:27:24 +01:00 · 2026-01-13 00:20:04 +08:00 · 2026-01-05 10:24:53 +01:00 · 2025-12-29 00:16:38 +01:00 · 2025-12-28 23:44:40 +01:00
8 changed files with 646 additions and 6 deletions
--- a/src/core/tasks/editorial-review-prose.xml
+++ b/src/core/tasks/editorial-review-prose.xml
@ -0,0 +1,91 @@
 <task id="_bmad/core/tasks/editorial-review-prose.xml"
  name="Editorial Review - Prose"
  description="Clinical copy-editor that reviews text for communication issues"
  standalone="false">
  <objective>Review text for communication issues that impede comprehension and output suggested fixes in a three-column table</objective>
  <inputs>
    <input name="content" required="true" desc="Cohesive unit of text to review (markdown, plain text, or text-heavy XML)" />
    <input name="reader_type" required="false" default="humans" desc="'humans' (default) for standard editorial, 'llm' for precision focus" />
  </inputs>
  <llm critical="true">
    <i>MANDATORY: Execute ALL steps in the flow section IN EXACT ORDER</i>
    <i>DO NOT skip steps or change the sequence</i>
    <i>HALT immediately when halt-conditions are met</i>
    <i>Each action xml tag within step xml tag is a REQUIRED action to complete that step</i>
    <i>You are a clinical copy-editor: precise, professional, neither warm nor cynical</i>
    <i>Apply Microsoft Writing Style Guide principles as your baseline</i>
    <i>Focus on communication issues that impede comprehension - not style preferences</i>
    <i>NEVER rewrite for preference - only fix genuine issues</i>
    <i critical="true">CONTENT IS SACROSANCT: Never challenge ideas—only clarify how they're expressed.</i>
    <principles>
      <i>Minimal intervention: Apply the smallest fix that achieves clarity</i>
      <i>Preserve structure: Fix prose within existing structure, never restructure</i>
      <i>Skip code/markup: Detect and skip code blocks, frontmatter, structural markup</i>
      <i>When uncertain: Flag with a query rather than suggesting a definitive change</i>
      <i>Deduplicate: Same issue in multiple places = one entry with locations listed</i>
      <i>No conflicts: Merge overlapping fixes into single entries</i>
      <i>Respect author voice: Preserve intentional stylistic choices</i>
    </principles>
  </llm>
  <flow>
    <step n="1" title="Validate Input">
      <action>Check if content is empty or contains fewer than 3 words</action>
      <action if="empty or fewer than 3 words">HALT with error: "Content too short for editorial review (minimum 3 words required)"</action>
      <action>Validate reader_type is "humans" or "llm" (or not provided, defaulting to "humans")</action>
      <action if="reader_type is invalid">HALT with error: "Invalid reader_type. Must be 'humans' or 'llm'"</action>
      <action>Identify content type (markdown, plain text, XML with text)</action>
      <action>Note any code blocks, frontmatter, or structural markup to skip</action>
    </step>
    <step n="2" title="Analyze Style">
      <action>Analyze the style, tone, and voice of the input text</action>
      <action>Note any intentional stylistic choices to preserve (informal tone, technical jargon, rhetorical patterns)</action>
      <action>Calibrate review approach based on reader_type parameter</action>
      <action if="reader_type='llm'">Prioritize: unambiguous references, consistent terminology, explicit structure, no hedging</action>
      <action if="reader_type='humans'">Prioritize: clarity, flow, readability, natural progression</action>
    </step>
    <step n="3" title="Editorial Review" critical="true">
      <action>Review all prose sections (skip code blocks, frontmatter, structural markup)</action>
      <action>Identify communication issues that impede comprehension</action>
      <action>For each issue, determine the minimal fix that achieves clarity</action>
      <action>Deduplicate: If same issue appears multiple times, create one entry listing all locations</action>
      <action>Merge overlapping issues into single entries (no conflicting suggestions)</action>
      <action>For uncertain fixes, phrase as query: "Consider: [suggestion]?" rather than definitive change</action>
      <action>Preserve author voice - do not "improve" intentional stylistic choices</action>
    </step>
    <step n="4" title="Output Results">
      <action if="issues found">Output a three-column markdown table with all suggested fixes</action>
      <action if="no issues found">Output: "No editorial issues identified"</action>
      <output-format>
 | Original Text | Revised Text | Changes |
 |---------------|--------------|---------|
 | The exact original passage | The suggested revision | Brief explanation of what changed and why |
      </output-format>
      <example title="Correct output format">
 | Original Text | Revised Text | Changes |
 |---------------|--------------|---------|
 | The system will processes data and it handles errors. | The system processes data and handles errors. | Fixed subject-verb agreement ("will processes" to "processes"); removed redundant "it" |
 | Users can chose from options (lines 12, 45, 78) | Users can choose from options | Fixed spelling: "chose" to "choose" (appears in 3 locations) |
      </example>
    </step>
  </flow>
  <halt-conditions>
    <condition>HALT with error if content is empty or fewer than 3 words</condition>
    <condition>HALT with error if reader_type is not "humans" or "llm"</condition>
    <condition>If no issues found after thorough review, output "No editorial issues identified" (this is valid completion, not an error)</condition>
  </halt-conditions>
 </task>
--- a/src/core/tasks/editorial-review-structure.xml
+++ b/src/core/tasks/editorial-review-structure.xml
@ -0,0 +1,198 @@
 <?xml version="1.0"?>
 <!-- if possible, run this in a separate subagent or process with read access to the project, 
  but no context except the content to review -->
 <task id="_bmad/core/tasks/editorial-review-structure.xml"
  name="Editorial Review - Structure"
  description="Structural editor that proposes cuts, reorganization,
    and simplification while preserving comprehension"
  standalone="false">
  <objective>Review document structure and propose substantive changes
    to improve clarity and flow-run this BEFORE copy editing</objective>
  <inputs>
    <input name="content" required="true"
      desc="Document to review (markdown, plain text, or structured content)"/>
    <input name="purpose" required="false"
      desc="Document's intended purpose (e.g., 'quickstart tutorial',
        'API reference', 'conceptual overview')"/>
    <input name="target_audience" required="false"
      desc="Who reads this? (e.g., 'new users', 'experienced developers',
        'decision makers')"/>
    <input name="reader_type" required="false" default="humans"
      desc="'humans' (default) preserves comprehension aids;
        'llm' optimizes for precision and density"/>
    <input name="length_target" required="false"
      desc="Target reduction (e.g., '30% shorter', 'half the length',
        'no limit')"/>
  </inputs>
  <llm critical="true">
    <i>MANDATORY: Execute ALL steps in the flow section IN EXACT ORDER</i>
    <i>DO NOT skip steps or change the sequence</i>
    <i>HALT immediately when halt-conditions are met</i>
    <i>Each action xml tag within step xml tag is a REQUIRED action to complete that step</i>
    <i>You are a structural editor focused on HIGH-VALUE DENSITY</i>
    <i>Brevity IS clarity: Concise writing respects limited attention spans and enables effective scanning</i>
    <i>Every section must justify its existence-cut anything that delays understanding</i>
    <i>True redundancy is failure</i>
    <principles>
      <i>Comprehension through calibration: Optimize for the minimum words needed to maintain understanding</i>
      <i>Front-load value: Critical information comes first; nice-to-know comes last (or goes)</i>
      <i>One source of truth: If information appears identically twice, consolidate</i>
      <i>Scope discipline: Content that belongs in a different document should be cut or linked</i>
      <i>Propose, don't execute: Output recommendations-user decides what to accept</i>
      <i critical="true">CONTENT IS SACROSANCT: Never challenge ideas—only optimize how they're organized.</i>
    </principles>
    <human-reader-principles>
      <i>These elements serve human comprehension and engagement-preserve unless clearly wasteful:</i>
      <i>Visual aids: Diagrams, images, and flowcharts anchor understanding</i>
      <i>Expectation-setting: "What You'll Learn" helps readers confirm they're in the right place</i>
      <i>Reader's Journey: Organize content biologically (linear progression), not logically (database)</i>
      <i>Mental models: Overview before details prevents cognitive overload</i>
      <i>Warmth: Encouraging tone reduces anxiety for new users</i>
      <i>Whitespace: Admonitions and callouts provide visual breathing room</i>
      <i>Summaries: Recaps help retention; they're reinforcement, not redundancy</i>
      <i>Examples: Concrete illustrations make abstract concepts accessible</i>
      <i>Engagement: "Flow" techniques (transitions, variety) are functional, not "fluff"-they maintain attention</i>
    </human-reader-principles>
    <llm-reader-principles>
      <i>When reader_type='llm', optimize for PRECISION and UNAMBIGUITY:</i>
      <i>Dependency-first: Define concepts before usage to minimize hallucination risk</i>
      <i>Cut emotional language, encouragement, and orientation sections</i>
      <i>
        IF concept is well-known from training (e.g., "conventional
          commits", "REST APIs"): Reference the standard-don't re-teach it
        ELSE: Be explicit-don't assume the LLM will infer correctly
      </i>
      <i>Use consistent terminology-same word for same concept throughout</i>
      <i>Eliminate hedging ("might", "could", "generally")-use direct statements</i>
      <i>Prefer structured formats (tables, lists, YAML) over prose</i>
      <i>Reference known standards ("conventional commits", "Google style guide") to leverage training</i>
      <i>STILL PROVIDE EXAMPLES even for known standards-grounds the LLM in your specific expectation</i>
      <i>Unambiguous references-no unclear antecedents ("it", "this", "the above")</i>
      <i>Note: LLM documents may be LONGER than human docs in some areas
        (more explicit) while shorter in others (no warmth)</i>
    </llm-reader-principles>
    <structure-models>
      <model name="Tutorial/Guide (Linear)" applicability="Tutorials, detailed guides, how-to articles, walkthroughs">
        <i>Prerequisites: Setup/Context MUST precede action</i>
        <i>Sequence: Steps must follow strict chronological or logical dependency order</i>
        <i>Goal-oriented: clear 'Definition of Done' at the end</i>
      </model>
      <model name="Reference/Database" applicability="API docs, glossaries, configuration references, cheat sheets">
        <i>Random Access: No narrative flow required; user jumps to specific item</i>
        <i>MECE: Topics are Mutually Exclusive and Collectively Exhaustive</i>
        <i>Consistent Schema: Every item follows identical structure (e.g., Signature to Params to Returns)</i>
      </model>
      <model name="Explanation (Conceptual)"
        applicability="Deep dives, architecture overviews, conceptual guides,
          whitepapers, project context">
        <i>Abstract to Concrete: Definition to Context to Implementation/Example</i>
        <i>Scaffolding: Complex ideas built on established foundations</i>
      </model>
      <model name="Prompt/Task Definition (Functional)"
        applicability="BMAD tasks, prompts, system instructions, XML definitions">
        <i>Meta-first: Inputs, usage constraints, and context defined before instructions</i>
        <i>Separation of Concerns: Instructions (logic) separate from Data (content)</i>
        <i>Step-by-step: Execution flow must be explicit and ordered</i>
      </model>
      <model name="Strategic/Context (Pyramid)" applicability="PRDs, research reports, proposals, decision records">
        <i>Top-down: Conclusion/Status/Recommendation starts the document</i>
        <i>Grouping: Supporting context grouped logically below the headline</i>
        <i>Ordering: Most critical information first</i>
        <i>MECE: Arguments/Groups are Mutually Exclusive and Collectively Exhaustive</i>
        <i>Evidence: Data supports arguments, never leads</i>
      </model>
    </structure-models>
  </llm>
  <flow>
    <step n="1" title="Validate Input">
      <action>Check if content is empty or contains fewer than 3 words</action>
      <action if="empty or fewer than 3 words">HALT with error: "Content
        too short for substantive review (minimum 3 words required)"</action>
      <action>Validate reader_type is "humans" or "llm" (or not provided, defaulting to "humans")</action>
      <action if="reader_type is invalid">HALT with error: "Invalid reader_type. Must be 'humans' or 'llm'"</action>
      <action>Identify document type and structure (headings, sections, lists, etc.)</action>
      <action>Note the current word count and section count</action>
    </step>
    <step n="2" title="Understand Purpose">
      <action>If purpose was provided, use it; otherwise infer from content</action>
      <action>If target_audience was provided, use it; otherwise infer from content</action>
      <action>Identify the core question the document answers</action>
      <action>State in one sentence: "This document exists to help [audience] accomplish [goal]"</action>
      <action>Select the most appropriate structural model from structure-models based on purpose/audience</action>
      <action>Note reader_type and which principles apply (human-reader-principles or llm-reader-principles)</action>
    </step>
    <step n="3" title="Structural Analysis" critical="true">
      <action>Map the document structure: list each major section with its word count</action>
      <action>Evaluate structure against the selected model's primary rules
        (e.g., 'Does recommendation come first?' for Pyramid)</action>
      <action>For each section, answer: Does this directly serve the stated purpose?</action>
      <action if="reader_type='humans'">For each comprehension aid (visual,
        summary, example, callout), answer: Does this help readers
        understand or stay engaged?</action>
      <action>Identify sections that could be: cut entirely, merged with
        another, moved to a different location, or split</action>
      <action>Identify true redundancies: identical information repeated
        without purpose (not summaries or reinforcement)</action>
      <action>Identify scope violations: content that belongs in a different document</action>
      <action>Identify burying: critical information hidden deep in the document</action>
    </step>
    <step n="4" title="Flow Analysis">
      <action>Assess the reader's journey: Does the sequence match how readers will use this?</action>
      <action>Identify premature detail: explanation given before the reader needs it</action>
      <action>Identify missing scaffolding: complex ideas without adequate setup</action>
      <action>Identify anti-patterns: FAQs that should be inline, appendices
        that should be cut, overviews that repeat the body verbatim</action>
      <action if="reader_type='humans'">Assess pacing: Is there enough
        whitespace and visual variety to maintain attention?</action>
    </step>
    <step n="5" title="Generate Recommendations">
      <action>Compile all findings into prioritized recommendations</action>
      <action>Categorize each recommendation: CUT (remove entirely),
        MERGE (combine sections), MOVE (reorder), CONDENSE (shorten
        significantly), QUESTION (needs author decision), PRESERVE
        (explicitly keep-for elements that might seem cuttable but
        serve comprehension)</action>
      <action>For each recommendation, state the rationale in one sentence</action>
      <action>Estimate impact: how many words would this save (or cost, for PRESERVE)?</action>
      <action>If length_target was provided, assess whether recommendations meet it</action>
      <action if="reader_type='humans' and recommendations would cut
        comprehension aids">Flag with warning: "This cut may impact
        reader comprehension/engagement"</action>
    </step>
    <step n="6" title="Output Results">
      <action>Output document summary (purpose, audience, reader_type, current length)</action>
      <action>Output the recommendation list in priority order</action>
      <action>Output estimated total reduction if all recommendations accepted</action>
      <action if="no recommendations">Output: "No substantive changes recommended-document structure is sound"</action>
      <output-format>
 ## Document Summary
 - **Purpose:** [inferred or provided purpose]
 - **Audience:** [inferred or provided audience]
 - **Reader type:** [selected reader type]
 - **Structure model:** [selected structure model]
 - **Current length:** [X] words across [Y] sections
 ## Recommendations
 ### 1. [CUT/MERGE/MOVE/CONDENSE/QUESTION/PRESERVE] - [Section or element name]
 **Rationale:** [One sentence explanation]
 **Impact:** ~[X] words
 **Comprehension note:** [If applicable, note impact on reader understanding]
 ### 2. ...
 ## Summary
 - **Total recommendations:** [N]
 - **Estimated reduction:** [X] words ([Y]% of original)
 - **Meets length target:** [Yes/No/No target specified]
 - **Comprehension trade-offs:** [Note any cuts that sacrifice reader engagement for brevity]
      </output-format>
    </step>
  </flow>
  <halt-conditions>
    <condition>HALT with error if content is empty or fewer than 3 words</condition>
    <condition>HALT with error if reader_type is not "humans" or "llm"</condition>
    <condition>If no structural issues found, output "No substantive changes
      recommended" (this is valid completion, not an error)</condition>
  </halt-conditions>
 </task>
--- a/src/core/tasks/review-adversarial-general.xml
+++ b/src/core/tasks/review-adversarial-general.xml
@ -9,6 +9,11 @@
  </inputs>
  <llm critical="true">
    <i>MANDATORY: Execute ALL steps in the flow section IN EXACT ORDER</i>
    <i>DO NOT skip steps or change the sequence</i>
    <i>HALT immediately when halt-conditions are met</i>
    <i>Each action xml tag within step xml tag is a REQUIRED action to complete that step</i>
    <i>You are a cynical, jaded reviewer with zero patience for sloppy work</i>
    <i>The content was submitted by a clueless weasel and you expect to find problems</i>
    <i>Be skeptical of everything</i>
--- a/src/modules/bmm/workflows/3-solutioning/check-implementation-readiness/steps/step-06-final-assessment.md
+++ b/src/modules/bmm/workflows/3-solutioning/check-implementation-readiness/steps/step-06-final-assessment.md
@ -111,6 +111,29 @@ Report generated: {outputFile}
 The assessment found [number] issues requiring attention. Review the detailed report for specific findings and recommendations."
 ### 6. Update IDE Prompt Recommendations
 If the readiness status is **READY**, update `.vscode/settings.json` to prioritize the implementation cycle prompts.
 Read the existing `chat.promptFilesRecommendations` object and modify these keys:
 **Set to `true` (implementation cycle - "keep going" loop):**
 - `bmd-create-story`
 - `bmd-dev-story`
 - `bmd-code-review`
 - `bmd-retrospective`
 - `bmd-correct-course`
 **Set to `false` (setup phase - already completed):**
 - `bmd-workflow-init`
 - `bmd-brainstorm`
 - `bmd-prd`
 - `bmd-ux-design`
 - `bmd-create-architecture`
 - `bmd-epics-stories`
 - `bmd-implementation-readiness`
 - `bmd-sprint-planning`
 ## WORKFLOW COMPLETE
 The implementation readiness workflow is now complete. The report contains all findings and recommendations for the user to consider.
--- a/src/modules/bmm/workflows/4-implementation/sprint-planning/instructions.md
+++ b/src/modules/bmm/workflows/4-implementation/sprint-planning/instructions.md
@ -179,6 +179,38 @@ development_status:
 </step>
 <step n="6" goal="Update IDE prompt recommendations for implementation phase">
 <action>Read the existing `.vscode/settings.json` and update the `chat.promptFilesRecommendations` object.</action>
 **Set to `true` (implementation cycle - "keep going" loop):**
 - `bmd-create-story`
 - `bmd-dev-story`
 - `bmd-code-review`
 - `bmd-retrospective`
 - `bmd-correct-course`
 **Set to `false` (setup phase - already completed):**
 - `bmd-workflow-init`
 - `bmd-brainstorm`
 - `bmd-prd`
 - `bmd-ux-design`
 - `bmd-create-architecture`
 - `bmd-epics-stories`
 - `bmd-implementation-readiness`
 - `bmd-sprint-planning`
 <action>Inform {user_name}:</action>
 **IDE Updated for Implementation Phase**
 The "keep going" cycle prompts are now prioritized in VS Code:
 - **@bmd-custom-bmm-sm → *create-story** (prepare a story)
 - **@bmd-custom-bmm-dev → *dev-story** (implement it)
 - **Same chat → *code-review** (review the code)
 - **Repeat!**
 </step>
 </workflow>
 ## Additional Documentation
--- a/tools/cli/installers/lib/ide/github-copilot.js
+++ b/tools/cli/installers/lib/ide/github-copilot.js
@ -2,6 +2,7 @@ const path = require('node:path');
 const { BaseIdeSetup } = require('./_base-ide');
 const chalk = require('chalk');
 const { AgentCommandGenerator } = require('./shared/agent-command-generator');
 const { WorkflowPromptGenerator } = require('./shared/workflow-prompt-generator');
 /**
 * GitHub Copilot setup handler
@ -12,6 +13,7 @@ class GitHubCopilotSetup extends BaseIdeSetup {
    super('github-copilot', 'GitHub Copilot', true); // preferred IDE
    this.configDir = '.github';
    this.agentsDir = 'agents';
    this.promptsDir = 'prompts';
    this.vscodeDir = '.vscode';
  }
@ -94,14 +96,12 @@ class GitHubCopilotSetup extends BaseIdeSetup {
  async setup(projectDir, bmadDir, options = {}) {
    console.log(chalk.cyan(`Setting up ${this.name}...`));
    // Configure VS Code settings using pre-collected config if available
    const config = options.preCollectedConfig || {};
    await this.configureVsCodeSettings(projectDir, { ...options, ...config });
    // Create .github/agents directory
    const githubDir = path.join(projectDir, this.configDir);
    const agentsDir = path.join(githubDir, this.agentsDir);
    const promptsDir = path.join(githubDir, this.promptsDir);
    await this.ensureDir(agentsDir);
    await this.ensureDir(promptsDir);
    // Clean up any existing BMAD files before reinstalling
    await this.cleanup(projectDir);
@ -117,22 +117,37 @@ class GitHubCopilotSetup extends BaseIdeSetup {
      const agentContent = await this.createAgentContent({ module: artifact.module, name: artifact.name }, content);
      // Use bmd- prefix: bmd-custom-{module}-{name}.agent.md
-      const targetPath = path.join(agentsDir, `bmd-custom-${artifact.module}-${artifact.name}.agent.md`);
+      const agentFileName = `bmd-custom-${artifact.module}-${artifact.name}`;
      const targetPath = path.join(agentsDir, `${agentFileName}.agent.md`);
      await this.writeFile(targetPath, agentContent);
      agentCount++;
-      console.log(chalk.green(`  ✓ Created agent: bmd-custom-${artifact.module}-${artifact.name}`));
+      console.log(chalk.green(`  ✓ Created agent: ${agentFileName}`));
    }
    // Generate workflow prompts from config (shared logic)
    // Each prompt includes nextSteps guidance for the agent to suggest next workflows
    const promptGen = new WorkflowPromptGenerator();
    const promptRecommendations = await promptGen.generatePromptFiles(promptsDir, options.selectedModules || []);
    const promptCount = Object.keys(promptRecommendations).length;
    // Configure VS Code settings using pre-collected config if available
    const config = options.preCollectedConfig || {};
    await this.configureVsCodeSettings(projectDir, { ...options, ...config, promptRecommendations });
    console.log(chalk.green(`✓ ${this.name} configured:`));
    console.log(chalk.dim(`  - ${agentCount} agents created`));
    console.log(chalk.dim(`  - ${promptCount} workflow prompts configured`));
    console.log(chalk.dim(`  - Agents directory: ${path.relative(projectDir, agentsDir)}`));
    console.log(chalk.dim(`  - Prompts directory: ${path.relative(projectDir, promptsDir)}`));
    console.log(chalk.dim(`  - VS Code settings configured`));
    console.log(chalk.dim('\n  Agents available in VS Code Chat view'));
    console.log(chalk.dim('  Workflow prompts show as new chat starters'));
    return {
      success: true,
      agents: agentCount,
      prompts: promptCount,
      settings: true,
    };
  }
@ -199,6 +214,11 @@ class GitHubCopilotSetup extends BaseIdeSetup {
      };
    }
    // Add prompt file recommendations for new chat starters
    if (options.promptRecommendations && Object.keys(options.promptRecommendations).length > 0) {
      bmadSettings['chat.promptFilesRecommendations'] = options.promptRecommendations;
    }
    // Merge settings (existing take precedence)
    const mergedSettings = { ...bmadSettings, ...existingSettings };
@ -307,6 +327,24 @@ ${cleanContent}
        console.log(chalk.dim(`  Cleaned up ${removed} existing BMAD agents`));
      }
    }
    // Clean up prompts directory
    const promptsDir = path.join(projectDir, this.configDir, this.promptsDir);
    if (await fs.pathExists(promptsDir)) {
      const files = await fs.readdir(promptsDir);
      let removed = 0;
      for (const file of files) {
        if (file.startsWith('bmd-') && file.endsWith('.prompt.md')) {
          await fs.remove(path.join(promptsDir, file));
          removed++;
        }
      }
      if (removed > 0) {
        console.log(chalk.dim(`  Cleaned up ${removed} existing BMAD prompt files`));
      }
    }
  }
  /**
--- a/tools/cli/installers/lib/ide/shared/workflow-prompt-generator.js
+++ b/tools/cli/installers/lib/ide/shared/workflow-prompt-generator.js
@ -0,0 +1,61 @@
 const path = require('node:path');
 const fs = require('fs-extra');
 const { workflowPromptsConfig } = require('./workflow-prompts-config');
 /**
 * Generate workflow prompt recommendations for IDE new chat starters
 * Uses static configuration from workflow-prompts-config.js which mirrors
 * the workflows documented in quick-start.md
 *
 * The implementation-readiness and sprint-planning workflows update
 * VS Code settings to toggle which prompts are shown based on project phase.
 */
 class WorkflowPromptGenerator {
  /**
   * Get workflow prompts for selected modules
   * @param {Array<string>} selectedModules - Modules to include (e.g., ['bmm', 'bmgd'])
   * @returns {Array<Object>} Array of workflow prompt configurations
   */
  getWorkflowPrompts(selectedModules = []) {
    const allPrompts = [];
    // Always include core prompts
    if (workflowPromptsConfig.core) {
      allPrompts.push(...workflowPromptsConfig.core);
    }
    // Add prompts for each selected module
    for (const moduleName of selectedModules) {
      if (workflowPromptsConfig[moduleName]) {
        allPrompts.push(...workflowPromptsConfig[moduleName]);
      }
    }
    return allPrompts;
  }
  /**
   * Generate prompt files for an IDE
   * @param {string} promptsDir - Directory to write prompt files
   * @param {Array<string>} selectedModules - Modules to include
   * @returns {Object} Map of prompt names to true for VS Code settings
   */
  async generatePromptFiles(promptsDir, selectedModules = []) {
    const prompts = this.getWorkflowPrompts(selectedModules);
    const recommendations = {};
    for (const prompt of prompts) {
      const promptContent = ['---', `agent: ${prompt.agent}`, `description: "${prompt.description}"`, '---', '', prompt.prompt, ''].join(
        '\n',
      );
      const promptFilePath = path.join(promptsDir, `bmd-${prompt.name}.prompt.md`);
      await fs.writeFile(promptFilePath, promptContent);
      recommendations[`bmd-${prompt.name}`] = true;
    }
    return recommendations;
  }
 }
 module.exports = { WorkflowPromptGenerator };
--- a/tools/cli/installers/lib/ide/shared/workflow-prompts-config.js
+++ b/tools/cli/installers/lib/ide/shared/workflow-prompts-config.js
@ -0,0 +1,192 @@
 /**
 * Workflow prompt configuration for IDE new chat starters
 *
 * This configuration defines the workflow prompts that appear as suggestions
 * when starting a new chat in VS Code (via chat.promptFilesRecommendations).
 *
 * The implementation-readiness and sprint-planning workflows update the
 * VS Code settings to toggle which prompts are shown based on project phase.
 *
 * Reference: docs/modules/bmm-bmad-method/quick-start.md
 */
 const workflowPromptsConfig = {
  // BMad Method Module (bmm) - Standard development workflow
  bmm: [
    // ═══════════════════════════════════════════════════════════════════════
    // Phase 1 - Analysis (Optional)
    // ═══════════════════════════════════════════════════════════════════════
    {
      name: 'workflow-init',
      agent: 'bmd-custom-bmm-analyst',
      shortcut: 'WI',
      description: '[WI] Initialize workflow and choose planning track',
      prompt: '*workflow-init',
    },
    {
      name: 'brainstorm',
      agent: 'bmd-custom-bmm-analyst',
      shortcut: 'BP',
      description: '[BP] Brainstorm project ideas and concepts',
      prompt: '*brainstorm-project',
    },
    {
      name: 'workflow-status',
      agent: 'bmd-custom-bmm-pm',
      shortcut: 'WS',
      description: '[WS] Check current workflow status and next steps',
      prompt: '*workflow-status',
    },
    // ═══════════════════════════════════════════════════════════════════════
    // Phase 2 - Planning (Required)
    // ═══════════════════════════════════════════════════════════════════════
    {
      name: 'prd',
      agent: 'bmd-custom-bmm-pm',
      shortcut: 'PD',
      description: '[PD] Create Product Requirements Document (PRD)',
      prompt: '*prd',
    },
    {
      name: 'ux-design',
      agent: 'bmd-custom-bmm-ux-designer',
      shortcut: 'UD',
      description: '[UD] Create UX Design specification',
      prompt: '*ux-design',
    },
    // ═══════════════════════════════════════════════════════════════════════
    // Phase 3 - Solutioning
    // ═══════════════════════════════════════════════════════════════════════
    {
      name: 'create-architecture',
      agent: 'bmd-custom-bmm-architect',
      shortcut: 'CA',
      description: '[CA] Create system architecture document',
      prompt: '*create-architecture',
    },
    {
      name: 'epics-stories',
      agent: 'bmd-custom-bmm-pm',
      shortcut: 'ES',
      description: '[ES] Create Epics and User Stories from PRD',
      prompt: '*epics-stories',
    },
    {
      name: 'implementation-readiness',
      agent: 'bmd-custom-bmm-architect',
      shortcut: 'IR',
      description: '[IR] Check implementation readiness across all docs',
      prompt: '*implementation-readiness',
    },
    {
      name: 'sprint-planning',
      agent: 'bmd-custom-bmm-sm',
      shortcut: 'SP',
      description: '[SP] Initialize sprint planning from epics',
      prompt: '*sprint-planning',
    },
    // ═══════════════════════════════════════════════════════════════════════
    // Phase 4 - Implementation: The "Keep Going" Cycle
    // SM → create-story → DEV → dev-story → code-review → (create-story | retrospective)
    // ═══════════════════════════════════════════════════════════════════════
    {
      name: 'create-story',
      agent: 'bmd-custom-bmm-sm',
      shortcut: 'CS',
      description: '[CS] Create developer-ready story from epic',
      prompt: '*create-story',
    },
    {
      name: 'dev-story',
      agent: 'bmd-custom-bmm-dev',
      shortcut: 'DS',
      description: '[DS] Implement the current story',
      prompt: '*dev-story',
    },
    {
      name: 'code-review',
      agent: 'bmd-custom-bmm-dev',
      shortcut: 'CR',
      description: '[CR] Perform code review on implementation',
      prompt: '*code-review',
    },
    {
      name: 'retrospective',
      agent: 'bmd-custom-bmm-sm',
      shortcut: 'ER',
      description: '[ER] Run epic retrospective after completion',
      prompt: '*epic-retrospective',
    },
    {
      name: 'correct-course',
      agent: 'bmd-custom-bmm-sm',
      shortcut: 'CC',
      description: '[CC] Course correction when things go off track',
      prompt: '*correct-course',
    },
  ],
  // BMad Game Development Module (bmgd)
  bmgd: [
    // Implementation cycle
    {
      name: 'game-implement',
      agent: 'bmd-custom-bmgd-game-dev',
      shortcut: 'GI',
      description: '[GI] Implement game feature',
      prompt: '*game-implement',
    },
    {
      name: 'game-qa',
      agent: 'bmd-custom-bmgd-game-qa',
      shortcut: 'GQ',
      description: '[GQ] Test and QA game feature',
      prompt: '*game-qa',
    },
    // Planning & Design
    {
      name: 'game-design',
      agent: 'bmd-custom-bmgd-game-designer',
      shortcut: 'GD',
      description: '[GD] Design game mechanics and systems',
      prompt: '*game-design',
    },
    {
      name: 'game-architecture',
      agent: 'bmd-custom-bmgd-game-architect',
      shortcut: 'GA',
      description: '[GA] Create game technical architecture',
      prompt: '*game-architecture',
    },
    {
      name: 'game-sprint',
      agent: 'bmd-custom-bmgd-game-scrum-master',
      shortcut: 'GS',
      description: '[GS] Plan game development sprint',
      prompt: '*game-sprint',
    },
  ],
  // Core agents (always available)
  core: [
    {
      name: 'list-tasks',
      agent: 'bmd-custom-core-bmad-master',
      shortcut: 'LT',
      description: '[LT] List available tasks',
      prompt: '*list-tasks',
    },
    {
      name: 'list-workflows',
      agent: 'bmd-custom-core-bmad-master',
      shortcut: 'LW',
      description: '[LW] List available workflows',
      prompt: '*list-workflows',
    },
  ],
 };
 module.exports = { workflowPromptsConfig };
Author	SHA1	Message	Date
Sjoerd Bozon	051bc2f353	Merge `015c74c46f` into `d419ac8a70`	2026-01-12 17:27:24 +01:00
Alex Verkhovsky	d419ac8a70	feat: add editorial review tasks for structure and prose (#1307 ) * feat: add editorial review tasks for structure and prose Add two complementary editorial review tasks: - editorial-review-structure.xml: Structural editor that proposes cuts, reorganization, and simplification. Includes 5 document archetype models (Tutorial, Reference, Explanation, Prompt, Strategic) for targeted evaluation. - editorial-review-prose.xml: Clinical copy-editor for prose improvements using Microsoft Writing Style Guide as baseline. Both tasks support humans and llm target audiences with different principles. * fix: add content-sacrosanct guardrail to editorial review tasks Both editorial review tasks (prose and structure) were missing the key constraint that reviewers should never challenge the ideas/knowledge themselves—only how clearly they are communicated. This restores the original design intent. Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> * fix: align reader_type parameter naming across editorial tasks Prose task was using 'target_audience' for the humans/llm optimization flag while structure task correctly separates 'target_audience' (who reads) from 'reader_type' (optimization mode). Aligns to reader_type. Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com> Co-authored-by: Brian <bmadcode@gmail.com>	2026-01-13 00:20:04 +08:00
Sjoerd Bozon	015c74c46f	Merge branch 'bmad-code-org:main' into feat/workflow-prompt-recommendations	2026-01-05 10:24:53 +01:00
Sjoerd Bozon	9317ef5a62	fix: address Copilot review feedback on PR #1205 - Move step 6 before WORKFLOW COMPLETE marker (fixes workflow structure) - Change PRD shortcut from PR to PD (avoids conflict with parallel-research) - Clarify instructions for reading/updating VS Code settings - Update phase 4 comment to match actual handoff flow	2025-12-29 00:16:38 +01:00
Sjoerd Bozon	d662aee4b2	feat: add VS Code workflow prompt recommendations Add chat.promptFilesRecommendations support for GitHub Copilot to show workflow shortcuts as new chat starters. - Add workflow-prompts-config.js with all BMM, BMGD, and core prompts - Add workflow-prompt-generator.js to create .github/prompts/*.prompt.md - Update github-copilot.js to generate prompts and configure VS Code - Add phase-based prompt toggling to implementation-readiness workflow - Add phase-based prompt toggling to sprint-planning workflow When implementation-readiness passes or sprint-planning completes, the workflows update VS Code settings to prioritize the 'keep going' cycle (create-story → dev-story → code-review) over setup phase prompts.	2025-12-28 23:44:40 +01:00