ma-agents 3.5.0 → 3.5.1

package/lib/bmad-extension/skills/sqa-requirements-quality/SKILL.md

@@ -0,0 +1,244 @@
+---
+name: sqa-requirements-quality
+description: Requirements Quality Audit workflow — evaluates requirements in selected project documents against 14 quality criteria, producing a per-requirement audit table, missing-elements section, and overall quality score
+type: skill
+triggers:
+  - "requirements quality"
+  - "audit requirements"
+  - "req quality"
+  - "requirements audit"
+---
+
+# Requirements Quality Audit Workflow
+
+## Purpose
+
+Evaluate requirements in selected project documents against **14 established quality criteria** (Clarity, Single Verb, Sentence Structure, Glossary Presence, Necessity, Implementation-Independence, Unambiguity, Completeness, Feasibility, Testability, Stakeholder Alignment, Convention Conformance, Understandability, Precision). Produce a structured per-requirement audit report and offer corrective-action support for failing requirements.
+
+---
+
+## Quality Criteria Reference
+
+| # | Criterion | Definition |
+|---|-----------|------------|
+| 1 | **Clarity & Directness** | No source-form verbs (e.g., "to save", "to keep"). States the required behavior, not a capability. |
+| 2 | **Single Primary Verb** | Each requirement contains exactly one main action verb; any conditions are separated by commas or placed on a new line. |
+| 3 | **Sentence Structure** | Follows the pattern: `Condition + Subject + Predicate + Object [+ Constraint]`. |
+| 4 | **Glossary Presence** | All domain-specific terms used in the requirement are defined in a dedicated glossary. |
+| 5 | **Necessity** | The requirement appears only once in the document and does not duplicate another. If conceptually identical to another, identify which requirement it duplicates. |
+| 6 | **Implementation-Independent** | Describes the need, not a specific solution or technology. |
+| 7 | **Unambiguous** | Has only one possible interpretation for all relevant stakeholders. |
+| 8 | **Completeness** | Self-contained; does not rely on other requirements for its meaning. |
+| 9 | **Feasibility** | Realistic and achievable within reasonable cost, schedule, and technology limits. |
+| 10 | **Testability** | Can be verified by a concrete test or inspection. |
+| 11 | **Stakeholder Alignment** | Accurately reflects the expressed needs of the identified stakeholders. |
+| 12 | **Conformance to Conventions** | Uses the project's standard format (e.g., Epic → User Stories → Acceptance Criteria) and consistent look-and-feel. |
+| 13 | **Understandability** | Written in plain language that the supplier can readily comprehend. |
+| 14 | **Precision** | Uses definite nouns, explicit units, and avoids vague qualifiers (e.g., "approximately", "usually", "high"). |
+
+---
+
+## Step 1 — Scope Selection
+
+Ask the user:
+
+> "Welcome to the Requirements Quality Audit. Which documents should I audit?
+>
+> **Available sources:**
+> 1. **PRD — Functional Requirements (FR)**: All FR-prefixed requirements in `prd.md`
+> 2. **PRD — Non-Functional Requirements (NFR)**: All NFR-prefixed requirements in `prd.md`
+> 3. **Epics & User Stories**: Epic goals and story acceptance criteria in `epics.md`
+> 4. **All of the above**
+>
+> Type **'all'** or list the numbers you want (e.g., '1,2')."
+
+Wait for user selection. Store as {rq_scope}.
+
+---
+
+## Step 2 — Data Collection
+
+Load the selected documents. Note presence or absence — missing documents result in that scope item being SKIPPED.
+
+| Source | Path |
+|--------|------|
+| PRD | `{output_folder}/planning-artifacts/prd.md` |
+| Epics & Stories | `{output_folder}/planning-artifacts/epics.md` |
+
+Inform the user which documents were found and which were missing before proceeding.
+
+---
+
+## Step 3 — Extract Requirements
+
+**Scope guard:** Only extract from documents selected in {rq_scope}.
+
+For each selected source, identify and list all requirements to be evaluated:
+
+- **PRD FRs**: All items prefixed `FR` in the Functional Requirements section
+- **PRD NFRs**: All items prefixed `NFR` in the Non-Functional Requirements section
+- **Epics**: Epic goal statements (the "Goal:" or intent sentence of each epic)
+- **User Stories**: The "As a / I want / so that" statement plus all Acceptance Criteria items
+
+If the total requirement count exceeds 30, ask the user:
+> "I found {N} requirements. Would you like me to audit all of them, or focus on a specific section? (Type 'all' or describe which section to prioritize)"
+
+---
+
+## Step 4 — Evaluate Requirements
+
+For each requirement, evaluate all 14 criteria. Produce a table per requirement:
+
+| Requirement ID | Requirement Summary | Type | Criterion | Pass/Fail | Comments / Suggested Revision |
+|----------------|-------------------|------|-----------|-----------|-------------------------------|
+| [ID] | [one-line summary] | [type] | 1 — Clarity & Directness | ✅ / ❌ | [comment or suggested revision if failed] |
+| | | | 2 — Single Primary Verb | ✅ / ❌ | |
+| | | | 3 — Sentence Structure | ✅ / ❌ | |
+| | | | 4 — Glossary Presence | ✅ / ❌ | |
+| | | | 5 — Necessity | ✅ / ❌ | |
+| | | | 6 — Implementation-Independent | ✅ / ❌ | |
+| | | | 7 — Unambiguous | ✅ / ❌ | |
+| | | | 8 — Completeness | ✅ / ❌ | |
+| | | | 9 — Feasibility | ✅ / ❌ | |
+| | | | 10 — Testability | ✅ / ❌ | |
+| | | | 11 — Stakeholder Alignment | ✅ / ❌ | |
+| | | | 12 — Convention Conformance | ✅ / ❌ | |
+| | | | 13 — Understandability | ✅ / ❌ | |
+| | | | 14 — Precision | ✅ / ❌ | |
+
+**Requirement Type codes:** `FR` `NFR` `US` (User Story) `AC` (Acceptance Criterion) `EPIC`
+
+**Rules:**
+- For every ❌, provide a specific, actionable suggested revision in the Comments column
+- For Criterion 5 (Necessity), if a duplicate is found, name the duplicating requirement by ID
+- A requirement FAILS overall if it fails 3 or more criteria (mark the ID row with ⚠️)
+- A requirement CRITICALLY FAILS if it fails criteria 7 (Unambiguous), 10 (Testability), or 14 (Precision) (mark the ID row with ❌)
+
+---
+
+## Step 5 — Missing Elements
+
+After all requirement tables, produce a **Missing Elements** section:
+
+```
+### Missing Elements
+
+- Glossary: [domain-specific terms used across requirements that lack a definition]
+- Acceptance Criteria: [User Stories with no AC]
+- Traceability: [requirements not linked to a parent epic, stakeholder need, or PRD section]
+- Testability gaps: [requirements where no concrete verification method is apparent]
+- Other: [any absent artifacts or structural issues]
+```
+
+If nothing is missing, state: *No missing elements identified.*
+
+---
+
+## Step 6 — Overall Quality Score
+
+```
+### Overall Quality Score
+
+{X} / {Y} criteria passed across {Z} requirements ({P}%)
+
+**By severity:**
+- Critical failures (failing criterion 7, 10, or 14): {N} requirements
+- Overall failures (≥3 criteria failing): {N} requirements
+- Minor issues (1-2 criteria failing): {N} requirements
+- Fully passing: {N} requirements
+```
+
+---
+
+## Step 7 — Compile and Save Report
+
+Compile the full report in this structure:
+
+```
+# Requirements Quality Audit Report
+**Date:** {today's date}
+**Auditor:** Gad (SQA Agent)
+**Scope:** {selected document sources}
+**Requirements Audited:** {total count}
+**Overall Quality Score:** {X}/{Y} ({P}%)
+
+---
+
+## Executive Summary
+{3-4 sentences: overall quality posture, most common failure patterns, primary recommendations}
+
+---
+
+## Per-Requirement Audit
+
+{requirement tables from Step 4}
+
+---
+
+## Missing Elements
+
+{section from Step 5}
+
+---
+
+## Overall Quality Score
+
+{section from Step 6}
+
+---
+
+## Top Recommendations
+
+{Ordered list of the most impactful improvements — focus on patterns, not individual requirements}
+
+| Priority | Pattern | Affected Requirements | Recommended Fix |
+|----------|---------|-----------------------|-----------------|
+| P1       | ...     | FR12, FR18, FR24      | ...             |
+```
+
+Save the report to:
+`{output_folder}/sqa-requirements-quality-report-{YYYY-MM-DD}.md`
+
+Inform the user of the saved path.
+
+---
+
+## Step 8 — Corrective Action Offers
+
+Ask:
+> "Would you like me to generate a remediation plan with suggested revisions for all failing requirements?"
+
+If yes, save a remediation plan to:
+`{output_folder}/sqa-remediation-plan-requirements-{YYYY-MM-DD}.md`
+
+### Remediation Plan Format
+
+```
+# Requirements Quality Remediation Plan
+**Date:** {today's date}
+**Auditor:** Gad (SQA Agent)
+**Source Report:** sqa-requirements-quality-report-{YYYY-MM-DD}.md
+
+---
+
+## Summary
+{count of critical failures, overall failures, minor issues}
+
+---
+
+## Corrective Actions
+
+| Priority | Req ID | Type | Failed Criteria | Issue | Suggested Revision | Effort |
+|----------|--------|------|----------------|-------|-------------------|--------|
+| P1       | FR12   | FR   | 7, 10          | ...   | ...               | Low    |
+
+---
+
+## Pattern-Level Fixes
+{If multiple requirements share the same failure pattern, describe a single structural fix that would resolve the pattern across all affected requirements}
+```
+
+Then, for each critically failing requirement (criterion 7, 10, or 14 failing), offer one at a time:
+> "Would you like me to create a backlog story to rewrite requirement [ID]? (yes/skip)"
+
+If yes, invoke `create-bug-story` for that item.

package/lib/bmad-extension/skills/sqa-requirements-quality/bmad-skill-manifest.yaml

@@ -0,0 +1,3 @@
+type: skill
+name: sqa-requirements-quality
+module: ma-skills

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "ma-agents",
-  "version": "3.5.0",
+  "version": "3.5.1",
   "description": "NPX tool to install skills for AI coding agents (Claude Code, Gemini, Copilot, Kilocode, Cline, Cursor, Roo Code)",
   "main": "index.js",
   "bin": {

package/test/extension-module-restructure.test.js

@@ -140,6 +140,13 @@ const expectedAgentSkills = [
   'bmad-ma-agent-cyber',
   'bmad-ma-agent-mil498',
   'bmad-ma-agent-ml',
+  'bmad-ma-agent-sqa',
+];
+
+const expectedSqaSkills = [
+  'sqa-audit',
+  'sqa-ieee12207',
+  'sqa-requirements-quality',
 ];
 
 const expectedMil498Skills = [
@@ -185,16 +192,17 @@ const allExpectedSkills = [
   ...expectedCyberSkills,
   ...expectedExtensionSkills,
   ...expectedMlSkills,
+  ...expectedSqaSkills,
 ];
 
-test('skills/ has exactly 58 subdirectories', () => {
+test('skills/ has exactly 62 subdirectories', () => {
   const entries = fs.readdirSync(skillsDir).filter(e =>
     fs.statSync(path.join(skillsDir, e)).isDirectory()
   );
-  assert.strictEqual(entries.length, 58, `Expected 58 skill dirs, found ${entries.length}`);
+  assert.strictEqual(entries.length, 62, `Expected 62 skill dirs, found ${entries.length}`);
 });
 
-test('all 5 agent skill directories exist', () => {
+test('all 6 agent skill directories exist', () => {
   for (const skill of expectedAgentSkills) {
     const p = path.join(skillsDir, skill);
     assert.ok(fs.existsSync(p), `Missing agent skill dir: ${skill}`);
@@ -243,6 +251,13 @@ test('all 14 extension workflow skill directories exist', () => {
   }
 });
 
+test('all 3 SQA skill directories exist', () => {
+  for (const skill of expectedSqaSkills) {
+    const p = path.join(skillsDir, skill);
+    assert.ok(fs.existsSync(p), `Missing SQA skill dir: ${skill}`);
+  }
+});
+
 test('every skill directory contains a .gitkeep file', () => {
   for (const skill of allExpectedSkills) {
     const gk = path.join(skillsDir, skill, '.gitkeep');
@@ -276,8 +291,8 @@ test('module-help.csv has correct header columns', () => {
   }
 });
 
-test('module-help.csv has 58 skill entries (excluding header)', () => {
-  assert.strictEqual(csvData.rows.length, 58, `Expected 58 rows, found ${csvData.rows.length}`);
+test('module-help.csv has 62 skill entries (excluding header)', () => {
+  assert.strictEqual(csvData.rows.length, 62, `Expected 62 rows, found ${csvData.rows.length}`);
 });
 
 test('all CSV entries use module code ma-skills', () => {
@@ -287,7 +302,7 @@ test('all CSV entries use module code ma-skills', () => {
   }
 });
 
-test('CSV has entries for all 5 agent skills', () => {
+test('CSV has entries for all 6 agent skills', () => {
   const codeIdx = csvData.headers.indexOf('code');
   const codes = csvData.rows.map(r => r[codeIdx]);
   for (const skill of expectedAgentSkills) {
@@ -295,6 +310,14 @@ test('CSV has entries for all 5 agent skills', () => {
   }
 });
 
+test('CSV has entries for all 3 SQA skills', () => {
+  const codeIdx = csvData.headers.indexOf('code');
+  const codes = csvData.rows.map(r => r[codeIdx]);
+  for (const skill of expectedSqaSkills) {
+    assert.ok(codes.includes(skill), `Missing CSV entry for SQA skill: ${skill}`);
+  }
+});
+
 test('CSV has entries for all 8 MIL-498 skills', () => {
   const codeIdx = csvData.headers.indexOf('code');
   const codes = csvData.rows.map(r => r[codeIdx]);

package/test/migration-validation.test.js

@@ -348,11 +348,11 @@ test('5.2: module.yaml has extends-module: bmm', () => {
   assert.ok(content.includes('extends-module: bmm'), 'module.yaml must declare extends-module: bmm');
 });
 
-test('5.3: skills/ contains exactly 58 skill folders', () => {
+test('5.3: skills/ contains exactly 62 skill folders', () => {
   const folders = fs.readdirSync(SKILLS_DIR).filter(f =>
     fs.statSync(path.join(SKILLS_DIR, f)).isDirectory());
-  assert.strictEqual(folders.length, 58,
-    `Expected 58 skill folders, found ${folders.length}: ${folders.join(', ')}`);
+  assert.strictEqual(folders.length, 62,
+    `Expected 62 skill folders, found ${folders.length}: ${folders.join(', ')}`);
 });
 
 test('5.4: every skill folder has SKILL.md', () => {
@@ -373,12 +373,12 @@ test('5.5: every skill folder has bmad-skill-manifest.yaml', () => {
   }
 });
 
-test('5.6: module-help.csv exists and lists all 58 skills', () => {
+test('5.6: module-help.csv exists and lists all 62 skills', () => {
   const csv = fs.readFileSync(path.join(EXT_DIR, 'module-help.csv'), 'utf-8');
   const lines = csv.split('\n').filter(l => l.trim() && !l.startsWith('module,'));
-  // Should have a line for each of the 58 skills (header excluded)
-  assert.strictEqual(lines.length, 58,
-    `Expected 58 data rows in module-help.csv, found ${lines.length}`);
+  // Should have a line for each of the 62 skills (header excluded)
+  assert.strictEqual(lines.length, 62,
+    `Expected 62 data rows in module-help.csv, found ${lines.length}`);
 });
 
 test('5.7: module-help.csv references module code ma-skills', () => {
@@ -390,7 +390,7 @@ test('5.7: module-help.csv references module code ma-skills', () => {
   }
 });
 
-test('5.8: skill folder breakdown: 5 agents + 8 mil498 + 7 sre + 5 devops + 7 cyber + 12 ml + 14 extension', () => {
+test('5.8: skill folder breakdown: 6 agents + 8 mil498 + 7 sre + 5 devops + 7 cyber + 12 ml + 17 extension (14 workflow + 3 sqa)', () => {
   const folders = fs.readdirSync(SKILLS_DIR).filter(f =>
     fs.statSync(path.join(SKILLS_DIR, f)).isDirectory());
 
@@ -405,13 +405,13 @@ test('5.8: skill folder breakdown: 5 agents + 8 mil498 + 7 sre + 5 devops + 7 cy
     !f.startsWith('sre-') && !f.startsWith('devops-') && !f.startsWith('cyber-') &&
     !f.startsWith('ml-'));
 
-  assert.strictEqual(agents.length, 5, `Expected 5 agent folders, found ${agents.length}`);
+  assert.strictEqual(agents.length, 6, `Expected 6 agent folders, found ${agents.length}`);
   assert.strictEqual(mil498.length, 8, `Expected 8 mil498 folders, found ${mil498.length}`);
   assert.strictEqual(sre.length, 7, `Expected 7 sre folders, found ${sre.length}`);
   assert.strictEqual(devops.length, 5, `Expected 5 devops folders, found ${devops.length}`);
   assert.strictEqual(cyber.length, 7, `Expected 7 cyber folders, found ${cyber.length}`);
   assert.strictEqual(ml.length, 12, `Expected 12 ml folders, found ${ml.length}`);
-  assert.strictEqual(ext.length, 14, `Expected 14 extension folders, found ${ext.length}`);
+  assert.strictEqual(ext.length, 17, `Expected 17 extension folders, found ${ext.length}`);
 });
 
 // ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

package/lib/bmad-cache/bmb/skills/bmad-builder-setup/assets/module-help.csv

@@ -1,6 +0,0 @@
-module,skill,display-name,menu-code,description,action,args,phase,after,before,required,output-location,outputs
-BMad Builder,bmad-builder-setup,Setup Builder Module,SB,"Install or update BMad Builder module config and help entries. Collects user preferences, writes config.yaml, and migrates legacy configs.",configure,,anytime,,,false,{project-root}/_bmad,config.yaml and config.user.yaml
-BMad Builder,bmad-agent-builder,Build an Agent,BA,"Create, edit, convert, or fix an agent skill.",build-process,"[-H] [description | path]",anytime,,bmad-agent-builder:quality-optimizer,false,output_folder,agent skill
-BMad Builder,bmad-agent-builder,Optimize an Agent,OA,Validate and optimize an existing agent skill. Produces a quality report.,quality-optimizer,[-H] [path],anytime,bmad-agent-builder:build-process,,false,bmad_builder_reports,quality report
-BMad Builder,bmad-workflow-builder,Build a Workflow,BW,"Create, edit, convert, or fix a workflow or utility skill.",build-process,"[-H] [description | path]",anytime,,bmad-workflow-builder:quality-optimizer,false,output_folder,workflow skill
-BMad Builder,bmad-workflow-builder,Optimize a Workflow,OW,Validate and optimize an existing workflow or utility skill. Produces a quality report.,quality-optimizer,[-H] [path],anytime,bmad-workflow-builder:build-process,,false,bmad_builder_reports,quality report