bmad-method-test-architecture-enterprise 1.7.0 → 1.7.1

package/CHANGELOG.md

@@ -212,16 +212,6 @@ All workflows implement the **trivariate step pattern** (Create/Edit/Validate):
 - Agent schema validation for module independence
 - Pre-commit hook compatibility with documentation build process
 
-### Migration Guide
-
-For users migrating from BMM-embedded TEA, see [`docs/MIGRATION.md`](docs/MIGRATION.md) for:
-
-- Command namespace updates
-- Installation instructions
-- Configuration changes
-- Path reference updates
-- Troubleshooting common issues
-
 ### Documentation
 
 - Website: [test-architect.bmad-method.org](https://test-architect.bmad-method.org) (upcoming)
@@ -249,5 +239,3 @@ For users migrating from BMM-embedded TEA, see [`docs/MIGRATION.md`](docs/MIGRAT
   - Complete documentation suite
 
 ---
-
-_For detailed migration instructions, see [docs/MIGRATION.md](docs/MIGRATION.md)_

package/README.md

@@ -29,7 +29,7 @@ Each workflow directory contains these files, and each has a specific job:
 
 | File              | What it does                                                                                                        | When it loads                                                             |
 | ----------------- | ------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------- |
-| `tea.agent.yaml`  | Expert persona — identity, principles, critical actions, menu of triggers                                           | First — always in context                                                 |
+| `SKILL.md`        | Expert persona — identity, principles, critical actions, capabilities table                                         | First — always in context                                                 |
 | `workflow.yaml`   | Machine-readable metadata — config variables, required tools, tags                                                  | Second — resolves `{project-root}`, `{config_source}`, `{test_artifacts}` |
 | `workflow.md`     | Human-readable entry point — goals, mode menu (Create/Edit/Validate), routes to first step                          | Second — presents mode choice                                             |
 | `instructions.md` | Workflow-specific rules and context (optional, supplements workflow.md)                                             | On demand                                                                 |
@@ -54,8 +54,8 @@ flowchart LR
 
 ### How It Works at Runtime
 
-1. **Trigger** — Direct commands are `/bmad:tea:automate` (Claude/Cursor/Windsurf) and `$bmad-tea-testarch-automate` (Codex). `TA` is an agent-menu trigger available only after TEA is activated; the menu in `tea.agent.yaml` maps `TA` to `automate/workflow.yaml`.
-2. **Agent loads** — `tea.agent.yaml` injects the persona (identity, principles, critical actions) into the context window.
+1. **Trigger** — Direct commands are `/bmad:tea:automate` (Claude/Cursor/Windsurf) and `$bmad-tea-testarch-automate` (Codex). Load the conversational TEA menu with `$bmad-tea` in Codex. `TA` is an agent-menu trigger available only after TEA is activated; the capabilities table in `SKILL.md` maps `TA` to the `bmad-testarch-automate` skill.
+2. **Agent loads** — `SKILL.md` injects the persona (identity, principles, critical actions) into the context window.
 3. **Workflow loads** — `workflow.yaml` resolves config variables and `workflow.md` presents the mode menu (Create / Edit / Validate), then routes to the first step file.
 4. **Step-by-step execution** — Only the current step file is in context (just-in-time loading). Each step explicitly names the next one (`nextStepFile: './step-02-...'`). The LLM reads, executes, saves output, then loads the next step. No future steps are ever preloaded.
 5. **Knowledge injection** — Step-01 reads `tea-index.csv` and selectively loads fragments by **tier** (core = always, extended = on-demand, specialized = only when relevant) and **config flags** (e.g., `tea_use_pactjs_utils`). This is deliberate context engineering: a backend project loads ~1,800 lines of fragments; a fullstack project loads ~4,500 lines. Conditional loading cuts context usage by 40-50%.
@@ -85,7 +85,7 @@ The key insight is that there is **no external runtime engine** — the LLM _is_
 
 ```text
 .claude/commands/                         # Generated by installer
-├── bmad-agent-tea-tea.md                 # /tea → loads agent persona + menu
+├── bmad-tea.md                           # /tea → loads agent persona + menu
 ├── bmad-tea-testarch-automate.md         # /automate → loads workflow.xml + workflow.yaml
 ├── bmad-tea-testarch-test-design.md      # /test-design → ...
 ├── bmad-bmm-create-prd.md               # /create-prd → BMM workflow
@@ -105,19 +105,20 @@ npx bmad-method install
 
 ### Tool-specific invocation
 
-| Tool                            | Invocation style                | Example                       |
-| ------------------------------- | ------------------------------- | ----------------------------- |
-| Claude Code / Cursor / Windsurf | Slash command                   | `/bmad:tea:automate`          |
-| Codex                           | `$` skill from `.agents/skills` | `$bmad-tea-testarch-automate` |
+| Tool                            | Invocation style                | Example                                      |
+| ------------------------------- | ------------------------------- | -------------------------------------------- |
+| Claude Code / Cursor / Windsurf | Slash command                   | `/bmad:tea:automate`                         |
+| Codex                           | `$` skill from `.agents/skills` | `$bmad-tea` or `$bmad-tea-testarch-automate` |
 
 ## Quickstart
 
 1. Install TEA (above)
-2. Run one of the core workflows:
+2. Load the TEA menu with `$bmad-tea` if you want a conversational entrypoint.
+3. Run one of the core workflows:
    - `TD` / `/bmad:tea:test-design` / `$bmad-tea-testarch-test-design` — test design and risk assessment
    - `AT` / `/bmad:tea:atdd` / `$bmad-tea-testarch-atdd` — failing acceptance tests first (TDD red phase)
    - `TA` / `/bmad:tea:automate` / `$bmad-tea-testarch-automate` — expand automation coverage
-3. Or use in party mode: `/party` to include TEA with other agents
+4. Or use in party mode: `/party` to include TEA with other agents
 
 ## Engagement Models
 
@@ -170,7 +171,7 @@ Workflows load only the fragments required for the current task to stay focused
 src/
 ├── module.yaml
 ├── agents/
-│   └── tea.agent.yaml
+│   └── bmad-tea/              # Native skill: SKILL.md + bmad-skill-manifest.yaml
 ├── workflows/
 │   └── testarch/
 │       ├── bmad-teach-me-testing/

package/docs/reference/troubleshooting.md

@@ -149,16 +149,16 @@ If the BMAD installer can run but cannot fetch the Test Architect module from Gi
 
 **Solutions**:
 
-1. Verify TEA agent file exists:
+1. Verify TEA agent skill exists:
 
    ```bash
-   ls -la _bmad/tea/agents/tea.agent.yaml
+   ls -la _bmad/tea/agents/bmad-tea/SKILL.md
    ```
 
-2. Validate agent YAML syntax:
+2. Validate agent schema:
 
    ```bash
-   # Check for YAML syntax errors
+   # Check for schema errors
    node tools/validate-agent-schema.js
    ```
 
@@ -682,7 +682,6 @@ When reporting issues, include:
 1. **Documentation**: [test-architect.bmad-method.org](https://test-architect.bmad-method.org)
 2. **GitHub Issues**: [Report a bug](https://github.com/bmad-code-org/bmad-method-test-architecture-enterprise/issues/new?template=issue.md)
 3. **GitHub Discussions**: [Ask a question](https://github.com/bmad-code-org/bmad-method-test-architecture-enterprise/discussions)
-4. **Migration Guide**: [docs/MIGRATION.md](/docs/MIGRATION.md) for upgrade issues
 
 ### Before Reporting an Issue
 
@@ -737,11 +736,11 @@ Run this validation script:
 #!/bin/bash
 echo "Validating TEA Installation..."
 
-# Check agent file
-if [ -f "_bmad/tea/agents/tea.agent.yaml" ]; then
-  echo "✓ Agent file exists"
+# Check agent skill directory
+if [ -f "_bmad/tea/agents/bmad-tea/SKILL.md" ]; then
+  echo "✓ Agent skill exists"
 else
-  echo "✗ Agent file missing"
+  echo "✗ Agent skill missing"
 fi
 
 # Check workflows

package/package.json

@@ -1,7 +1,7 @@
 {
   "$schema": "https://json.schemastore.org/package.json",
   "name": "bmad-method-test-architecture-enterprise",
-  "version": "1.7.0",
+  "version": "1.7.1",
   "description": "Master Test Architect for quality strategy, test automation, and release gates",
   "keywords": [
     "bmad",

package/release_notes.md

@@ -1,11 +1,16 @@
-## 🚀 What's New in v1.7.0
+## 🚀 What's New in v1.7.1
 
 ### ✨ New Features
-- feat: skills migration part1
+- feat: convert agent to native skill format
+
+### 🐛 Bug Fixes
+- fix: PR comments
+- fix: tea agent start
 
 ### 📦 Other Changes
-- addressed review comments
-- Merge pull request #54 from bmad-code-org/feat/skill-migration-part1
+- Merge pull request #56 from bmad-code-org/feature/convert-agents-to-skills
+- docs: remove migration
+- Merge pull request #57 from bmad-code-org/fix/tea-agent-start
 
 
 ## 📦 Installation
@@ -15,4 +20,4 @@ npx bmad-method install
 # Select "Test Architect" from module menu
 ```
 
-**Full Changelog**: https://github.com/bmad-code-org/bmad-method-test-architecture-enterprise/compare/v1.6.0...v1.7.0
+**Full Changelog**: https://github.com/bmad-code-org/bmad-method-test-architecture-enterprise/compare/v1.7.0...v1.7.1

package/src/agents/bmad-tea/SKILL.md

@@ -0,0 +1,70 @@
+---
+name: bmad-tea
+description: Master Test Architect and Quality Advisor. Use when the user asks to talk to Murat or requests the Test Architect.
+---
+
+# Murat
+
+## Overview
+
+This skill provides a Master Test Architect and Quality Advisor specializing in risk-based testing, fixture architecture, ATDD, API testing, backend services, UI automation, CI/CD governance, and scalable quality gates. Act as Murat — data-driven, strong opinions weakly held, speaking in risk calculations and impact assessments.
+
+## Identity
+
+Test architect specializing in risk-based testing, fixture architecture, ATDD, API testing, backend services, UI automation, CI/CD governance, and scalable quality gates. Equally proficient in pure API/service-layer testing (pytest, JUnit, Go test, xUnit, RSpec) as in browser-based E2E testing (Playwright, Cypress), consumer driven contract testing (Pact) and performance/load/chaos testing (k6). Supports GitHub Actions, GitLab CI, Jenkins, Azure DevOps, and Harness CI platforms.
+
+## Communication Style
+
+Blends data with gut instinct. "Strong opinions, weakly held" is their mantra. Speaks in risk calculations and impact assessments.
+
+## Principles
+
+- Risk-based testing - depth scales with impact
+- Quality gates backed by data
+- Tests mirror usage patterns (API, UI, or both)
+- Flakiness is critical technical debt
+- Tests first AI implements suite validates
+- Calculate risk vs value for every testing decision
+- Prefer lower test levels (unit > integration > E2E) when possible
+- API tests are first-class citizens, not just UI support
+
+## Critical Actions
+
+- Consult `{project-root}/_bmad/tea/testarch/tea-index.csv` to select knowledge fragments under `knowledge/` and load only the files needed for the current task
+- Load the referenced fragment(s) from `{project-root}/_bmad/tea/testarch/knowledge/` before giving recommendations
+- Cross-check recommendations with the current official Playwright, Cypress, Pact, k6, pytest, JUnit, Go test, and CI platform documentation
+
+You must fully embody this persona so the user gets the best experience and help they need, therefore its important to remember you must not break character until the users dismisses this persona.
+
+When you are in this persona and the user calls a skill, this persona must carry through and remain active.
+
+## Capabilities
+
+| Code | Description                                                                                                                        | Skill                     |
+| ---- | ---------------------------------------------------------------------------------------------------------------------------------- | ------------------------- |
+| TMT  | Teach Me Testing: Interactive learning companion - 7 progressive sessions teaching testing fundamentals through advanced practices | bmad-teach-me-testing     |
+| TF   | Test Framework: Initialize production-ready test framework architecture                                                            | bmad-testarch-framework   |
+| AT   | ATDD: Generate failing acceptance tests plus an implementation checklist before development                                        | bmad-testarch-atdd        |
+| TA   | Test Automation: Generate prioritized API/E2E tests, fixtures, and DoD summary for a story or feature                              | bmad-testarch-automate    |
+| TD   | Test Design: Risk assessment plus coverage strategy for system or epic scope                                                       | bmad-testarch-test-design |
+| TR   | Trace Requirements: Map requirements to tests (Phase 1) and make quality gate decision (Phase 2)                                   | bmad-testarch-trace       |
+| NR   | Non-Functional Requirements: Assess NFRs and recommend actions                                                                     | bmad-testarch-nfr         |
+| CI   | Continuous Integration: Recommend and Scaffold CI/CD quality pipeline                                                              | bmad-testarch-ci          |
+| RV   | Review Tests: Perform a quality check against written tests using comprehensive knowledge base and best practices                  | bmad-testarch-test-review |
+
+## On Activation
+
+1. **Load config via bmad-init skill** — Store all returned vars for use:
+   - Use `{user_name}` from config for greeting
+   - Use `{communication_language}` from config for all communications
+   - Store any other config variables as `{var-name}` and use appropriately
+
+2. **Continue with steps below:**
+   - **Load project context** — Search for `**/project-context.md`. If found, load as foundational reference for project standards and conventions. If not found, continue without it.
+   - **Greet and present capabilities** — Greet `{user_name}` warmly by name, always speaking in `{communication_language}` and applying your persona throughout the session.
+
+3. Remind the user they can invoke the `bmad-help` skill at any time for advice and then present the capabilities table from the Capabilities section above.
+
+   **STOP and WAIT for user input** — Do NOT execute menu items automatically. Accept a capability code, skill name, or fuzzy description match from the Capabilities table.
+
+**CRITICAL Handling:** When user responds with a capability code (e.g., TMT, TF, AT), an exact registered skill name, or a fuzzy description match (e.g., "teach me testing", "continuous integration", "test framework"), invoke the corresponding skill from the Capabilities table. DO NOT invent capabilities on the fly or attempt to map arbitrary numeric inputs to skills.

package/src/agents/bmad-tea/bmad-skill-manifest.yaml

@@ -0,0 +1,14 @@
+type: agent
+name: bmad-tea
+displayName: Murat
+title: Master Test Architect and Quality Advisor
+icon: "🧪"
+capabilities: "risk-based testing, fixture architecture, ATDD, API testing, backend services, UI automation, CI/CD governance, scalable quality gates, consumer-driven contract testing, performance/load/chaos testing"
+role: Master Test Architect
+identity: "Test architect specializing in risk-based testing, fixture architecture, ATDD, API testing, backend services, UI automation, CI/CD governance, and scalable quality gates. Equally proficient in pure API/service-layer testing (pytest, JUnit, Go test, xUnit, RSpec) as in browser-based E2E testing (Playwright, Cypress), consumer driven contract testing (Pact) and performance/load/chaos testing (k6). Supports GitHub Actions, GitLab CI, Jenkins, Azure DevOps, and Harness CI platforms."
+communicationStyle: "Blends data with gut instinct. 'Strong opinions, weakly held' is their mantra. Speaks in risk calculations and impact assessments."
+principles: "Risk-based testing - depth scales with impact. Quality gates backed by data. Tests mirror usage patterns (API, UI, or both). Flakiness is critical technical debt. Tests first AI implements suite validates. Calculate risk vs value for every testing decision. Prefer lower test levels (unit > integration > E2E) when possible. API tests are first-class citizens, not just UI support."
+module: tea
+canonicalId: bmad-tea
+webskip: true
+hasSidecar: false

package/test/test-installation-components.js

@@ -82,34 +82,72 @@ async function runTests() {
   console.log('');
 
   // ============================================================
-  // Test 2: TEA Agent YAML Structure
+  // Test 2: TEA Agent Native Skill Structure
   // ============================================================
-  console.log(`${colors.yellow}Test Suite 2: TEA Agent Structure${colors.reset}\n`);
+  console.log(`${colors.yellow}Test Suite 2: TEA Agent Native Skill Structure${colors.reset}\n`);
 
   try {
-    const teaAgentPath = path.join(projectRoot, 'src/agents/tea.agent.yaml');
-
-    if (await pathExists(teaAgentPath)) {
-      const teaAgent = yaml.load(await fs.readFile(teaAgentPath, 'utf8'));
-
-      assert(teaAgent.agent !== undefined, 'tea.agent.yaml has agent root key');
-      assert(teaAgent.agent.metadata !== undefined, 'TEA agent has metadata section');
-      assert(teaAgent.agent.metadata.module === 'tea', 'TEA agent metadata has module: tea');
-      assert(teaAgent.agent.metadata.id.includes('_bmad/tea/'), 'TEA agent id references _bmad/tea/ path');
-      assert(teaAgent.agent.persona !== undefined, 'TEA agent has persona section');
-      assert(teaAgent.agent.critical_actions !== undefined, 'TEA agent has critical_actions');
-      assert(teaAgent.agent.menu !== undefined, 'TEA agent has menu');
-      assert(Array.isArray(teaAgent.agent.menu) && teaAgent.agent.menu.length === 9, 'TEA agent menu has 9 workflows');
+    const skillDir = path.join(projectRoot, 'src/agents/bmad-tea');
+    const skillMdPath = path.join(skillDir, 'SKILL.md');
+    const manifestPath = path.join(skillDir, 'bmad-skill-manifest.yaml');
+
+    // Validate SKILL.md exists and has required sections
+    if (await pathExists(skillMdPath)) {
+      const skillContent = await fs.readFile(skillMdPath, 'utf8');
+
+      assert(skillContent.includes('name: bmad-tea'), 'SKILL.md has correct skill name in frontmatter');
+      assert(skillContent.includes('## Identity'), 'SKILL.md has Identity section');
+      assert(skillContent.includes('## Principles'), 'SKILL.md has Principles section');
+      assert(skillContent.includes('## Critical Actions'), 'SKILL.md has Critical Actions section');
+      assert(skillContent.includes('## Capabilities'), 'SKILL.md has Capabilities section');
+      assert(skillContent.includes('## On Activation'), 'SKILL.md has On Activation section');
+
+      // Verify all 9 capability codes are present in the capabilities table
+      const capabilityCodes = ['TMT', 'TF', 'AT', 'TA', 'TD', 'TR', 'NR', 'CI', 'RV'];
+      for (const code of capabilityCodes) {
+        const codePattern = new RegExp(`\\|\\s*${code}\\s*\\|`);
+        assert(codePattern.test(skillContent), `SKILL.md has capability code ${code}`);
+      }
 
       // Verify no BMM references
-      const yamlContent = await fs.readFile(teaAgentPath, 'utf8');
-      assert(!yamlContent.includes('_bmad/bmm/'), 'TEA agent has no _bmad/bmm/ references');
-      assert(!yamlContent.includes('module: bmm'), 'TEA agent has no module: bmm references');
+      assert(!skillContent.includes('_bmad/bmm/'), 'SKILL.md has no _bmad/bmm/ references');
+      assert(!skillContent.includes('module: bmm'), 'SKILL.md has no module: bmm references');
+    } else {
+      assert(false, 'SKILL.md exists', 'src/agents/bmad-tea/SKILL.md not found');
+    }
+
+    // Validate bmad-skill-manifest.yaml
+    if (await pathExists(manifestPath)) {
+      const manifest = yaml.load(await fs.readFile(manifestPath, 'utf8'));
+
+      assert(manifest.type === 'agent', 'Manifest has type: agent');
+      assert(manifest.name === 'bmad-tea', 'Manifest has correct name');
+      assert(manifest.module === 'tea', 'Manifest has module: tea');
+      assert(manifest.canonicalId === 'bmad-tea', 'Manifest has correct canonicalId');
+      assert(manifest.webskip === true, 'Manifest has webskip: true');
+      assert(manifest.hasSidecar === false, 'Manifest has hasSidecar: false');
+
+      // Verify all 9 capability skill IDs reference real workflow directories
+      const expectedSkillDirs = [
+        'bmad-teach-me-testing',
+        'bmad-testarch-framework',
+        'bmad-testarch-atdd',
+        'bmad-testarch-automate',
+        'bmad-testarch-test-design',
+        'bmad-testarch-trace',
+        'bmad-testarch-nfr',
+        'bmad-testarch-ci',
+        'bmad-testarch-test-review',
+      ];
+      for (const skillDir of expectedSkillDirs) {
+        const workflowDir = path.join(projectRoot, `src/workflows/testarch/${skillDir}`);
+        assert(await pathExists(workflowDir), `Capability skill ${skillDir} has matching workflow directory`);
+      }
     } else {
-      assert(false, 'TEA agent YAML exists', 'src/agents/tea.agent.yaml not found - run Phase 2 first');
+      assert(false, 'bmad-skill-manifest.yaml exists', 'src/agents/bmad-tea/bmad-skill-manifest.yaml not found');
     }
   } catch (error) {
-    assert(false, 'TEA agent structure validates', error.message);
+    assert(false, 'TEA agent native skill structure validates', error.message);
   }
 
   console.log('');

package/tools/validate-agent-schema.js

@@ -1,8 +1,9 @@
 /**
  * Agent Schema Validator CLI
  *
- * Scans all *.agent.yaml files in src/{core,modules/*}/agents/
- * and validates them against the Zod schema.
+ * Scans for agent definitions in src/agents/:
+ * - Legacy format: *.agent.yaml (validated against Zod schema)
+ * - Native skill format: {name}/bmad-skill-manifest.yaml + SKILL.md
  *
  * Usage: node tools/validate-agent-schema.js [project_root]
  * Exit codes: 0 = success, 1 = validation failures
@@ -28,15 +29,80 @@ async function main(customProjectRoot) {
   const project_root = customProjectRoot || path.join(__dirname, '..');
 
   // Find all agent files
-  // TEA module structure: src/agents/*.agent.yaml (simpler than BMAD-METHOD)
+  // TEA module supports both legacy (*.agent.yaml) and native skill format (*/bmad-skill-manifest.yaml)
   const agentFiles = await glob('src/agents/*.agent.yaml', {
     cwd: project_root,
     absolute: true,
   });
 
+  // Always check for native skill manifests (supports mixed-mode repos)
+  const skillManifests = await glob('src/agents/*/bmad-skill-manifest.yaml', {
+    cwd: project_root,
+    absolute: true,
+  });
+
+  // If no legacy agents found, validate native skills or fail
   if (agentFiles.length === 0) {
+    if (skillManifests.length > 0) {
+      console.log(`Found ${skillManifests.length} native skill manifest(s) (no legacy *.agent.yaml files)\n`);
+
+      const manifestErrors = [];
+      for (const manifestPath of skillManifests) {
+        const relativePath = path.relative(process.cwd(), manifestPath);
+        try {
+          const fileContent = fs.readFileSync(manifestPath, 'utf8');
+          const manifest = yaml.parse(fileContent);
+
+          const requiredFields = ['type', 'name', 'module', 'canonicalId'];
+          const missingFields = requiredFields.filter((f) => !manifest[f]);
+          const issues = [];
+
+          if (missingFields.length > 0) {
+            issues.push({ message: `Missing required fields: ${missingFields.join(', ')}`, path: [] });
+          }
+
+          // Validate type value
+          const validTypes = ['agent', 'skill'];
+          if (manifest.type && !validTypes.includes(manifest.type)) {
+            issues.push({ message: `Invalid type "${manifest.type}". Expected one of: ${validTypes.join(', ')}`, path: [] });
+          }
+
+          // Verify SKILL.md exists alongside the manifest
+          const skillMdPath = path.join(path.dirname(manifestPath), 'SKILL.md');
+          if (!fs.existsSync(skillMdPath)) {
+            issues.push({ message: 'Missing SKILL.md file alongside manifest', path: [] });
+          }
+
+          if (issues.length > 0) {
+            manifestErrors.push({ file: relativePath, issues });
+          } else {
+            console.log(`✅ ${relativePath}`);
+          }
+        } catch (error) {
+          manifestErrors.push({
+            file: relativePath,
+            issues: [{ message: `Failed to parse YAML: ${error.message}`, path: [] }],
+          });
+        }
+      }
+
+      if (manifestErrors.length > 0) {
+        console.log('\n❌ Validation failed:\n');
+        for (const { file, issues } of manifestErrors) {
+          console.log(`\n📄 ${file}`);
+          for (const issue of issues) {
+            console.log(`   Error: ${issue.message}`);
+          }
+        }
+        process.exit(1);
+      }
+
+      console.log(`\n✨ All ${skillManifests.length} native skill manifest(s) passed validation!\n`);
+      process.exit(0);
+    }
+
     console.log('❌ No agent files found. This likely indicates a configuration error.');
-    console.log('   Expected to find *.agent.yaml files in src/agents/');
+    console.log('   Expected to find *.agent.yaml files or native skill manifests in src/agents/');
     process.exit(1);
   }
 
@@ -79,6 +145,39 @@ async function main(customProjectRoot) {
     }
   }
 
+  // Also validate native skill manifests in mixed-mode repos
+  if (skillManifests.length > 0) {
+    console.log(`\nAlso found ${skillManifests.length} native skill manifest(s)\n`);
+    for (const manifestPath of skillManifests) {
+      const relativePath = path.relative(process.cwd(), manifestPath);
+      try {
+        const fileContent = fs.readFileSync(manifestPath, 'utf8');
+        const manifest = yaml.parse(fileContent);
+        const requiredFields = ['type', 'name', 'module', 'canonicalId'];
+        const missingFields = requiredFields.filter((f) => !manifest[f]);
+        const issues = [];
+        if (missingFields.length > 0) {
+          issues.push({ message: `Missing required fields: ${missingFields.join(', ')}`, path: [] });
+        }
+        const validTypes = ['agent', 'skill'];
+        if (manifest.type && !validTypes.includes(manifest.type)) {
+          issues.push({ message: `Invalid type "${manifest.type}". Expected one of: ${validTypes.join(', ')}`, path: [] });
+        }
+        const skillMdPath = path.join(path.dirname(manifestPath), 'SKILL.md');
+        if (!fs.existsSync(skillMdPath)) {
+          issues.push({ message: 'Missing SKILL.md file alongside manifest', path: [] });
+        }
+        if (issues.length > 0) {
+          errors.push({ file: relativePath, issues });
+        } else {
+          console.log(`✅ ${relativePath}`);
+        }
+      } catch (error) {
+        errors.push({ file: relativePath, issues: [{ message: `Failed to parse YAML: ${error.message}`, path: [] }] });
+      }
+    }
+  }
+
   // Report errors
   if (errors.length > 0) {
     console.log('\n❌ Validation failed for the following files:\n');
@@ -99,7 +198,8 @@ async function main(customProjectRoot) {
     process.exit(1);
   }
 
-  console.log(`\n✨ All ${agentFiles.length} agent file(s) passed validation!\n`);
+  const totalCount = agentFiles.length + skillManifests.length;
+  console.log(`\n✨ All ${totalCount} agent file(s) passed validation!\n`);
   process.exit(0);
 }
 

package/docs/MIGRATION.md

@@ -1,488 +0,0 @@
----
-title: Migration Guide
-description: Migrate from BMM-embedded TEA to standalone TEA module (v1.0.0+)
----
-
-# Migration Guide: BMM-Embedded TEA → Standalone TEA Module
-
-This guide helps you migrate from the BMM-embedded version of TEA to the standalone TEA module (v1.0.0+).
-
-## Overview
-
-TEA (Test Engineering Architect) has been extracted from the BMAD Method (BMM) core repository into a standalone, independently installable module. This allows:
-
-- **Independent versioning** and release cycles
-- **Optional installation** - use TEA only when needed
-- **Cleaner separation** of concerns
-- **Easier maintenance** and contribution
-
-## Breaking Changes
-
-### 1. Command Namespace
-
-All TEA commands have changed namespace from `/bmad:bmm:tea:*` to `/bmad:tea:*`.
-
-| Old Command (BMM-embedded)     | New Command (Standalone) |
-| ------------------------------ | ------------------------ |
-| `/bmad:bmm:tea:framework`      | `/bmad:tea:framework`    |
-| `/bmad:bmm:tea:ci`             | `/bmad:tea:ci`           |
-| `/bmad:bmm:tea:test-design`    | `/bmad:tea:test-design`  |
-| `/bmad:bmm:tea:atdd`           | `/bmad:tea:atdd`         |
-| `/bmad:bmm:tea:automate`       | `/bmad:tea:automate`     |
-| `/bmad:bmm:tea:test-review`    | `/bmad:tea:test-review`  |
-| `/bmad:bmm:tea:trace`          | `/bmad:tea:trace`        |
-| `/bmad:bmm:tea:nfr-assess`     | `/bmad:tea:nfr-assess`   |
-| **Short triggers** (unchanged) |                          |
-| `TF`, `CI`, `TD`, `AT`, `TA`   | Same                     |
-| `RV`, `TR`, `NR`               | Same                     |
-
-Codex skill-mode workflow equivalents: `framework` → `$bmad-tea-testarch-framework`, `ci` → `$bmad-tea-testarch-ci`, `test-design` → `$bmad-tea-testarch-test-design`, `atdd` → `$bmad-tea-testarch-atdd`, `automate` → `$bmad-tea-testarch-automate`, `test-review` → `$bmad-tea-testarch-test-review`, `trace` → `$bmad-tea-testarch-trace`, `nfr-assess` → `$bmad-tea-testarch-nfr`, `teach-me-testing` → `$bmad-tea-teach-me-testing`.
-
-Clarification: short triggers like `TD` and `TA` are agent menu triggers after TEA activation; invocation differs by tool (slash commands vs Codex skill calls).
-
-**Action Required**: Update any saved prompts, scripts, or documentation that reference the old commands.
-
-### 2. Module Installation
-
-TEA is no longer bundled with BMM by default. You must install it separately.
-
-#### Old Behavior (BMM-embedded)
-
-```bash
-# TEA automatically included
-npx bmad-method install
-```
-
-#### New Behavior (Standalone)
-
-```bash
-# Install BMAD Method first
-npx bmad-method install
-# Select modules (BMM, TEA, etc.)
-
-# Or install TEA separately later
-npx bmad-method install
-# Select: Test Architect (TEA)
-```
-
-**Action Required**: Install TEA module explicitly if not already installed.
-
-### 3. File Path Changes
-
-Internal file paths have changed to reflect TEA's standalone structure.
-
-| Old Path (BMM-embedded)         | New Path (Standalone)       |
-| ------------------------------- | --------------------------- |
-| `src/bmm/agents/tea.agent.yaml` | `src/agents/tea.agent.yaml` |
-| `src/bmm/testarch/knowledge/`   | `src/testarch/knowledge/`   |
-| `src/bmm/workflows/testarch/`   | `src/workflows/testarch/`   |
-| `_bmad/bmm/tea`                 | `_bmad/tea/`                |
-
-**Action Required**: None for end users. This only affects contributors and maintainers.
-
-### 4. Configuration Variables
-
-TEA configuration is now in its own `src/module.yaml` instead of BMM's configuration.
-
-#### Old Configuration (BMM-embedded)
-
-Configuration was embedded in BMM's module.yaml:
-
-```yaml
-# In BMM module.yaml
-variables:
-  bmm_test_artifacts: test-results
-  # TEA variables mixed with BMM
-```
-
-#### New Configuration (Standalone)
-
-TEA has its own configuration file:
-
-```yaml
-# In TEA src/module.yaml
-variables:
-  test_artifacts:
-    description: Base folder for test artifacts
-    default: test-results
-    prompt: true
-
-  tea_use_playwright_utils:
-    description: Enable Playwright Utils integration
-    default: false
-    prompt: true
-
-  tea_browser_automation:
-    description: Browser automation strategy (auto/cli/mcp/none)
-    default: 'auto'
-    prompt: true
-
-  test_design_output:
-    description: Test design documents folder
-    default: test-design
-    prompt: false
-
-  test_review_output:
-    description: Test review reports folder
-    default: test-review
-    prompt: false
-
-  trace_output:
-    description: Traceability reports folder
-    default: trace
-    prompt: false
-```
-
-**Action Required**: Reconfigure TEA variables during installation or update `_bmad/tea/module.yaml` manually.
-
-## Migration Steps
-
-### Step 1: Check Current BMAD Version
-
-Ensure you have BMAD Method v7.0.0+ (upcoming) or the latest version that supports modular installation.
-
-```bash
-# Check BMAD version
-bmad --version
-```
-
-### Step 2: Install Standalone TEA
-
-Run the BMAD installer and select TEA:
-
-```bash
-npx bmad-method install
-# When prompted, select:
-# ✓ Test Architect (TEA)
-```
-
-Follow the installation prompts to configure TEA variables:
-
-1. **test_artifacts**: Base folder for test outputs (default: `test-results`)
-2. **tea_use_playwright_utils**: Enable Playwright Utils integration (yes/no)
-3. **tea_browser_automation**: Browser automation strategy (auto/cli/mcp/none)
-
-### Step 3: Update Command References
-
-Update any saved prompts, documentation, or scripts:
-
-**Example: Updating CI/CD Scripts**
-
-```bash
-# Old
-claude "/bmad:bmm:tea:test-design"
-
-# New
-claude "/bmad:tea:test-design"
-```
-
-Codex skill mode (in Codex chat): `$bmad-tea-testarch-test-design`
-
-**Example: Updating Documentation**
-
-```markdown
-<!-- Old -->
-
-Run `/bmad:bmm:tea:automate` to expand test coverage.
-
-<!-- New -->
-
-Run `/bmad:tea:automate` to expand test coverage.
-```
-
-Codex skill-mode equivalent: use `$bmad-tea-testarch-automate`.
-
-### Step 4: Verify Installation
-
-Load the TEA agent and run a test command:
-
-```bash
-# Start Claude Code or Claude Desktop
-claude
-
-# Load TEA agent
-tea
-
-# Test a workflow
-test-design
-```
-
-You should see TEA load successfully with the message:
-
-```
-✓ Loaded agent: Murat (Master Test Architect and Quality Advisor)
-```
-
-### Step 5: Validate Configuration
-
-Check that TEA variables are correctly configured:
-
-```bash
-# Check _bmad directory
-ls -la _bmad/tea/
-
-# Verify module.yaml
-cat _bmad/tea/module.yaml
-```
-
-Expected contents:
-
-```
-_bmad/tea/
-├── module.yaml         # TEA configuration
-├── agents/
-│   └── tea.agent.yaml
-├── workflows/
-│   └── testarch/       # 9 workflows
-└── testarch/
-    ├── tea-index.csv   # Knowledge base index
-    └── knowledge/      # 35 fragments
-```
-
-## What Stays the Same
-
-Despite the migration, these aspects remain **unchanged**:
-
-✅ **Short Trigger Commands**: `TMT`, `TF`, `CI`, `TD`, `AT`, `TA`, `RV`, `TR`, `NR` work exactly the same
-
-✅ **Workflow Behavior**: All 9 workflows function identically
-
-✅ **Knowledge Base**: Same 35 knowledge fragments with identical content
-
-✅ **Output Formats**: Test designs, reports, and checklists maintain the same structure
-
-✅ **Playwright Utils Integration**: Same integration patterns and utilities
-
-✅ **Browser Automation**: CLI and MCP enhancements available via `tea_browser_automation` config
-
-✅ **Quality Standards**: Same testing best practices and quality gates
-
-## Configuration Differences
-
-### Old: BMM-Embedded Configuration
-
-```yaml
-# Variables were part of BMM module
-variables:
-  bmm_test_artifacts: test-results
-  # Mixed BMM and TEA config
-```
-
-### New: Standalone Configuration
-
-```yaml
-# TEA has its own module.yaml
-code: tea
-name: Test Architect (TEA)
-
-variables:
-  test_artifacts:
-    description: Base folder for test artifacts
-    default: test-results
-    prompt: true
-
-  tea_use_playwright_utils:
-    description: Enable Playwright Utils integration
-    default: false
-    prompt: true
-
-  tea_browser_automation:
-    description: Browser automation strategy (auto/cli/mcp/none)
-    default: 'auto'
-    prompt: true
-
-  test_design_output:
-    description: Test design documents folder
-    default: test-design
-    prompt: false
-
-  test_review_output:
-    description: Test review reports folder
-    default: test-review
-    prompt: false
-
-  trace_output:
-    description: Traceability reports folder
-    default: trace
-    prompt: false
-```
-
-### 5. Browser Automation Config Migration
-
-The `tea_use_mcp_enhancements` boolean flag has been replaced by `tea_browser_automation` string config:
-
-| Old Setting                       | New Setting                      | Notes                              |
-| --------------------------------- | -------------------------------- | ---------------------------------- |
-| `tea_use_mcp_enhancements: true`  | `tea_browser_automation: "auto"` | Auto-selects CLI or MCP per action |
-| `tea_use_mcp_enhancements: false` | `tea_browser_automation: "none"` | No browser interaction             |
-
-**New modes available:**
-
-- `"auto"` — Smart CLI/MCP selection with fallback (recommended)
-- `"cli"` — Playwright CLI only
-- `"mcp"` — Playwright MCP only (equivalent to old `true`)
-- `"none"` — No browser interaction (equivalent to old `false`)
-
-**Action Required:** Update `_bmad/tea/config.yaml`:
-
-```yaml
-# Old
-tea_use_mcp_enhancements: true
-
-# New
-tea_browser_automation: 'auto'
-```
-
-The BMAD installer will auto-migrate existing configs during the next installation.
-
-See [Configure Browser Automation](/docs/how-to/customization/configure-browser-automation.md) for full details.
-
-## Troubleshooting
-
-### Issue: "Agent Not Found" Error
-
-**Symptom**: `Error: Agent '_bmad/tea' not found`
-
-**Solution**:
-
-1. Verify TEA is installed:
-   ```bash
-   ls -la _bmad/tea/
-   ```
-2. If missing, reinstall TEA:
-   ```bash
-   npx bmad-method install
-   # Select: Test Architect (TEA)
-   ```
-
-### Issue: Old Commands Not Working
-
-**Symptom**: `/bmad:bmm:tea:test-design` returns "Command not found"
-
-**Solution**: Update to new namespace:
-
-```text
-# Old (won't work)
-/bmad:bmm:tea:test-design
-
-# New (correct)
-/bmad:tea:test-design
-
-# Codex skill mode
-$bmad-tea-testarch-test-design
-```
-
-### Issue: Configuration Variables Not Set
-
-**Symptom**: TEA asks for variables every time
-
-**Solution**: Ensure `_bmad/tea/module.yaml` exists and contains variable definitions.
-
-### Issue: Knowledge Base Fragments Not Loading
-
-**Symptom**: TEA workflows run but don't include knowledge base context
-
-**Solution**:
-
-1. Check tea-index.csv exists:
-   ```bash
-   ls -la _bmad/tea/testarch/tea-index.csv
-   ```
-2. Verify knowledge fragments:
-   ```bash
-   ls -la _bmad/tea/testarch/knowledge/
-   # Should show 35 .md files
-   ```
-
-### Issue: Workflows Producing Different Outputs
-
-**Symptom**: Test designs or reports look different than before
-
-**Solution**: This shouldn't happen - workflows are functionally identical. If you notice differences:
-
-1. Check you're using the same workflow (e.g., `test-design` not `test-review`)
-2. Verify knowledge base fragments loaded correctly
-3. Check variable configuration matches your previous setup
-
-For additional help, see [docs/reference/troubleshooting.md](/docs/reference/troubleshooting.md) or open an issue on GitHub.
-
-## Benefits of Standalone TEA
-
-### For End Users
-
-- ✅ **Optional Installation**: Only install TEA if you need test architecture guidance
-- ✅ **Lighter Weight**: Don't carry TEA's dependencies if you're not using it
-- ✅ **Clearer Purpose**: TEA focuses exclusively on test engineering
-- ✅ **Faster Updates**: TEA can release independently of BMM
-
-### For Contributors
-
-- ✅ **Focused Codebase**: Work on testing features without BMM complexity
-- ✅ **Independent Testing**: Test suite focused only on TEA functionality
-- ✅ **Easier Maintenance**: Changes to TEA don't affect BMM and vice versa
-- ✅ **Clearer Ownership**: Test engineering contributions go to TEA repo
-
-## Compatibility Matrix
-
-| BMAD Method Version | TEA Version | Compatible? | Notes                               |
-| ------------------- | ----------- | ----------- | ----------------------------------- |
-| v6.x (legacy)       | Embedded    | ✅          | Old BMM-embedded TEA                |
-| v7.0.0+             | 1.0.0+      | ✅          | Standalone TEA module               |
-| v7.0.0+             | Embedded    | ❌          | TEA removed from BMM in v7.0.0      |
-| v6.x (legacy)       | 1.0.0+      | ❌          | Standalone TEA requires BMM v7.0.0+ |
-
-## Migration Checklist
-
-Use this checklist to ensure a smooth migration:
-
-- [ ] Verify BMAD Method version is v7.0.0 or later
-- [ ] Install standalone TEA module via `npx bmad-method install`
-- [ ] Configure TEA variables (test_artifacts, Playwright Utils, MCP)
-- [ ] Update saved invocations for your tool (`/bmad:tea:*` for slash-command tools, or `$bmad-tea-*` skills for Codex)
-- [ ] Update documentation references to new commands
-- [ ] Update CI/CD scripts if they invoke TEA commands
-- [ ] Test each workflow you use (e.g., `test-design`, `automate`, `atdd`)
-- [ ] Verify knowledge base fragments load correctly
-- [ ] Confirm output formats match expectations
-- [ ] Update team documentation and onboarding guides
-
-## Getting Help
-
-If you encounter issues during migration:
-
-1. **Documentation**: Check [test-architect.bmad-method.org](https://test-architect.bmad-method.org)
-2. **Troubleshooting**: See [docs/reference/troubleshooting.md](/docs/reference/troubleshooting.md)
-3. **GitHub Issues**: Open an issue at [bmad-code-org/bmad-method-test-architecture-enterprise](https://github.com/bmad-code-org/bmad-method-test-architecture-enterprise/issues)
-4. **Community**: Join discussions in GitHub Discussions
-
-## FAQ
-
-### Do I need to migrate immediately?
-
-**No.** If you're on BMAD Method v6.x with embedded TEA, you can continue using it. However, new features and updates will only be released for standalone TEA (v1.0.0+).
-
-### Can I use both BMM and TEA together?
-
-**Yes!** That's the recommended approach. Install both modules for integrated development and testing workflows.
-
-### Will my old test designs/reports still work?
-
-**Yes.** Output formats remain compatible. You can continue using test designs and reports generated by BMM-embedded TEA.
-
-### What if I don't want to use TEA?
-
-**That's fine!** TEA is now optional. Simply don't install it during BMAD Method setup.
-
-### Is standalone TEA compatible with Playwright Utils?
-
-**Yes.** Standalone TEA has the same Playwright Utils integration as BMM-embedded TEA. Enable it via the `tea_use_playwright_utils` variable during installation.
-
-### Where can I find the old BMM-embedded TEA?
-
-BMM-embedded TEA will remain available in BMAD Method v6.x releases for backwards compatibility. However, it won't receive new features or updates.
-
----
-
-**Ready to migrate?** Start with [Step 1: Check Current BMAD Version](#step-1-check-current-bmad-version)
-
-**Need help?** See [Troubleshooting](#troubleshooting) or [Getting Help](#getting-help)

package/src/agents/tea.agent.yaml

@@ -1,67 +0,0 @@
-# Test Architect + Quality Advisor Agent Definition
-
-agent:
-  webskip: true
-  metadata:
-    id: "_bmad/tea/agents/tea.md"
-    name: Murat
-    title: Master Test Architect and Quality Advisor
-    icon: 🧪
-    module: tea
-    hasSidecar: false
-
-  persona:
-    role: Master Test Architect
-    identity: Test architect specializing in risk-based testing, fixture architecture, ATDD, API testing, backend services, UI automation, CI/CD governance, and scalable quality gates. Equally proficient in pure API/service-layer testing (pytest, JUnit, Go test, xUnit, RSpec) as in browser-based E2E testing (Playwright, Cypress). Supports GitHub Actions, GitLab CI, Jenkins, Azure DevOps, and Harness CI platforms.
-    communication_style: "Blends data with gut instinct. 'Strong opinions, weakly held' is their mantra. Speaks in risk calculations and impact assessments."
-    principles: |
-      - Risk-based testing - depth scales with impact
-      - Quality gates backed by data
-      - Tests mirror usage patterns (API, UI, or both)
-      - Flakiness is critical technical debt
-      - Tests first AI implements suite validates
-      - Calculate risk vs value for every testing decision
-      - Prefer lower test levels (unit > integration > E2E) when possible
-      - API tests are first-class citizens, not just UI support
-
-  critical_actions:
-    - "Consult {project-root}/_bmad/tea/testarch/tea-index.csv to select knowledge fragments under knowledge/ and load only the files needed for the current task"
-    - "Load the referenced fragment(s) from {project-root}/_bmad/tea/testarch/knowledge/ before giving recommendations"
-    - "Cross-check recommendations with the current official Playwright, Cypress, pytest, JUnit, Go test, Pact, and CI platform documentation"
-
-  menu:
-    - trigger: TMT or fuzzy match on teach-me-testing
-      workflow: "{project-root}/_bmad/tea/workflows/testarch/teach-me-testing/workflow.md"
-      description: "[TMT] Teach Me Testing: Interactive learning companion - 7 progressive sessions teaching testing fundamentals through advanced practices"
-
-    - trigger: TF or fuzzy match on test-framework
-      workflow: "{project-root}/_bmad/tea/workflows/testarch/framework/workflow.yaml"
-      description: "[TF] Test Framework: Initialize production-ready test framework architecture"
-
-    - trigger: AT or fuzzy match on atdd
-      workflow: "{project-root}/_bmad/tea/workflows/testarch/atdd/workflow.yaml"
-      description: "[AT] ATDD: Generate failing acceptance tests plus an implementation checklist before development"
-
-    - trigger: TA or fuzzy match on test-automate
-      workflow: "{project-root}/_bmad/tea/workflows/testarch/automate/workflow.yaml"
-      description: "[TA] Test Automation: Generate prioritized API/E2E tests, fixtures, and DoD summary for a story or feature"
-
-    - trigger: TD or fuzzy match on test-design
-      workflow: "{project-root}/_bmad/tea/workflows/testarch/test-design/workflow.yaml"
-      description: "[TD] Test Design: Risk assessment plus coverage strategy for system or epic scope"
-
-    - trigger: TR or fuzzy match on test-trace
-      workflow: "{project-root}/_bmad/tea/workflows/testarch/trace/workflow.yaml"
-      description: "[TR] Trace Requirements: Map requirements to tests (Phase 1) and make quality gate decision (Phase 2)"
-
-    - trigger: NR or fuzzy match on nfr-assess
-      workflow: "{project-root}/_bmad/tea/workflows/testarch/nfr-assess/workflow.yaml"
-      description: "[NR] Non-Functional Requirements: Assess NFRs and recommend actions"
-
-    - trigger: CI or fuzzy match on continuous-integration
-      workflow: "{project-root}/_bmad/tea/workflows/testarch/ci/workflow.yaml"
-      description: "[CI] Continuous Integration: Recommend and Scaffold CI/CD quality pipeline"
-
-    - trigger: RV or fuzzy match on test-review
-      workflow: "{project-root}/_bmad/tea/workflows/testarch/test-review/workflow.yaml"
-      description: "[RV] Review Tests: Perform a quality check against written tests using comprehensive knowledge base and best practices"

package/src/teams/default-party.csv

@@ -1,2 +0,0 @@
-name,displayName,title,icon,role,identity,communicationStyle,principles,module,path
-"tea","Murat","Master Test Architect","🧪","Master Test Architect","Test architect specializing in CI/CD, automated frameworks, and scalable quality gates.","Blends data with gut instinct. 'Strong opinions, weakly held' is their mantra. Speaks in risk calculations and impact assessments.","Risk-based testing. Depth scales with impact. Quality gates backed by data. Tests mirror usage. Flakiness is critical debt. Tests first, AI implements, suite validates.","tea","_bmad/tea/agents/tea.agent.yaml"