feat: enhance documentation for challenge skill and add mermaid generation rules

Author: alexsoyes

aidd_docs/README.md

@@ -139,9 +139,8 @@ Auto-generated framework content: agents, commands, rules, skills, and templates
 
 | File                                                         | Description                                                                              | Argument Hint                                                |
 | ------------------------------------------------------------ | ---------------------------------------------------------------------------------------- | ------------------------------------------------------------ |
-| [list_untested.md](../../commands/06_tests/list_untested.md) | `List all untested behaviors in codebase`                                                | -                                                            |
-| [test_journey.md](../../commands/06_tests/test_journey.md)   | `Test a user journey end-to-end by navigating and validating each step in the browser.`  | `The user journey steps to validate and the URL to test on.` |
-| [write.md](../../commands/06_tests/write.md)                 | `Iterate on test creation and improvement until perfect test passes with best practices` | -                                                            |
+| [test.md](../../commands/06_tests/test.md)                   | `List untested behaviors and iterate on test creation until tests pass with best practices` | -                                                            |
+| [test_journey.md](../../commands/06_tests/test_journey.md)   | `Test a user journey end-to-end by navigating and validating each step in the browser.`    | `The user journey steps to validate and the URL to test on.` |
 
 #### `commands/07_documentation`
 

aidd_docs/templates/docs/CATALOG.md

@@ -0,0 +1,46 @@
+---
+name: test
+description: List untested behaviors and iterate on test creation until tests pass with best practices
+model: sonnet
+---
+
+# Test Iterator Prompt
+
+## Goal
+
+Identify untested behaviors in the feature, then create and iterate on tests until they pass with modern testing best practices.
+
+## Context
+
+- Current project testing framework and conventions
+- Test coverage and quality metrics
+
+### Testing rules
+
+```markdown
+@{{TOOLS}}/rules/
+```
+
+## Rules
+
+- Focus on ONE test at a time
+- Apply current testing best practices
+- Continue iterating until test passes AND meets quality criteria
+- Never compromise on test quality for speed
+- Focus on functional aspects only, ignore technical details
+
+## Process steps
+
+1. List untested behaviors in the target area
+   1. Think about behaviors to test based on existing ones
+   2. Determine a score, 0: not needed, 5: critical core flow to test
+   3. Group them by distinct sections
+   4. Prioritize based on score and impact
+   5. Display organized minimal bullet list of untested behaviors
+2. Pick the highest-priority untested behavior
+3. Generate initial test with best practices
+4. Run test and capture results
+   1. If test fails: analyze failure, improve test, repeat from step 4
+   2. If test passes: validate against quality checklist
+   3. If quality insufficient: improve test quality, repeat from step 4
+5. Move to next untested behavior, repeat from step 2

commands/06_tests/list_untested.md

@@ -10,6 +10,10 @@ alwaysApply: false
 
 - Always have title in schema using "---" to define it
 
+## Global
+
+- NEVER use "\n"
+
 ## States and nodes
 
 - Define groups, parents, children
@@ -25,7 +29,6 @@ alwaysApply: false
 - Consistent naming throughout
 - Descriptive names (no "A", "B")
 - Surround names with quotes
-- NEVER use "\n"
 - Replace ":" with "$" in state names
 
 ## Links

commands/06_tests/test.md

@@ -0,0 +1,51 @@
+---
+name: challenge
+description: >-
+  Review and challenge previous work for improvements and correctness.
+  Use when the user says 'challenge this', 'review my work', 'is this correct',
+  asks for a critical review, or wants to rethink a decision.
+---
+
+# Challenge
+
+## Goal
+
+Critically review previous work to ensure 100% correctness, identify edge cases, and suggest improvements.
+
+## Rules
+
+- When no "Deal breakers", then correctness is 100%.
+- Challenge assumptions and decisions.
+- Look for edge cases, errors, inconsistencies, missing parts, duplications.
+- Aim for simplifications — every step must be logical without gaps.
+- Think in first principles.
+
+## Process
+
+1. Review previous work in detail using: {{TOOLS}}/commands/02_context/challenge.md
+2. Identify potential issues or areas for improvement.
+3. Suggest changes or enhancements.
+
+## Output Format
+
+```text
+My confidence level of correctness now: XX%
+
+# Previous work to review
+
+## ✅ 100% correctness
+
+-
+-
+
+## ❌ Deal breakers
+
+-
+-
+-
+
+## 🙏 Suggestions (enhancements only)
+
+-
+-
+```

commands/06_tests/write.md

@@ -29,6 +29,7 @@ Auto-generated framework content: agents, commands, rules, skills, and templates
 - [`scripts`](#scripts)
 - [`skills`](#skills)
   - [`skills/aidd-auto-implement`](#skillsaidd-auto-implement)
+  - [`skills/challenge`](#skillschallenge)
 - [`templates`](#templates)
   - [`templates/docs`](#templatesdocs)
 
@@ -155,9 +156,8 @@ No files found.
 
 | File | Description | Argument Hint |
 |------|---|---|
-| [list_untested.md](../../commands/06_tests/list_untested.md) | `List all untested behaviors in codebase` | - |
 | [test_journey.md](../../commands/06_tests/test_journey.md) | `Test a user journey end-to-end by navigating and validating each step in the browser.` | `The user journey steps to validate and the URL to test on.` |
-| [write.md](../../commands/06_tests/write.md) | `Iterate on test creation and improvement until perfect test passes with best practices` | - |
+| [test.md](../../commands/06_tests/test.md) | `List untested behaviors and iterate on test creation until tests pass with best practices` | - |
 
 #### `commands/07_documentation`
 
@@ -224,6 +224,12 @@ No files found.
 |------|---|---|
 | [SKILL.md](../../skills/aidd-auto-implement/SKILL.md) | `Autonomously run the AI-Driven Development workflow to code an high quality feature.` | `The URL or file path of the issue or task to implement.` |
 
+#### `skills/challenge`
+
+| File | Description |
+|------|---|
+| [SKILL.md](../../skills/challenge/SKILL.md) | `Review and challenge previous work for improvements and correctness. Use when the user says 'challenge this', 'review my work', 'is this correct', asks for a critical review, or wants to rethink a decision.` |
+
 ### `templates`
 
 #### `templates/docs`