clavix 2.8.2 → 3.0.1

package/dist/templates/slash-commands/_canonical/fast.md

@@ -1,38 +1,50 @@
 ---
 name: "Clavix: Fast"
-description: CLEAR-guided quick improvements (C, L, E components)
+description: Quick prompt improvements with smart quality assessment and triage
 ---
 
-# Clavix Fast Mode - CLEAR Framework Quick Improvement
+# Clavix Fast Mode - Universal Prompt Intelligence
 
-You are helping the user improve their prompt using Clavix's fast mode, which applies the CLEAR Framework (Concise, Logical, Explicit components) with smart triage.
+You are helping the user improve their prompt using Clavix's fast mode, which applies universal prompt intelligence with smart quality assessment and triage.
 
-## CLEAR Framework (Fast Mode)
+## What is Clavix?
 
-**What is CLEAR?**
-An academically-validated prompt engineering framework by Dr. Leo Lo (University of New Mexico).
+Clavix provides **universal prompt intelligence** that automatically detects intent and applies the right optimization patterns. No frameworks to learn—just better prompts, instantly.
 
-**Fast Mode Uses:**
-- **[C] Concise**: Remove verbosity, pleasantries, unnecessary words
-- **[L] Logical**: Ensure coherent sequencing (context → requirements → constraints → output)
-- **[E] Explicit**: Add persona, format, tone, success criteria
+**Fast Mode Features:**
+- **Intent Detection**: Automatically identifies what you're trying to achieve
+- **Quality Assessment**: 5-dimension analysis (Clarity, Efficiency, Structure, Completeness, Actionability)
+- **Smart Optimization**: Applies proven patterns based on your intent
+- **Intelligent Triage**: Recommends deep mode when comprehensive analysis would help
 
-**Deep Mode Adds:** [A] Adaptive variations, [R] Reflective validation (use `/clavix:deep` for these)
+**Deep Mode Adds:** Alternative approaches, edge case analysis, validation checklists (use `/clavix:deep` for these)
 
 ## Instructions
 
 1. Take the user's prompt: `{{ARGS}}`
 
-2. **CLEAR Analysis** - Assess the prompt using three components:
+2. **Intent Detection** - Analyze what the user is trying to achieve:
+   - **code-generation**: Writing new code or functions
+   - **planning**: Designing architecture or breaking down tasks
+   - **refinement**: Improving existing code or prompts
+   - **debugging**: Finding and fixing issues
+   - **documentation**: Creating docs or explanations
+   - **prd-generation**: Creating requirements documents
 
-   - **Conciseness [C]**: Identify verbose language, pleasantries ("please", "could you"), unnecessary qualifiers
-   - **Logic [L]**: Check sequencing and flow - is information presented coherently?
-   - **Explicitness [E]**: Verify specifications - persona, output format, tone, success criteria
+3. **Quality Assessment** - Evaluate across 5 dimensions:
 
-3. **CLEAR-Aware Smart Triage**: Use multi-factor content-quality assessment to determine if deep analysis is needed:
+   - **Clarity**: Is the objective clear and unambiguous?
+   - **Efficiency**: Is the prompt concise without losing critical information?
+   - **Structure**: Is information organized logically?
+   - **Completeness**: Are all necessary details provided?
+   - **Actionability**: Can AI take immediate action on this prompt?
 
-   **Primary Indicators** (CLEAR scores - most important):
-   - **Low CLEAR scores**: Conciseness < 60%, Logic < 60%, or Explicitness < 50%
+   Score each dimension 0-100%, calculate weighted overall score.
+
+4. **Smart Triage** - Determine if deep analysis is needed:
+
+   **Primary Indicators** (quality scores - most important):
+   - **Low quality scores**: Overall < 65%, or any dimension < 50%
 
    **Secondary Indicators** (content quality):
    - **Missing critical elements**: 3+ missing from (context, tech stack, success criteria, user needs, expected output)
@@ -41,39 +53,43 @@ An academically-validated prompt engineering framework by Dr. Leo Lo (University
    - **Context depth**: Extremely brief (<15 words) OR overly verbose (>100 words without structure)
 
    **Escalation Decision**:
-   - If **Low CLEAR scores** + **2+ Secondary Indicators**: **Strongly recommend `/clavix:deep`**
-   - If **Low CLEAR scores** only: **Suggest `/clavix:deep`** but can proceed with fast mode
-   - Explain which CLEAR component needs deeper analysis and why
+   - If **Low quality scores** + **2+ Secondary Indicators**: **Strongly recommend `/clavix:deep`**
+   - If **Low quality scores** only: **Suggest `/clavix:deep`** but can proceed with fast mode
+   - Explain which quality dimension needs deeper analysis and why
 
    Ask the user:
    - Switch to deep mode (recommended when strongly recommended)
    - Continue with fast mode (acceptable for suggestion-level, but at their own risk for strong recommendation)
 
-4. Generate a **CLEAR-optimized** structured prompt with these sections:
+5. Generate an **optimized** structured prompt with these sections:
    **Objective**: Clear, specific goal
    **Requirements**: Detailed, actionable requirements
    **Technical Constraints**: Technologies, performance needs, integrations
    **Expected Output**: What the result should look like
    **Success Criteria**: How to measure completion
 
-5. **CLEAR Changes Made**: List improvements with CLEAR component labels:
-   - **[C]** "Removed 15 unnecessary words and pleasantries"
-   - **[L]** "Restructured: context → requirements → constraints → output"
-   - **[E]** "Added explicit persona (senior developer), output format (React component), tone (production-ready)"
+6. **Improvements Applied**: List enhancements with quality dimension labels:
+   - **[Efficiency]** "Removed 15 unnecessary words and pleasantries"
+   - **[Structure]** "Reorganized: objective → requirements → constraints → output"
+   - **[Clarity]** "Added explicit persona (senior developer), output format (React component), tone (production-ready)"
+   - **[Completeness]** "Added missing tech stack and success criteria"
+   - **[Actionability]** "Converted vague request into specific, executable tasks"
 
-6. Present the CLEAR-optimized prompt in a code block for easy copying.
+7. Present the optimized prompt in a code block for easy copying.
 
 ## Fast Mode Features
 
-**Include (CLEAR C, L, E):**
-- **CLEAR Assessment** (Conciseness, Logic, Explicitness scores with issues)
-- Single CLEAR-optimized improved prompt
-- **CLEAR Changes Made** (labeled with [C], [L], [E] components)
-- Recommendation to use deep mode for Adaptive & Reflective components
+**Include:**
+- **Intent Analysis** (detected intent type with confidence)
+- **Quality Assessment** (5 dimensions: Clarity, Efficiency, Structure, Completeness, Actionability)
+- Single optimized improved prompt
+- **Improvements Applied** (labeled with quality dimensions)
+- Recommendation to use deep mode for comprehensive analysis
 
 **Skip (use `/clavix:deep` instead):**
-- **[A] Adaptive**: Alternative phrasings, structures, flexibility
-- **[R] Reflective**: Validation checklists, edge cases, quality criteria
+- Alternative phrasings and structures
+- Validation checklists and edge cases
+- Quality criteria and risk assessment
 - Strategic analysis (architecture, security - that's for `/clavix:prd`)
 
 ## Example
@@ -82,29 +98,41 @@ If user provides: "Please could you maybe help me create a login page?"
 
 Output:
 ```
-## CLEAR Analysis (Fast Mode)
+## Clavix Fast Mode Analysis
+
+### Intent Detection:
+Type: code-generation
+Confidence: 85%
 
-### CLEAR Framework Assessment:
+### Quality Assessment:
 
-[C] Conciseness: 45%
-    • 4 unnecessary pleasantries detected ("Please", "could you", "maybe", "help me")
+Clarity: 40%
+    • Objective unclear - "create" vs "design" vs "implement"?
+    • No specifics about authentication method
+
+Efficiency: 35%
+    • 4 unnecessary pleasantries ("Please", "could you", "maybe", "help me")
     • Low signal-to-noise ratio (core request is only 4 words)
 
-[L] Logic: 85%
+Structure: 85%
     • Single request, coherent but minimal
-    • Suggested flow: Context → Requirements → Constraints → Output
+    • Suggested flow: Objective → Requirements → Constraints → Output
+
+Completeness: 20%
+    • Missing: tech stack, authentication context, success criteria, constraints
+    • No authentication method specified
 
-[E] Explicitness: 25%
-    • Missing: persona, output format, tone, success criteria, technical constraints
-    • No authentication context specified
+Actionability: 30%
+    • Too vague to start implementation
+    • Missing technical specifications
 
-Overall CLEAR Score: 51% (needs-improvement)
+Overall Quality: 42% (needs-improvement)
 
 Recommendation:
-For Adaptive variations (A) and Reflective validation (R), use:
+For comprehensive analysis with alternatives, edge cases, and validation checklists, use:
   clavix deep "<your prompt>"
 
-### CLEAR-Optimized Prompt:
+### Optimized Prompt:
 
 Objective: Build a secure user authentication login page
 
@@ -129,18 +157,20 @@ Success Criteria:
 - Invalid credentials show appropriate errors
 - Page is accessible via keyboard navigation
 
-### CLEAR Changes Made:
+### Improvements Applied:
 
-[C] Removed 4 pleasantries ("Please", "could you", "maybe", "help me"), reduced from 11 words to core intent
-[L] Structured logical flow: Objective → Requirements → Technical Constraints → Expected Output → Success Criteria
-[E] Added explicit specifications: React TypeScript persona, component output format, production-ready tone, accessibility criteria
+[Efficiency] Removed 4 pleasantries ("Please", "could you", "maybe", "help me"), reduced from 11 words to core intent
+[Structure] Organized logical flow: Objective → Requirements → Technical Constraints → Expected Output → Success Criteria
+[Clarity] Added explicit specifications: React TypeScript persona, component output format, production-ready tone
+[Completeness] Added tech stack (React/TypeScript), authentication method (JWT), accessibility standards (WCAG 2.1 AA)
+[Actionability] Converted vague "create" into specific implementation requirements with measurable success criteria
 ```
 
 ## Next Steps (v2.7+)
 
 ### Saving the Prompt (REQUIRED)
 
-After displaying the CLEAR-optimized prompt, you MUST save it to ensure it's available for the prompt lifecycle workflow.
+After displaying the optimized prompt, you MUST save it to ensure it's available for the prompt lifecycle workflow.
 
 **If user ran CLI command** (`clavix fast "prompt"`):
 - Prompt is automatically saved ✓
@@ -177,12 +207,14 @@ originalPrompt: <user's original prompt text>
 
 # Improved Prompt
 
-<Insert the CLEAR-optimized prompt content from your analysis above>
+<Insert the optimized prompt content from your analysis above>
 
-## CLEAR Scores
-- **C** (Conciseness): <percentage>%
-- **L** (Logic): <percentage>%
-- **E** (Explicitness): <percentage>%
+## Quality Scores
+- **Clarity**: <percentage>%
+- **Efficiency**: <percentage>%
+- **Structure**: <percentage>%
+- **Completeness**: <percentage>%
+- **Actionability**: <percentage>%
 - **Overall**: <percentage>% (<rating>)
 
 ## Original Prompt
@@ -246,7 +278,7 @@ clavix prompts clear --fast
 
 ## Workflow Navigation
 
-**You are here:** Fast Mode (Quick CLEAR Improvement)
+**You are here:** Fast Mode (Quick Prompt Intelligence)
 
 **Common workflows:**
 - **Quick cleanup**: `/clavix:fast` → `/clavix:execute` → Implement
@@ -257,18 +289,18 @@ clavix prompts clear --fast
 **Related commands:**
 - `/clavix:execute` - Execute saved prompt
 - `/clavix:prompts` - Manage saved prompts
-- `/clavix:deep` - Full CLEAR analysis (all 5 components: C, L, E, A, R)
-- `/clavix:prd` - Generate PRD for strategic planning
+- `/clavix:deep` - Comprehensive analysis with alternatives, edge cases, validation
+- `/clavix:prd` - Generate PRD for strategic planning (Clavix Planning Mode)
 - `/clavix:start` - Conversational exploration before prompting
 
 ## Tips
 
-- **Apply CLEAR framework** systematically: C, L, E components
-- Use **CLEAR-aware triage** to prevent inadequate analysis
-- Label all changes with CLEAR components for education
-- For comprehensive analysis with [A] and [R], recommend `/clavix:deep`
+- **Intent-aware optimization**: Clavix automatically detects what you're trying to achieve
+- Use **smart triage** to prevent inadequate analysis
+- Label all changes with quality dimensions for education
+- For comprehensive analysis with alternatives and validation, recommend `/clavix:deep`
 - For strategic planning, recommend `/clavix:prd`
-- Focus on making prompts **CLEAR** quickly
+- Focus on making prompts **actionable** quickly
 
 ## Troubleshooting
 
@@ -294,22 +326,22 @@ echo '{"version":"1.0","prompts":[]}' > .clavix/outputs/prompts/fast/.index.json
 - Try creating the directory structure again
 
 ### Issue: Triage keeps recommending deep mode
-**Cause**: Prompt has low CLEAR scores + multiple secondary indicators
+**Cause**: Prompt has low quality scores + multiple secondary indicators
 **Solution**:
 - Accept the recommendation - deep mode will provide better analysis
 - OR improve prompt manually before running fast mode again
-- Check which CLEAR component is scoring low and address it
+- Check which quality dimension is scoring low and address it
 
 ### Issue: Can't determine if prompt is complex enough for deep mode
-**Cause**: Borderline CLEAR scores or unclear content quality
+**Cause**: Borderline quality scores or unclear content quality
 **Solution**:
 - Err on side of fast mode first
 - If output feels insufficient, escalate to `/clavix:deep`
 - Use triage as guidance, not absolute rule
 
 ### Issue: Improved prompt still feels incomplete
-**Cause**: Fast mode only applies C, L, E components
+**Cause**: Fast mode only applies basic optimizations
 **Solution**:
-- Use `/clavix:deep` for Adaptive variations and Reflective validation
+- Use `/clavix:deep` for alternative approaches, edge cases, and validation checklists
 - OR use `/clavix:prd` if strategic planning is needed
 - Fast mode is for quick cleanup, not comprehensive analysis

package/dist/templates/slash-commands/_canonical/implement.md

@@ -66,7 +66,7 @@ You are helping the user implement tasks from their task plan with AI assistance
 
    d. **Implement the task**:
       - Write/modify code as needed
-      - Follow CLEAR principles
+      - Follow quality principles (clarity, structure, actionability)
       - Use PRD requirements as your guide
       - Ask user for clarification if needed
 

package/dist/templates/slash-commands/_canonical/plan.md

@@ -5,7 +5,7 @@ description: Generate implementation task breakdown from PRD
 
 # Clavix Plan - Task Breakdown Generator
 
-You are helping the user generate a CLEAR-optimized implementation task breakdown from their PRD.
+You are helping the user generate an optimized implementation task breakdown from their PRD.
 
 ## Instructions
 
@@ -54,12 +54,12 @@ If you have the full PRD content in memory and want to generate tasks directly:
 
 ### Part B: Behavioral Guidance (Task Breakdown Strategy)
 
-3. **How to structure tasks** (CLEAR-optimized task breakdown):
+3. **How to structure tasks** (optimized task breakdown):
 
    **Task Granularity Principles:**
-   - **[C] Concise**: Each task = 1 clear action (not "Build authentication system", but "Create user registration endpoint")
-   - **[L] Logical**: Tasks flow in implementation order (database schema → backend logic → frontend UI)
-   - **[E] Explicit**: Tasks specify deliverable (not "Add tests", but "Write unit tests for user service with >80% coverage")
+   - **Clarity**: Each task = 1 clear action (not "Build authentication system", but "Create user registration endpoint")
+   - **Structure**: Tasks flow in implementation order (database schema → backend logic → frontend UI)
+   - **Actionability**: Tasks specify deliverable (not "Add tests", but "Write unit tests for user service with >80% coverage")
 
    **Atomic Task Guidelines:**
    - **Ideal size**: Completable in 15-60 minutes
@@ -74,7 +74,7 @@ If you have the full PRD content in memory and want to generate tasks directly:
 
 4. **Review and customize generated tasks**:
    - The command will generate `tasks.md` in the PRD folder
-   - Tasks are organized into logical phases with CLEAR principles
+   - Tasks are organized into logical phases with quality principles
    - Each task includes:
      - Checkbox `- [ ]` for tracking
      - Clear deliverable description
@@ -85,11 +85,11 @@ If you have the full PRD content in memory and want to generate tasks directly:
      - Reorder for better flow
      - Add notes or sub-tasks
 
-5. **CLEAR Task Labeling** (optional, for education):
+5. **Task Quality Labeling** (optional, for education):
    When reviewing tasks, you can annotate improvements:
-   - **[C]**: "Split vague 'Add UI' into 3 concrete tasks"
-   - **[L]**: "Reordered tasks: database schema before API endpoints"
-   - **[E]**: "Added specific acceptance criteria (>80% test coverage)"
+   - **[Clarity]**: "Split vague 'Add UI' into 3 concrete tasks"
+   - **[Structure]**: "Reordered tasks: database schema before API endpoints"
+   - **[Actionability]**: "Added specific acceptance criteria (>80% test coverage)"
 
 6. **Next steps**:
    - Review and edit `tasks.md` if needed
@@ -221,7 +221,7 @@ The generated `tasks.md` will look like:
 
 ## Tips
 
-- Tasks are automatically optimized using CLEAR framework
+- Tasks are automatically optimized for clarity, structure, and actionability
 - Each task is concise and actionable
 - Tasks can reference specific PRD sections
 - Supports mini-PRD outputs from `/clavix:summarize` and session workflows via `--session` or `--active-session`
@@ -285,7 +285,7 @@ The generated `tasks.md` will look like:
    - Cut and paste tasks to correct order
    - Preserve task ID format
    - Maintain phase groupings
-4. Follow CLEAR [L] Logic principle: ensure sequential coherence
+4. Follow structure principle: ensure sequential coherence
 
 ### Issue: Tasks conflict with PRD or duplicate work
 **Cause**: Misinterpretation of PRD or redundant task generation

package/dist/templates/slash-commands/_canonical/prd.md

@@ -1,11 +1,19 @@
 ---
 name: "Clavix: PRD"
-description: CLEAR-validated PRD generation through Socratic questioning
+description: Clavix Planning Mode - Transform ideas into structured PRDs through strategic questioning
 ---
 
-# Clavix PRD Generation - CLEAR Framework Validated
+# Clavix Planning Mode
 
-You are helping the user create a Product Requirements Document (PRD) using Clavix's Socratic questioning approach. **Generated PRDs are automatically validated using the CLEAR Framework** (Concise, Logical, Explicit) for AI consumption quality.
+You are helping the user create a Product Requirements Document (PRD) using Clavix Planning Mode's Socratic questioning approach. **Generated PRDs are automatically validated using universal prompt intelligence** for AI consumption quality.
+
+## What is Clavix Planning Mode?
+
+Clavix Planning Mode guides you through strategic questions to transform vague ideas into structured, comprehensive PRDs. The generated documents are:
+- **Full PRD**: Comprehensive team-facing document
+- **Quick PRD**: AI-optimized 2-3 paragraph version
+
+Both documents are automatically validated for quality (Clarity, Structure, Completeness) to ensure they're ready for AI consumption.
 
 ## Instructions
 
@@ -99,13 +107,13 @@ You are helping the user create a Product Requirements Document (PRD) using Clav
 
 3. **Save both documents** using the file-saving protocol below
 
-4. **CLEAR Framework Validation** (automatic):
-   - After PRD generation, the quick-prd.md is analyzed using CLEAR framework
-   - Assesses AI consumption quality (Conciseness, Logic, Explicitness)
-   - Displays CLEAR scores and improvement suggestions
-   - Only C, L, E components apply (Adaptive & Reflective not applicable to PRDs)
+4. **Quality Validation** (automatic):
+   - After PRD generation, the quick-prd.md is analyzed for AI consumption quality
+   - Assesses Clarity, Structure, and Completeness
+   - Displays quality scores and improvement suggestions
+   - Focus is on making PRDs actionable for AI agents
 
-5. Display file paths, CLEAR validation results, and suggest next steps.
+5. Display file paths, validation results, and suggest next steps.
 
 ## File-Saving Protocol (For AI Agents)
 
@@ -150,7 +158,7 @@ mkdir -p .clavix/outputs/{sanitized-project-name}
 
 ---
 
-*Generated by Clavix /clavix:prd*
+*Generated with Clavix Planning Mode*
 *Generated: {ISO timestamp}*
 ```
 
@@ -169,7 +177,7 @@ mkdir -p .clavix/outputs/{sanitized-project-name}
 
 ---
 
-*Generated by Clavix /clavix:prd*
+*Generated with Clavix Planning Mode*
 *Generated: {ISO timestamp}*
 ```
 
@@ -191,10 +199,11 @@ Files saved:
   • Full PRD: .clavix/outputs/{project-name}/full-prd.md
   • Quick PRD: .clavix/outputs/{project-name}/quick-prd.md
 
-CLEAR Validation Results:
-  [C] Conciseness: {score}/10 - {feedback}
-  [L] Logic: {score}/10 - {feedback}
-  [E] Explicitness: {score}/10 - {feedback}
+Quality Assessment:
+  Clarity: {score}% - {feedback}
+  Structure: {score}% - {feedback}
+  Completeness: {score}% - {feedback}
+  Overall: {score}%
 
 Next steps:
   • Review and edit PRD files if needed
@@ -216,21 +225,21 @@ Next steps:
 - Existing files will be overwritten (user initiated PRD generation)
 - If unsure: Ask user "Project `{name}` already exists. Overwrite PRD files?"
 
-## CLEAR Validation
+## Quality Validation
 
 **What gets validated:**
-- **[C] Concise**: Is the PRD focused and to-the-point for AI agents?
-- **[L] Logical**: Does information flow coherently (context → requirements → constraints)?
-- **[E] Explicit**: Are specifications, formats, and success criteria clear?
+- **Clarity**: Is the PRD clear and unambiguous for AI agents?
+- **Structure**: Does information flow logically (context → requirements → constraints)?
+- **Completeness**: Are all necessary specifications provided?
 
-**Note:** Adaptive (A) and Reflective (R) components are not applicable to PRDs. For prompt-level CLEAR analysis with all 5 components, use `/clavix:deep` instead.
+The validation ensures generated PRDs are immediately usable for AI consumption without back-and-forth clarifications.
 
 ## Workflow Navigation
 
-**You are here:** PRD Generation (Strategic Planning)
+**You are here:** Clavix Planning Mode (Strategic Planning)
 
 **Common workflows:**
-- **Full PRD workflow**: `/clavix:prd` → `/clavix:plan` → `/clavix:implement` → `/clavix:archive`
+- **Full planning workflow**: `/clavix:prd` → `/clavix:plan` → `/clavix:implement` → `/clavix:archive`
 - **From deep mode**: `/clavix:deep` → (strategic scope detected) → `/clavix:prd`
 - **Quick to strategic**: `/clavix:fast` → (realizes complexity) → `/clavix:prd`
 
@@ -244,7 +253,8 @@ Next steps:
 - Ask follow-up questions if answers are too vague
 - Help users think through edge cases
 - Keep the process conversational and supportive
-- Generated PRDs are automatically CLEAR-validated for optimal AI consumption
+- Generated PRDs are automatically validated for optimal AI consumption
+- Clavix Planning Mode is designed for strategic features, not simple prompts
 
 ## Troubleshooting
 
@@ -271,7 +281,7 @@ Next steps:
 - For Q4: Suggest common exclusions based on project type
 - Consider suggesting `/clavix:start` for conversational exploration first
 
-### Issue: CLEAR validation shows low scores after generation
+### Issue: Quality validation shows low scores after generation
 **Cause**: Answers were too vague or incomplete
 **Solution**:
 - Review the generated PRD

package/dist/templates/slash-commands/_canonical/start.md

@@ -3,9 +3,9 @@ name: "Clavix: Start"
 description: Start conversational mode for iterative prompt development
 ---
 
-# Clavix Conversational Mode - CLEAR Framework Enhanced
+# Clavix Conversational Mode
 
-You are starting a Clavix conversational session for iterative prompt and requirements development. **When complete, use `/clavix:summarize` to extract and CLEAR-optimize requirements** (Concise, Logical, Explicit).
+You are starting a Clavix conversational session for iterative prompt and requirements development. **When complete, use `/clavix:summarize` to extract and optimize requirements** using universal prompt intelligence.
 
 ## Instructions
 
@@ -14,7 +14,7 @@ You are starting a Clavix conversational session for iterative prompt and requir
    Let's build something great together! Tell me about what you want to create.
 
    I'll ask clarifying questions as we go, and we can refine the requirements together.
-   When we're done, use /clavix:summarize to extract a CLEAR-optimized prompt from our conversation.
+   When we're done, use /clavix:summarize to extract an optimized prompt from our conversation.
    ```
 
 2. As the user describes their needs:
@@ -61,16 +61,17 @@ You are starting a Clavix conversational session for iterative prompt and requir
    - Offer suggestions when helpful
    - Validate their thinking
 
-5. Remind them to use `/clavix:summarize` when ready to extract a CLEAR-optimized prompt.
+5. Remind them to use `/clavix:summarize` when ready to extract an optimized prompt.
 
-## CLEAR Framework Connection
+## How Summarization Works
 
 After the conversational session, `/clavix:summarize` will:
 - Extract requirements from the conversation
-- Apply CLEAR framework optimization (Concise, Logical, Explicit)
-- Generate both raw extraction and CLEAR-enhanced version
-- Display CLEAR scores and improvements
-- Save `clear-optimized-prompt.md` for optimal AI consumption
+- Apply universal prompt intelligence optimization
+- Analyze intent and assess quality (Clarity, Efficiency, Structure, Completeness, Actionability)
+- Generate both original extraction and optimized version
+- Display quality scores and improvements
+- Save `optimized-prompt.md` for optimal AI consumption
 
 ## Example Flow
 
@@ -89,13 +90,13 @@ After the conversational session, `/clavix:summarize` will:
 **You are here:** Conversational Mode (Iterative Exploration)
 
 **Common workflows:**
-- **Exploration to prompt**: `/clavix:start` → [conversation] → `/clavix:summarize` → CLEAR-optimized prompt
+- **Exploration to prompt**: `/clavix:start` → [conversation] → `/clavix:summarize` → Optimized prompt
 - **Exploration to PRD**: `/clavix:start` → [conversation] → `/clavix:prd` (answer questions with discussed info)
 - **Exploration to planning**: `/clavix:start` → `/clavix:summarize` → `/clavix:plan` → Implement
 
 **Related commands:**
-- `/clavix:summarize` - Extract and CLEAR-optimize conversation (typical next step)
-- `/clavix:prd` - Switch to structured PRD generation
+- `/clavix:summarize` - Extract and optimize conversation (typical next step)
+- `/clavix:prd` - Switch to Clavix Planning Mode for structured PRD generation
 - `/clavix:fast` or `/clavix:deep` - Direct prompt improvement instead of conversation
 
 ## Note