clavix 2.3.0 → 2.4.0

package/dist/templates/slash-commands/gemini/plan.toml

@@ -1,170 +0,0 @@
-description = "Generate implementation task breakdown from PRD"
-prompt = """
-
-# Clavix Plan - Task Breakdown Generator
-
-You are helping the user generate a CLEAR-optimized implementation task breakdown from their PRD.
-
-## Instructions
-
-### Part A: Procedural Steps (CLI Commands)
-
-1. **Locate the PRD outputs**:
-   - Look for the most recent artifacts in `.clavix/outputs/[project-name]/`
-   - Accepted sources: `full-prd.md`, `quick-prd.md`, `mini-prd.md`, or `optimized-prompt.md`
-   - **If not found**: Error inline - "No PRD found in `.clavix/outputs/`. Use `/clavix:prd` or `/clavix:summarize` first."
-
-2. **Run the plan command**:
-   ```bash
-   clavix plan
-   ```
-
-   Or specify a project:
-   ```bash
-   clavix plan --project project-name
-   ```
-
-   Or generate tasks directly from a saved session (auto-creates mini-prd.md):
-   ```bash
-   clavix plan --session SESSION_ID
-   ```
-
-   The CLI will prompt you to pick a project when multiple outputs are available.
-
-### Part B: Behavioral Guidance (Task Breakdown Strategy)
-
-3. **How to structure tasks** (CLEAR-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")
-
-   **Atomic Task Guidelines:**
-   - **Ideal size**: Completable in 15-60 minutes
-   - **Too large**: "Implement user authentication" → Break into registration, login, logout, password reset
-   - **Too small**: "Import React" → Combine with "Setup component structure"
-   - **Dependencies**: If Task B needs Task A, ensure A comes first
-
-   **Phase Organization:**
-   - Group related tasks into phases (Setup, Core Features, Testing, Polish)
-   - Each phase should be independently deployable when possible
-   - Critical path first (must-haves before nice-to-haves)
-
-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
-   - Each task includes:
-     - Checkbox `- [ ]` for tracking
-     - Clear deliverable description
-     - Optional reference to PRD section `(ref: PRD Section)`
-   - **You can edit tasks.md** before implementing:
-     - Add/remove tasks
-     - Adjust granularity
-     - Reorder for better flow
-     - Add notes or sub-tasks
-
-5. **CLEAR Task 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)"
-
-6. **Next steps**:
-   - Review and edit `tasks.md` if needed
-   - Then run `/clavix:implement` to start implementation
-
-## Task Format
-
-The generated `tasks.md` will look like:
-
-```markdown
-# Implementation Tasks
-
-**Project**: [Project Name]
-**Generated**: [Timestamp]
-
-
-## Phase 1: Feature Name
-- [ ] Task 1 description (ref: PRD Section)
-- [ ] Task 2 description
-- [ ] Task 3 description
-
-## Phase 2: Another Feature
-- [ ] Task 4 description
-- [ ] Task 5 description
-
-
-*Generated by Clavix /clavix:plan*
-```
-
-## Workflow Navigation
-
-**You are here:** Plan (Task Breakdown)
-
-**Common workflows:**
-- **PRD workflow**: `/clavix:prd` → `/clavix:plan` → `/clavix:implement` → `/clavix:archive`
-- **Conversation workflow**: `/clavix:summarize` → `/clavix:plan` → `/clavix:implement` → `/clavix:archive`
-- **Standalone**: [Existing PRD] → `/clavix:plan` → Review tasks.md → `/clavix:implement`
-
-**Related commands:**
-- `/clavix:prd` - Generate PRD (typical previous step)
-- `/clavix:summarize` - Extract mini-PRD from conversation (alternative previous step)
-- `/clavix:implement` - Execute generated tasks (next step)
-
-## Tips
-
-- Tasks are automatically optimized using CLEAR framework
-- 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`
-- You can manually edit tasks.md before implementing
-- Use `--overwrite` flag to regenerate if needed
-
-## Troubleshooting
-
-### Issue: No PRD found in `.clavix/outputs/`
-**Cause**: User hasn't generated a PRD yet
-**Solution** (inline - already in template):
-- Show error: "No PRD found in `.clavix/outputs/`"
-- Suggest: "Use `/clavix:prd` or `/clavix:summarize` to generate one first"
-- Do not proceed with plan generation
-
-### Issue: Generated tasks are too granular (100+ tasks)
-**Cause**: Over-decomposition or large project scope
-**Solution**:
-- Group related micro-tasks into larger atomic tasks
-- Each task should be 15-60 minutes, not 5 minutes
-- Combine setup/configuration tasks
-- Suggest breaking project into multiple PRDs if truly massive
-
-### Issue: Generated tasks are too high-level (only 3-4 tasks)
-**Cause**: PRD was too vague or task breakdown too coarse
-**Solution**:
-- Review PRD - if vague, regenerate with more detail
-- Break each high-level task into 3-5 concrete sub-tasks
-- Each task should have a clear, testable deliverable
-
-### Issue: Tasks don't follow logical dependency order
-**Cause**: Generator didn't detect dependencies correctly
-**Solution**:
-- Manually reorder in tasks.md (database before API, API before UI)
-- Follow CLEAR [L] Logic principle: ensure sequential coherence
-- Group by technical layers or feature completion
-
-### Issue: Tasks conflict with PRD or duplicate work
-**Cause**: Misinterpretation of PRD or redundant task generation
-**Solution**:
-- Review PRD and tasks side-by-side
-- Remove duplicate tasks
-- Align tasks with PRD requirements
-- Use `--overwrite` to regenerate after PRD clarification
-
-### Issue: `tasks.md` already exists, unsure if should regenerate
-**Cause**: Previous plan exists for this PRD
-**Solution**:
-- Check if tasks.md has progress (any [x] checkboxes)
-- If no progress: Safe to use `--overwrite`
-- If progress exists: Review carefully before overwriting
-- Consider manual edits instead of full regeneration
-"""

package/dist/templates/slash-commands/gemini/prd.toml

@@ -1,177 +0,0 @@
-description = "CLEAR-validated PRD generation through Socratic questioning"
-prompt = """
-
-# Clavix PRD Generation - CLEAR Framework Validated
-
-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.
-
-## Instructions
-
-1. Guide the user through these strategic questions, **one at a time** with validation:
-
-   **Question 1**: What are we building and why? (Problem + goal in 2-3 sentences)
-
-   - **Validation**: Must have both problem AND goal stated clearly
-   - **If vague/short** (e.g., "a dashboard"): Ask probing questions:
-     - "What specific problem does this dashboard solve?"
-     - "Who will use this and what decisions will they make with it?"
-     - "What happens if this doesn't exist?"
-   - **If "I don't know"**: Ask:
-     - "What triggered the need for this?"
-     - "Can you describe the current pain point or opportunity?"
-   - **Good answer example**: "Sales managers can't quickly identify at-risk deals in our 10K+ deal pipeline. Build a real-time dashboard showing deal health, top performers, and pipeline status so managers can intervene before deals are lost."
-
-   **Question 2**: What are the must-have core features? (List 3-5 critical features)
-
-   - **Validation**: At least 2 concrete features provided
-   - **If vague** (e.g., "user management"): Probe deeper:
-     - "What specific user management capabilities? (registration, roles, permissions, profile management?)"
-     - "Which feature would you build first if you could only build one?"
-   - **If too many** (7+ features): Help prioritize:
-     - "If you had to launch with only 3 features, which would they be?"
-     - "Which features are launch-blockers vs nice-to-have?"
-   - **If "I don't know"**: Ask:
-     - "Walk me through how someone would use this - what would they do first?"
-     - "What's the core value this provides?"
-
-   **Question 3**: Tech stack and requirements? (Technologies, integrations, constraints)
-
-   - **Optional**: Can skip if extending existing project
-   - **If vague** (e.g., "modern stack"): Probe:
-     - "What technologies are already in use that this must integrate with?"
-     - "Any specific frameworks or languages your team prefers?"
-     - "Are there performance requirements (load time, concurrent users)?"
-   - **If "I don't know"**: Suggest common stacks based on project type or skip
-
-   **Question 4**: What is explicitly OUT of scope? (What are we NOT building?)
-
-   - **Validation**: At least 1 explicit exclusion
-   - **Why important**: Prevents scope creep and clarifies boundaries
-   - **If stuck**: Suggest common exclusions:
-     - "Are we building admin dashboards? Mobile apps? API integrations?"
-     - "Are we handling payments? User authentication? Email notifications?"
-   - **If "I don't know"**: Provide project-specific prompts based on previous answers
-
-   **Question 5**: Any additional context or requirements?
-
-   - **Optional**: Press Enter to skip
-   - **Helpful areas**: Compliance needs, accessibility, localization, deadlines, team constraints
-
-2. **Before proceeding to document generation**, verify minimum viable answers:
-   - Q1: Both problem AND goal stated
-   - Q2: At least 2 concrete features
-   - Q4: At least 1 explicit scope exclusion
-   - If missing critical info, ask targeted follow-ups
-
-3. After collecting and validating all answers, generate TWO documents:
-
-   **Full PRD** (comprehensive):
-   ```markdown
-   # Product Requirements Document: [Project Name]
-
-   ## Problem & Goal
-   [User's answer to Q1]
-
-   ## Requirements
-   ### Must-Have Features
-   [User's answer to Q2, expanded with details]
-
-   ### Technical Requirements
-   [User's answer to Q3, detailed]
-
-   ## Out of Scope
-   [User's answer to Q4]
-
-   ## Additional Context
-   [User's answer to Q5 if provided]
-   ```
-
-   **Quick PRD** (2-3 paragraphs, AI-optimized):
-   ```markdown
-   [Concise summary combining problem, goal, and must-have features from Q1+Q2]
-
-   [Technical requirements and constraints from Q3]
-
-   [Out of scope and additional context from Q4+Q5]
-   ```
-
-3. Save both documents to `.clavix/outputs/[project-name]/`
-
-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)
-
-5. Display file paths, CLEAR validation results, and suggest next steps.
-
-## CLEAR 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?
-
-**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.
-
-## Workflow Navigation
-
-**You are here:** PRD Generation (Strategic Planning)
-
-**Common workflows:**
-- **Full PRD 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`
-
-**Related commands:**
-- `/clavix:plan` - Generate task breakdown from PRD (next step)
-- `/clavix:implement` - Execute tasks (after plan)
-- `/clavix:summarize` - Alternative: Extract PRD from conversation instead of Q&A
-
-## Tips
-
-- 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
-
-## Troubleshooting
-
-### Issue: User's answers to Q1 are too vague ("make an app")
-**Cause**: User hasn't thought through the problem/goal deeply enough
-**Solution** (inline):
-- Stop and ask probing questions before proceeding
-- "What specific problem does this app solve?"
-- "Who will use this and what pain point does it address?"
-- Don't proceed until both problem AND goal are clear
-
-### Issue: User lists 10+ features in Q2
-**Cause**: Unclear priorities or scope creep
-**Solution** (inline):
-- Help prioritize: "If you could only launch with 3 features, which would they be?"
-- Separate must-have from nice-to-have
-- Document extras in "Additional Context" or "Out of scope"
-
-### Issue: User says "I don't know" to critical questions
-**Cause**: Genuine uncertainty or needs exploration
-**Solution**:
-- For Q1: Ask about what triggered the need, current pain points
-- For Q2: Walk through user journey step-by-step
-- 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
-**Cause**: Answers were too vague or incomplete
-**Solution**:
-- Review the generated PRD
-- Identify specific gaps (missing context, vague requirements)
-- Ask targeted follow-up questions
-- Regenerate PRD with enhanced answers
-
-### Issue: Generated PRD doesn't match user's vision
-**Cause**: Miscommunication during Q&A or assumptions made
-**Solution**:
-- Review each section with user
-- Ask "What's missing or inaccurate?"
-- Update PRD manually or regenerate with corrected answers
-"""

package/dist/templates/slash-commands/gemini/start.toml

@@ -1,141 +0,0 @@
-description = "Start conversational mode for iterative prompt development"
-prompt = """
-
-# Clavix Conversational Mode - CLEAR Framework Enhanced
-
-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).
-
-## Instructions
-
-1. Begin with a friendly introduction:
-   ```
-   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.
-   ```
-
-2. As the user describes their needs:
-   - Ask clarifying questions about unclear points
-   - Probe for technical constraints
-   - Explore edge cases and requirements
-   - Help them think through user needs
-   - Identify potential challenges
-
-3. **Track conversation topics and manage complexity**:
-
-   **Key points to track:**
-   - Problem statement
-   - Target users
-   - Core features
-   - Technical requirements
-   - Success criteria
-   - Constraints and scope
-
-   **Multi-topic detection** (track distinct topics being discussed):
-   - Consider topics distinct if they address different problems/features/user needs
-   - Examples: "dashboard for sales" + "API for integrations" + "mobile app" = 3 topics
-
-   **When 3+ distinct topics detected**:
-   Auto-suggest focusing: "I notice we're discussing multiple distinct areas: [Topic A: summary], [Topic B: summary], and [Topic C: summary]. To ensure we develop clear requirements for each, would you like to:
-   - **Focus on one** - Pick the most important topic to explore thoroughly first
-   - **Continue multi-topic** - We'll track all of them, but the resulting prompt may need refinement
-   - **Create separate sessions** - Start fresh for each topic with dedicated focus"
-
-   **Complexity indicators** (suggest wrapping up/summarizing):
-   - Conversation > 15 exchanges
-   - Requirements for 5+ major features discussed
-   - Multiple technology stacks mentioned
-   - Significant scope changes or pivots occurred
-
-   When complexity threshold reached: "We've covered substantial ground. Would you like to:
-   - Continue exploring
-   - Use `/clavix:summarize` to extract what we have so far
-   - Switch to `/clavix:prd` for more structured planning"
-
-4. Be conversational and supportive:
-   - Don't interrogate - have a natural discussion
-   - Build on their ideas
-   - Offer suggestions when helpful
-   - Validate their thinking
-
-5. Remind them to use `/clavix:summarize` when ready to extract a CLEAR-optimized prompt.
-
-## CLEAR Framework Connection
-
-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
-
-## Example Flow
-
-**User**: "I need a dashboard for analytics"
-
-**Assistant**: "Great! What kind of analytics are we talking about? Is this for business metrics, user behavior, system performance, or something else?"
-
-**User**: "Business metrics - sales, revenue, customer growth"
-
-**Assistant**: "Perfect. Who will be using this dashboard? Executives, sales team, analysts? Their needs might be quite different."
-
-[Continue conversational refinement...]
-
-## Workflow Navigation
-
-**You are here:** Conversational Mode (Iterative Exploration)
-
-**Common workflows:**
-- **Exploration to prompt**: `/clavix:start` → [conversation] → `/clavix:summarize` → CLEAR-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:fast` or `/clavix:deep` - Direct prompt improvement instead of conversation
-
-## Note
-
-The goal is natural exploration of requirements, not a rigid questionnaire. Follow the user's lead while gently guiding toward clarity.
-
-## Troubleshooting
-
-### Issue: Conversation going in circles without progress
-**Cause**: Unclear focus or too many topics being explored
-**Solution** (inline):
-- Pause and summarize: "So far we've discussed [A], [B], [C]. Which should we focus on?"
-- Suggest focusing on one topic at a time
-- Or suggest `/clavix:summarize` to extract what's been discussed
-
-### Issue: User provides very high-level descriptions ("build something cool")
-**Cause**: User hasn't crystallized their ideas yet
-**Solution**:
-- Ask open-ended questions: "What made you think of this?"
-- Probe for use cases: "Walk me through how someone would use this"
-- Be patient - this mode is for exploration
-- Multiple exchanges are normal and expected
-
-### Issue: Detecting 3+ distinct topics but user keeps adding more
-**Cause**: Brainstorming mode or unclear priorities
-**Solution** (inline):
-- Interrupt after 3+ topics detected (per multi-topic protocol)
-- Strongly suggest focusing on one topic
-- Alternative: Document all topics and help prioritize
-- Consider suggesting `/clavix:prd` for each topic separately
-
-### Issue: Conversation exceeds 20 exchanges without clarity
-**Cause**: Too exploratory without convergence
-**Solution**:
-- Suggest wrapping up: "We've covered a lot. Ready to `/clavix:summarize`?"
-- Or pivot to `/clavix:prd` for structured planning
-- Or focus conversation: "Let's nail down the core problem first"
-
-### Issue: User wants to switch topics mid-conversation
-**Cause**: New idea occurred or original topic wasn't right
-**Solution**:
-- Note what was discussed so far
-- Ask: "Should we continue with [original topic] or switch to [new topic]?"
-- Suggest summarizing current topic first before switching
-"""

package/dist/templates/slash-commands/gemini/summarize.toml

@@ -1,178 +0,0 @@
-description = "Extract and CLEAR-optimize requirements from conversation"
-prompt = """
-
-# Clavix Conversation Summarization - CLEAR Framework Enhanced
-
-You are analyzing the conversation history and extracting optimized requirements. **Extracted prompts are automatically enhanced using the CLEAR Framework** (Concise, Logical, Explicit) for optimal AI consumption.
-
-## Instructions
-
-1. **Pre-Extraction Validation** - Check conversation completeness:
-
-   **Minimum viable requirements:**
-   - **Objective/Goal**: Is there a clear problem or goal stated?
-   - **Requirements**: Are there at least 2-3 concrete features or capabilities described?
-   - **Context**: Is there enough context about who/what/why?
-
-   **If missing critical elements:**
-   - Identify what's missing (e.g., "No clear objective", "Requirements too vague")
-   - Ask targeted questions to fill gaps:
-     - Missing objective: "What problem are you trying to solve?"
-     - Vague requirements: "Can you describe 2-3 specific things this should do?"
-     - No context: "Who will use this and in what situation?"
-   - **DO NOT** proceed to extraction until minimum viable requirements met
-
-   **Confidence indicators** (annotate extracted elements):
-   - **[HIGH]**: Explicitly stated multiple times with details
-   - **[MEDIUM]**: Mentioned once or inferred from context
-   - **[LOW]**: Assumed based on limited information
-
-2. Review the entire conversation and identify (with confidence indicators):
-   - **Problem/Goal** [confidence]: What is the user trying to build or solve?
-   - **Key Requirements** [confidence per requirement]: What features and functionality were discussed?
-   - **Technical Constraints** [confidence]: Any technologies, integrations, or performance needs?
-   - **User Needs** [confidence]: Who are the end users and what do they need?
-   - **Success Criteria** [confidence]: How will success be measured?
-   - **Context** [confidence]: Any important background or constraints?
-
-3. Generate TWO outputs:
-
-   **Mini-PRD** (structured document):
-   ```markdown
-   # Requirements: [Project Name]
-
-   ## Objective
-   [Clear, specific goal extracted from conversation]
-
-   ## Key Requirements
-   - [Requirement 1]
-   - [Requirement 2]
-   - [Requirement 3]
-
-   ## Technical Constraints
-   - [Constraint 1]
-   - [Constraint 2]
-
-   ## Success Criteria
-   - [Criterion 1]
-   - [Criterion 2]
-
-   ## Context
-   [Important background information]
-   ```
-
-   **Optimized Prompt** (AI-ready, 2-3 paragraphs):
-   ```
-   [Dense paragraph combining objective, key features, and user needs]
-
-   [Technical requirements and constraints]
-
-   [Success criteria and any important context]
-   ```
-
-3. **CLEAR Framework Optimization** (automatic with labeled improvements):
-   - After extracting the optimized prompt, analyze using CLEAR framework
-   - Apply Conciseness, Logic, and Explicitness enhancements
-   - **Label all improvements** with CLEAR component tags:
-     - **[C]**: "Removed 12 conversational words, reduced from 45 to 28 words"
-     - **[L]**: "Restructured flow: context → requirements → constraints → success criteria"
-     - **[E]**: "Added explicit output format (React component), persona (senior dev), success metrics (load time < 2s)"
-   - Display both raw extraction and CLEAR-enhanced version
-   - Show CLEAR scores (before/after) and labeled improvements
-   - Save both versions:
-     - `optimized-prompt.md` (raw extraction)
-     - `clear-optimized-prompt.md` (CLEAR-enhanced with improvement notes)
-
-4. Highlight key insights discovered during the conversation.
-
-5. Suggest saving to `.clavix/outputs/[session-name]/`
-
-6. If anything is still unclear or missing, point it out and suggest areas for further discussion.
-
-## CLEAR Enhancement
-
-**What gets optimized:**
-- **[C] Concise**: Remove any verbosity from extracted requirements
-- **[L] Logical**: Ensure coherent flow (context → requirements → constraints → output)
-- **[E] Explicit**: Add missing specifications, formats, success criteria
-
-**Output files:**
-- `optimized-prompt.md` - Raw extraction from conversation
-- `clear-optimized-prompt.md` - CLEAR-enhanced version (recommended for AI agents)
-
-## Quality Checks
-
-- Clear objective stated
-- Specific, actionable requirements
-- Technical constraints identified
-- Success criteria defined
-- User needs considered
-- CLEAR framework applied for AI consumption
-
-## Workflow Navigation
-
-**You are here:** Summarize (Conversation Extraction)
-
-**Common workflows:**
-- **Standard flow**: `/clavix:start` → [conversation] → `/clavix:summarize` → Use CLEAR-optimized prompt
-- **To implementation**: `/clavix:summarize` → `/clavix:plan` → `/clavix:implement` → `/clavix:archive`
-- **Standalone use**: [Any conversation] → `/clavix:summarize` → Extract and optimize
-
-**Related commands:**
-- `/clavix:start` - Begin conversational exploration (typical previous step)
-- `/clavix:plan` - Generate tasks from extracted mini-PRD (next step)
-- `/clavix:fast` or `/clavix:deep` - Further optimize the extracted prompt
-
-## Example
-
-From conversation about "analytics dashboard for sales team"...
-
-**Optimized Prompt**:
-```
-Build a real-time sales analytics dashboard for the sales team showing revenue trends, top performers, pipeline status, and conversion rates. The dashboard should update live as deals progress, support filtering by date range/region/rep, and display key metrics prominently. Users need to quickly identify at-risk deals and celebrate wins.
-
-Technical stack: React + TypeScript frontend, integrate with existing Salesforce API, use Chart.js for visualizations, responsive design for mobile access. Must handle 10K+ deals without performance degradation.
-
-Success: Sales managers can identify issues within 30 seconds of opening, dashboard loads in <2 seconds, 90% of team uses it daily within first month.
-```
-
-## Troubleshooting
-
-### Issue: Pre-extraction validation fails (missing objective/requirements)
-**Cause**: Conversation didn't cover enough detail
-**Solution** (inline - DO NOT extract):
-- List what's missing specifically
-- Ask targeted questions to fill gaps
-- Only proceed to extraction after minimum viable requirements met
-- Show confidence indicators for what WAS discussed
-
-### Issue: Conversation covered multiple unrelated topics
-**Cause**: Exploratory discussion without focus
-**Solution**:
-- Ask user which topic to extract/focus on
-- Or extract all topics separately into different sections
-- Mark multi-topic extraction with [MULTI-TOPIC] indicator
-- Suggest breaking into separate PRDs for each topic
-
-### Issue: CLEAR optimization doesn't significantly improve extracted prompt
-**Cause**: Conversation was already well-structured and detailed
-**Solution**:
-- Minor improvements are normal for good conversations
-- Show CLEAR scores (should be high: >80%)
-- Still provide both versions but note that original extraction was already CLEAR
-
-### Issue: Low confidence indicators across all extracted elements
-**Cause**: Conversation was too vague or high-level
-**Solution** (inline):
-- Don't just extract with [LOW] markers everywhere
-- Ask follow-up questions to increase confidence
-- Or inform user: "Our conversation was exploratory. I recommend `/clavix:start` to go deeper, or `/clavix:prd` for structured planning"
-
-### Issue: Extracted prompt contradicts earlier conversation
-**Cause**: Requirements evolved during conversation
-**Solution**:
-- Use latest/final version of requirements
-- Note that requirements evolved
-- Ask user to confirm which version is correct
-- Suggest starting fresh with `/clavix:prd` if major contradictions exist
-"""