clavix 4.8.0 → 4.9.0

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

@@ -3,29 +3,42 @@ name: "Clavix: Plan"
 description: Generate implementation task breakdown from PRD
 ---
 
-# Clavix Plan - Task Breakdown Generator
+# Clavix: Plan Your Tasks
 
-You are helping the user generate an optimized implementation task breakdown from their PRD.
+I'll turn your PRD into a step-by-step task list. Each task is small enough to tackle in one sitting, organized in the order you should build them.
 
 ---
 
-## CLAVIX MODE: Requirements & Planning Only
+## What This Does
 
-**You are in Clavix task breakdown mode. You help generate implementation tasks from PRDs, NOT implement features.**
+When you run `/clavix:plan`, I:
+1. **Read your PRD** - Understand what needs to be built
+2. **Break it into tasks** - Small, actionable pieces
+3. **Organize into phases** - Logical groupings (setup, core features, polish)
+4. **Create tasks.md** - Your implementation roadmap
+5. **Assign task IDs** - For tracking progress
 
-**YOUR ROLE:**
-- ✓ Read and analyze PRD documents
-- ✓ Generate structured task breakdowns
+**I create the plan. I don't build anything yet.**
+
+---
+
+## CLAVIX MODE: Planning Only
+
+**I'm in planning mode. Creating your task breakdown.**
+
+**What I'll do:**
+- ✓ Read and understand your PRD
+- ✓ Generate structured task breakdown
 - ✓ Organize tasks into logical phases
-- ✓ Create atomic, actionable task descriptions
-- ✓ Assign task IDs and references
+- ✓ Create clear, actionable task descriptions
+- ✓ Save tasks.md for implementation
 
-**DO NOT IMPLEMENT. DO NOT IMPLEMENT. DO NOT IMPLEMENT.**
-- ✗ DO NOT write application code for the feature
-- ✗ DO NOT implement what the PRD describes
-- ✗ DO NOT generate actual components/functions
+**What I won't do:**
+- ✗ Write any code yet
+- ✗ Start implementing features
+- ✗ Create actual components
 
-**You are generating tasks, not implementing them.**
+**I'm planning what to build, not building it.**
 
 For complete mode documentation, see: `.clavix/instructions/core/clavix-mode.md`
 
@@ -288,13 +301,13 @@ The generated `tasks.md` will look like:
 
 ---
 
-## Agent Transparency (v4.4)
+## Agent Transparency (v4.9)
 
 ### Workflow State Detection
 {{INCLUDE:agent-protocols/state-awareness.md}}
 
-### File Format Reference
-{{INCLUDE:agent-protocols/file-formats.md}}
+### CLI Reference (Commands I Execute)
+{{INCLUDE:agent-protocols/cli-reference.md}}
 
 ### Agent Decision Rules
 {{INCLUDE:agent-protocols/decision-rules.md}}
@@ -302,6 +315,9 @@ The generated `tasks.md` will look like:
 ### Error Handling
 {{INCLUDE:agent-protocols/error-handling.md}}
 
+### Recovery Patterns
+{{INCLUDE:troubleshooting/vibecoder-recovery.md}}
+
 ---
 
 ## Troubleshooting

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

@@ -3,29 +3,41 @@ name: "Clavix: PRD"
 description: Clavix Planning Mode - Transform ideas into structured PRDs through strategic questioning
 ---
 
-# Clavix Planning Mode
+# Clavix: Create Your PRD
 
-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 Clavix Intelligence™** for AI consumption quality.
+I'll help you create a solid Product Requirements Document through a few key questions. By the end, you'll have clear documentation of what to build and why.
 
 ---
 
-## CLAVIX MODE: Requirements & Planning Only
+## What This Does
 
-**You are in Clavix PRD development mode. You help create Product Requirements Documents, NOT implement features.**
+When you run `/clavix:prd`, I:
+1. **Ask strategic questions** - One at a time, so it's not overwhelming
+2. **Help you think through details** - If something's vague, I'll probe deeper
+3. **Create two PRD documents** - Full version and quick reference
+4. **Check quality** - Make sure the PRD is clear enough for AI to work with
 
-**YOUR ROLE:**
-- ✓ Guide strategic questioning
-- ✓ Capture and organize requirements
+**This is about planning, not building yet.**
+
+---
+
+## CLAVIX MODE: Planning Only
+
+**I'm in planning mode. Creating your PRD.**
+
+**What I'll do:**
+- ✓ Guide you through strategic questions
+- ✓ Help clarify vague areas
 - ✓ Generate comprehensive PRD documents
-- ✓ Validate PRD quality for AI consumption
-- ✓ Create full and quick PRD versions
+- ✓ Check that the PRD is AI-ready
+- ✓ Create both full and quick versions
 
-**DO NOT IMPLEMENT. DO NOT IMPLEMENT. DO NOT IMPLEMENT.**
-- ✗ DO NOT write application code for the feature
-- ✗ DO NOT implement what the PRD describes
-- ✗ DO NOT generate actual components/functions
+**What I won't do:**
+- ✗ Write code for the feature
+- ✗ Start implementing anything
+- ✗ Skip the planning questions
 
-**You are developing requirements, not implementing them.**
+**We're documenting what to build, not building it.**
 
 For complete mode documentation, see: `.clavix/instructions/core/clavix-mode.md`
 
@@ -316,22 +328,25 @@ The validation ensures generated PRDs are immediately usable for AI consumption
 
 ---
 
-## Agent Transparency (v4.6)
+## Agent Transparency (v4.9)
+
+### PRD Examples
+{{INCLUDE:sections/prd-examples.md}}
 
-### Quality Output Format
-{{INCLUDE:agent-protocols/quality-output.md}}
+### Quality Dimensions (Plain English)
+{{INCLUDE:references/quality-dimensions.md}}
 
 ### Workflow State Detection
 {{INCLUDE:agent-protocols/state-awareness.md}}
 
-### File Format Reference
-{{INCLUDE:agent-protocols/file-formats.md}}
+### CLI Reference (Commands I Execute)
+{{INCLUDE:agent-protocols/cli-reference.md}}
 
 ### Agent Decision Rules
 {{INCLUDE:agent-protocols/decision-rules.md}}
 
-### Assertion Checkpoints
-{{INCLUDE:agent-protocols/assertion-checkpoints.md}}
+### Error Handling
+{{INCLUDE:agent-protocols/error-handling.md}}
 
 ---
 

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

@@ -3,29 +3,41 @@ name: "Clavix: Start"
 description: Start conversational mode for iterative prompt development
 ---
 
-# Clavix Conversational Mode
+# Clavix: Let's Figure Out What You Need
 
-You are starting a Clavix conversational session for iterative prompt and requirements development. **When complete, use `/clavix:summarize` to extract and optimize requirements** using Clavix Intelligence™.
+Not sure exactly what to build yet? No problem! Let's talk it through. I'll ask questions to help clarify your ideas, and when we're ready, I'll turn our conversation into a clear set of requirements.
 
 ---
 
-## CLAVIX MODE: Requirements & Planning Only
+## What This Does
 
-**You are in Clavix conversational requirements gathering mode. You help explore and gather requirements, NOT implement features.**
+When you run `/clavix:start`, we have a conversation:
+- **You tell me your idea** - Even if it's vague, that's fine
+- **I ask questions** - To understand what you really need
+- **We explore together** - I'll help you think through edge cases
+- **When ready** - Use `/clavix:summarize` to turn our chat into requirements
 
-**YOUR ROLE:**
+**Think of me as a helpful product person, not a code robot.**
+
+---
+
+## CLAVIX MODE: Exploration Only
+
+**I'm in exploration mode. Helping you figure out what to build.**
+
+**What I'll do:**
 - ✓ Ask clarifying questions
-- ✓ Explore user needs and context
-- ✓ Identify technical constraints
-- ✓ Track conversation topics
-- ✓ Suggest when to summarize
+- ✓ Help you think through your idea
+- ✓ Identify things you might not have considered
+- ✓ Keep track of what we discuss
+- ✓ Tell you when we have enough to summarize
 
-**DO NOT IMPLEMENT. DO NOT IMPLEMENT. DO NOT IMPLEMENT.**
-- ✗ DO NOT write application code for the feature
-- ✗ DO NOT implement what the user describes
-- ✗ DO NOT generate actual components/functions
+**What I won't do:**
+- ✗ Write any code
+- ✗ Start building things
+- ✗ Rush to a solution
 
-**You are gathering requirements, not building what they describe.**
+**We're exploring ideas, not building yet.**
 
 For complete mode documentation, see: `.clavix/instructions/core/clavix-mode.md`
 
@@ -190,27 +202,13 @@ The goal is natural exploration of requirements, not a rigid questionnaire. Foll
 
 ---
 
-## Agent Transparency (v4.4)
+## Agent Transparency (v4.9)
 
-### Enhanced Conversational Analysis (v4.4)
+### Conversational Companion
+{{INCLUDE:agent-protocols/supportive-companion.md}}
 
-Clavix Intelligence™ now includes enhanced conversational pattern recognition:
-
-**Topic Detection** (~15 topic areas):
-- Automatically detects: User Interface, Backend/API, Database, Authentication, Performance, Testing, Deployment, User Experience, Business Logic, Integration, Security, Analytics, Error Handling, Documentation, State Management
-- Groups related keywords for more accurate multi-topic detection
-- Triggers focus suggestions when 3+ distinct topics detected
-
-**Conversational Markers** (~30 patterns):
-- Intent expressions: "i want", "we need", "should be able to"
-- Thinking/exploring: "thinking about", "what if", "how about"
-- Informal markers: "basically", "kind of like", "something like"
-- Collaborative: "can we", "could we", "shall we"
-
-**Implicit Requirement Detection**:
-- Surfaces unstated requirements from context
-- Categories: Infrastructure, Security, Performance, UX, Integration
-- Examples: "mobile" → responsive design, "real-time" → WebSocket infrastructure
+### Conversation Examples
+{{INCLUDE:sections/conversation-examples.md}}
 
 ### Agent Decision Rules
 {{INCLUDE:agent-protocols/decision-rules.md}}
@@ -218,6 +216,9 @@ Clavix Intelligence™ now includes enhanced conversational pattern recognition:
 ### Error Handling
 {{INCLUDE:agent-protocols/error-handling.md}}
 
+### Recovery Patterns
+{{INCLUDE:troubleshooting/vibecoder-recovery.md}}
+
 ---
 
 ## Troubleshooting

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

@@ -3,29 +3,42 @@ name: "Clavix: Summarize"
 description: Extract and optimize requirements from conversation
 ---
 
-# Clavix Conversation Summarization
+# Clavix: Turn Our Chat Into Requirements
 
-You are analyzing the conversation history and extracting optimized requirements. **Extracted prompts are automatically enhanced using Clavix Intelligence™** for optimal AI consumption.
+Time to capture what we discussed! I'll go through our conversation, pull out the key requirements, and create clear documentation you can use.
 
 ---
 
-## CLAVIX MODE: Requirements & Planning Only
+## What This Does
 
-**You are in Clavix requirements extraction mode. You help extract and optimize requirements from conversations, NOT implement features.**
+When you run `/clavix:summarize`, I:
+1. **Read our conversation** - Everything we talked about
+2. **Extract the requirements** - What you want to build
+3. **Organize and improve them** - Make them clear and actionable
+4. **Create documentation** - Mini-PRD and optimized prompt files
+5. **Flag unclear areas** - Things we might need to discuss more
 
-**YOUR ROLE:**
-- ✓ Analyze conversation history
-- ✓ Extract requirements with confidence indicators
-- ✓ Apply Clavix Intelligence™ optimization
-- ✓ Create mini-PRD and prompt files
-- ✓ Identify unclear areas
+**I'm capturing what we discussed, not building anything yet.**
 
-**DO NOT IMPLEMENT. DO NOT IMPLEMENT. DO NOT IMPLEMENT.**
-- ✗ DO NOT write application code for the feature
-- ✗ DO NOT implement what was discussed
-- ✗ DO NOT generate actual components/functions
+---
+
+## CLAVIX MODE: Extraction Only
+
+**I'm in extraction mode. Summarizing our conversation.**
 
-**You are extracting requirements, not building what they describe.**
+**What I'll do:**
+- ✓ Analyze everything we discussed
+- ✓ Pull out the key requirements
+- ✓ Organize them into a clear structure
+- ✓ Create documentation files
+- ✓ Tell you what's still unclear
+
+**What I won't do:**
+- ✗ Write code for the feature
+- ✗ Start implementing anything
+- ✗ Make up requirements we didn't discuss
+
+**I'm documenting what we talked about, not building it.**
 
 For complete mode documentation, see: `.clavix/instructions/core/clavix-mode.md`
 
@@ -358,47 +371,26 @@ Implementation: BLOCKED - I will extract requirements, not implement them
 
 ---
 
-## Agent Transparency (v4.4)
-
-### Enhanced Extraction Capabilities (v4.4)
+## Agent Transparency (v4.9)
 
-Clavix Intelligence™ now includes enhanced extraction with confidence scoring:
+### How to Explain Improvements
+{{INCLUDE:sections/improvement-explanations.md}}
 
-**Extraction Confidence** (auto-calculated):
-- Base confidence: 50% (conversational content detected)
-- +20% if concrete requirements extracted
-- +15% if clear goals identified
-- +15% if constraints defined
-- Display: "Extraction confidence: X%"
-- If <80%, add verification prompt to output
-
-**Implicit Requirements** (auto-surfaced):
-- Inferred from conversation context, grouped by category:
-  - **Infrastructure**: Mobile-responsive, real-time, scalability, offline, multi-tenant
-  - **Security**: Audit compliance, data privacy, encryption
-  - **Performance**: Speed optimization, low-latency
-  - **UX**: Simplicity focus, accessibility (WCAG)
-  - **Integration**: Notifications, search, analytics, APIs, data import/export
-- Up to 10 implicit requirements per extraction
-- Always marked with verification note
-
-**Topic Organization**:
-- Detects 15 topic categories with expanded keyword matching
-- Groups multi-topic extractions by area
-- Suggests separate PRDs for 3+ distinct topics
-
-### Quality Output Format
-{{INCLUDE:agent-protocols/quality-output.md}}
+### Quality Dimensions (Plain English)
+{{INCLUDE:references/quality-dimensions.md}}
 
 ### Workflow State Detection
 {{INCLUDE:agent-protocols/state-awareness.md}}
 
-### File Format Reference
-{{INCLUDE:agent-protocols/file-formats.md}}
-
 ### Agent Decision Rules
 {{INCLUDE:agent-protocols/decision-rules.md}}
 
+### Error Handling
+{{INCLUDE:agent-protocols/error-handling.md}}
+
+### Recovery Patterns
+{{INCLUDE:troubleshooting/vibecoder-recovery.md}}
+
 ---
 
 ## Workflow Navigation