clavix 7.2.2 → 7.2.3

package/dist/templates/skills/improve.md

@@ -156,28 +156,40 @@ All improvements must be labeled with quality dimension tags:
 
 ---
 
-## File-Saving Protocol
+## File-Saving Protocol (REQUIRED - DO NOT SKIP)
 
-### Step 1: Generate ID
+DO NOT output any "saved" message until you have COMPLETED and VERIFIED all save steps.
 
-Format: `{depth}-YYYYMMDD-HHMMSS-{random4}`
-- `std-20240115-143022-a7x2` for standard depth
-- `comp-20240115-143022-b9k4` for comprehensive depth
+This is a BLOCKING checkpoint. You cannot proceed to the final message until saving is verified.
 
-### Step 2: Create Directory
+### What You MUST Do Before Final Output
 
-```bash
-mkdir -p .clavix/outputs/prompts
-```
+| Step | Action | Tool to Use | Verification |
+|------|--------|-------------|--------------|
+| 1 | Create directory with prompt file | **Write tool** (creates parent dirs automatically) | Directory exists |
+| 2 | Generate prompt ID | Format: `{std|comp}-YYYYMMDD-HHMMSS-<random>` | ID is unique |
+| 3 | Write prompt file with frontmatter | **Write tool** | File created |
+| 4 | **VERIFY: Read back file** | **Read tool** | File readable |
+
+**⚠️ CRITICAL: You MUST invoke the Write tool to create the file. Showing the content in your response is NOT enough - the file must actually exist on disk.**
+
+---
+
+### Step 1: Generate Prompt ID
+
+Create a unique identifier using this format:
+- **Standard depth**: `std-YYYYMMDD-HHMMSS-<random>` (e.g., `std-20250117-143022-a3f2`)
+- **Comprehensive depth**: `comp-YYYYMMDD-HHMMSS-<random>` (e.g., `comp-20250117-143022-a3f2`)
 
-### Step 3: Save File
+### Step 2: Write Prompt File (Write Tool)
 
-Path: `.clavix/outputs/prompts/{id}.md`
+**You MUST use the Write tool** to create the prompt file at:
+- **Path**: `.clavix/outputs/prompts/{prompt-id}.md`
 
-Content structure:
-```yaml
+**File content format**:
+```markdown
 ---
-id: {generated-id}
+id: {prompt-id}
 depthUsed: standard|comprehensive
 timestamp: {ISO-8601 timestamp}
 executed: false
@@ -185,10 +197,19 @@ originalPrompt: |
   {original user prompt text}
 ---
 
-# Optimized Prompt
+# Improved Prompt
 
 {The improved prompt content}
 
+## Quality Scores
+- **Clarity**: {percentage}%
+- **Efficiency**: {percentage}%
+- **Structure**: {percentage}%
+- **Completeness**: {percentage}%
+- **Actionability**: {percentage}%
+- **Specificity**: {percentage}%
+- **Overall**: {percentage}% ({rating})
+
 ## Analysis Summary
 
 Intent: {detected intent}
@@ -196,13 +217,24 @@ Quality: {before}% → {after}%
 Patterns Applied: {list of patterns}
 ```
 
-### Step 4: Verify After Write
+### Step 3: Verify File Exists (Read Tool)
+
+After using Write tool to create the file, use the Read tool to verify:
+- Path: `.clavix/outputs/prompts/{prompt-id}.md`
+
+**If Read fails**: ⛔ STOP - Saving failed. Retry Write tool with proper content.
+
+### Step 4: Final Response
 
-**CRITICAL**: Use Read to confirm file exists and has valid content.
+ONLY after verification passes, output:
+
+```
+✅ Prompt saved to: `.clavix/outputs/prompts/{actual-prompt-id}.md`
+
+Ready to implement? Run: /clavix:implement --latest
+```
 
-If verification fails:
-- Retry save once
-- If still fails, display prompt content for manual copy
+**⚠️ DO NOT output the saved message until you have verified the file exists.**
 
 ---
 

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

@@ -274,7 +274,7 @@ Result: Project permanently deleted
 
 ---
 
-## Agent Transparency (v7.2.2)
+## Agent Transparency (v7.2.3)
 
 ### Agent Manual (Universal Protocols)
 {{INCLUDE:agent-protocols/AGENT_MANUAL.md}}

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

@@ -615,7 +615,7 @@ I'll explain what's wrong and what you might need to do:
 
 ---
 
-## Agent Transparency (v7.2.2)
+## Agent Transparency (v7.2.3)
 
 ### Agent Manual (Universal Protocols)
 {{INCLUDE:agent-protocols/AGENT_MANUAL.md}}

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

@@ -524,7 +524,7 @@ Wait for the user to decide what to do next.
 
 ---
 
-## Agent Transparency (v7.2.2)
+## Agent Transparency (v7.2.3)
 
 ### Agent Manual (Universal Protocols)
 {{INCLUDE:agent-protocols/AGENT_MANUAL.md}}

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

@@ -229,7 +229,7 @@ Present the plan and ask:
 
 ---
 
-## Agent Transparency (v7.2.2)
+## Agent Transparency (v7.2.3)
 
 ### Agent Manual (Universal Protocols)
 {{INCLUDE:agent-protocols/AGENT_MANUAL.md}}

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

@@ -354,7 +354,7 @@ The validation ensures generated PRDs are immediately usable for AI consumption
 
 ---
 
-## Agent Transparency (v7.2.2)
+## Agent Transparency (v7.2.3)
 
 ### Agent Manual (Universal Protocols)
 {{INCLUDE:agent-protocols/AGENT_MANUAL.md}}

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

@@ -415,7 +415,7 @@ I'll update the PRD and add this to the refinement history. Confirm?
 
 ---
 
-## Agent Transparency (v7.2.2)
+## Agent Transparency (v7.2.3)
 
 ### Agent Manual (Universal Protocols)
 {{INCLUDE:agent-protocols/AGENT_MANUAL.md}}

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

@@ -447,7 +447,7 @@ consistent with the project's conventions.
 
 ---
 
-## Agent Transparency (v7.2.2)
+## Agent Transparency (v7.2.3)
 
 ### Agent Manual (Universal Protocols)
 {{INCLUDE:agent-protocols/AGENT_MANUAL.md}}

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

@@ -230,7 +230,7 @@ The goal is natural exploration of requirements, not a rigid questionnaire. Foll
 
 ---
 
-## Agent Transparency (v7.2.2)
+## Agent Transparency (v7.2.3)
 
 ### Agent Manual (Universal Protocols)
 {{INCLUDE:agent-protocols/AGENT_MANUAL.md}}

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

@@ -409,7 +409,7 @@ The `/clavix:summarize` command extracts requirements from exploratory conversat
 
 ---
 
-## Agent Transparency (v7.2.2)
+## Agent Transparency (v7.2.3)
 
 ### Agent Manual (Universal Protocols)
 {{INCLUDE:agent-protocols/AGENT_MANUAL.md}}

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

@@ -123,7 +123,7 @@ Implementation: BLOCKED - I'll analyze and report, not modify or fix
 
 ----
 
-## Agent Transparency (v7.2.2)
+## Agent Transparency (v7.2.3)
 
 ### Agent Manual (Universal Protocols)
 {{INCLUDE:agent-protocols/AGENT_MANUAL.md}}

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "clavix",
-  "version": "7.2.2",
+  "version": "7.2.3",
   "description": "Agentic-first prompt workflows. Markdown templates that teach AI agents how to optimize prompts, create PRDs, and manage implementation.\n\nSLASH COMMANDS (in your AI assistant):\n  /clavix:improve    Optimize prompts with auto-depth\n  /clavix:prd        Generate PRD through questions\n  /clavix:plan       Create task breakdown from PRD\n  /clavix:implement  Execute tasks with progress tracking\n  /clavix:start      Begin conversational session\n  /clavix:summarize  Extract requirements from conversation\n  /clavix:refine     Refine existing PRD or prompt\n  /clavix:verify     Verify implementation against requirements\n  /clavix:review     Review teammate PRs with criteria\n  /clavix:archive    Archive completed projects\n\nWorks with Claude Code, Cursor, Windsurf, and 20 AI coding tools.",
   "type": "module",
   "main": "dist/index.js",