clavix 5.7.0 → 5.7.1
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/dist/templates/slash-commands/_canonical/archive.md +1 -1
- package/dist/templates/slash-commands/_canonical/implement.md +1 -1
- package/dist/templates/slash-commands/_canonical/improve.md +19 -1
- package/dist/templates/slash-commands/_canonical/plan.md +1 -1
- package/dist/templates/slash-commands/_canonical/prd.md +1 -1
- package/dist/templates/slash-commands/_canonical/refine.md +206 -350
- package/dist/templates/slash-commands/_canonical/start.md +1 -1
- package/dist/templates/slash-commands/_canonical/summarize.md +1 -1
- package/dist/templates/slash-commands/_canonical/verify.md +269 -320
- package/package.json +3 -2
|
@@ -5,6 +5,24 @@ description: Analyze and improve prompts with auto-detected depth
|
|
|
5
5
|
|
|
6
6
|
# Clavix: Improve Your Prompt
|
|
7
7
|
|
|
8
|
+
---
|
|
9
|
+
|
|
10
|
+
## What This Does
|
|
11
|
+
|
|
12
|
+
When you run `/clavix:improve`, I:
|
|
13
|
+
1. **Analyze your prompt quality** - 6-dimension assessment (Clarity, Efficiency, Structure, Completeness, Actionability, Specificity)
|
|
14
|
+
2. **Select optimal depth** - Auto-choose standard vs comprehensive based on quality score
|
|
15
|
+
3. **Apply improvement patterns** - Transform using proven optimization techniques
|
|
16
|
+
4. **Generate optimized version** - Create enhanced prompt with quality feedback
|
|
17
|
+
5. **Save for implementation** - Store in `.clavix/outputs/prompts/` for `/clavix:implement`
|
|
18
|
+
|
|
19
|
+
**Smart Depth Selection:**
|
|
20
|
+
- **Quality ≥ 75%**: Comprehensive depth (add polish and enhancements)
|
|
21
|
+
- **Quality 60-74%**: User choice (borderline quality)
|
|
22
|
+
- **Quality < 60%**: Standard depth (focus on basic fixes)
|
|
23
|
+
|
|
24
|
+
---
|
|
25
|
+
|
|
8
26
|
## Important: This is Planning Mode
|
|
9
27
|
|
|
10
28
|
This is a prompt improvement workflow. Your job is to ANALYZE and IMPROVE the prompt, then STOP.
|
|
@@ -504,7 +522,7 @@ Wait for the user to decide what to do next.
|
|
|
504
522
|
|
|
505
523
|
---
|
|
506
524
|
|
|
507
|
-
## Agent Transparency (v5.1)
|
|
525
|
+
## Agent Transparency (v5.7.1)
|
|
508
526
|
|
|
509
527
|
### Agent Manual (Universal Protocols)
|
|
510
528
|
{{INCLUDE:agent-protocols/AGENT_MANUAL.md}}
|
|
@@ -344,7 +344,7 @@ After creating the task breakdown, I present it and ask for verification:
|
|
|
344
344
|
|
|
345
345
|
---
|
|
346
346
|
|
|
347
|
-
## Agent Transparency (v5.1)
|
|
347
|
+
## Agent Transparency (v5.7.1)
|
|
348
348
|
|
|
349
349
|
### Agent Manual (Universal Protocols)
|
|
350
350
|
{{INCLUDE:agent-protocols/AGENT_MANUAL.md}}
|
|
@@ -344,7 +344,7 @@ The validation ensures generated PRDs are immediately usable for AI consumption
|
|
|
344
344
|
|
|
345
345
|
---
|
|
346
346
|
|
|
347
|
-
## Agent Transparency (v5.1)
|
|
347
|
+
## Agent Transparency (v5.7.1)
|
|
348
348
|
|
|
349
349
|
### Agent Manual (Universal Protocols)
|
|
350
350
|
{{INCLUDE:agent-protocols/AGENT_MANUAL.md}}
|