mirror of
https://github.com/catlog22/Claude-Code-Workflow.git
synced 2026-02-05 01:50:27 +08:00
- Implement full coverage tests for Embedder model loading and embedding generation - Add CRUD operations and caching tests for VectorStore - Include cosine similarity computation tests - Validate semantic search accuracy and relevance through various queries - Establish performance benchmarks for embedding and search operations - Ensure edge cases and error handling are covered - Test thread safety and concurrent access scenarios - Verify availability of semantic search dependencies
25 lines
647 B
Plaintext
25 lines
647 B
Plaintext
PURPOSE: Generate semantic summaries and search keywords for code files
|
|
TASK:
|
|
- For each code block, generate a concise summary (1-2 sentences)
|
|
- Extract 5-10 relevant search keywords
|
|
- Identify the functional purpose/category
|
|
MODE: analysis
|
|
EXPECTED: JSON format output
|
|
|
|
=== CODE BLOCKS ===
|
|
[FILE: auth.py]
|
|
```python
|
|
def auth(): pass
|
|
```
|
|
|
|
=== OUTPUT FORMAT ===
|
|
Return ONLY valid JSON (no markdown, no explanation):
|
|
{
|
|
"files": {
|
|
"<file_path>": {
|
|
"summary": "Brief description of what this code does",
|
|
"keywords": ["keyword1", "keyword2", ...],
|
|
"purpose": "category like: auth, api, util, ui, data, config, test"
|
|
}
|
|
}
|
|
} |