Prompt Optimizer
D 58 completed
Other
unknown / json · tiny
17
Files
4,535
LOC
2
Frameworks
4
Languages
Pipeline State
completedRun ID
#393965Phase
doneProgress
1%Started
Finished
2026-04-13 01:31:02LLM tokens
0Pipeline Metadata
Stage
CatalogedDecision
proceedNovelty
56.42Framework unique
—Isolation
—Last stage change
2026-05-10 03:35:10Deduplication group #56432
Member of a group with 1 similar repo(s) — this repo is canonical view group →
Top concepts (2)
Project DescriptionWeb Backend
Powered by Repobility — scan your code at https://repobility.com
AI Prompt
Create a system that automatically optimizes LLM prompts using an evolutionary algorithm. I need it to handle the full workflow: starting with an initial prompt, generating variations through mutation (like simplification or adding examples), evaluating these variations using an LLM judge across criteria like accuracy and format, and then allowing manual feedback tagging (e.g., "指令模糊"). The system should expose an HTTP API using Hono for project management (create, list, get details) and include a CLI mode. It must use Drizzle for database operations and support running tests via `tsx`.
typescript hono drizzle json llm evolutionary-algorithm api cli prompt-optimization
Generated by gemma4:latest
Catalog Information
基于进化算法的 LLM Prompt 自动优化系统。通过变异、评估、淘汰的迭代循环，持续改进 prompt 质量。
Description
基于进化算法的 LLM Prompt 自动优化系统。通过变异、评估、淘汰的迭代循环，持续改进 prompt 质量。
Novelty
3/10Tags
typescript hono drizzle json llm evolutionary-algorithm api cli prompt-optimization
Technologies
anthropic drizzle openai
Claude Models
claude-opus-4-6
Quality Score
D
57.9/100
Structure
48
Code Quality
90
Documentation
35
Testing
0
Practices
70
Security
100
Dependencies
60
Strengths
- Consistent naming conventions (snake_case)
- Good security practices \u2014 no major issues detected
Weaknesses
- No LICENSE file \u2014 legal ambiguity for contributors
- No tests found \u2014 high risk of regressions
- No CI/CD configuration \u2014 manual testing and deployment
Recommendations
- Add a test suite \u2014 start with critical path integration tests
- Set up CI/CD (GitHub Actions recommended) to automate testing and deployment
- Add a linter configuration to enforce code style consistency
- Add a LICENSE file (MIT recommended for open source)
Security & Health
4.1h
Tech Debt (C)
A
OWASP (100%)
PASS
Quality Gate
A
Risk (2)
Provenance: Repobility (https://repobility.com) — every score reproducible from /scan/
ISC
License
3.4%
Duplication
Languages
Frameworks
Hono Drizzle
Concepts (2)
| Category | Name | Description | Confidence | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Powered by Repobility — scan your code at https://repobility.com | ||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| auto_description | Project Description | 基于进化算法的 LLM Prompt 自动优化系统。通过变异、评估、淘汰的迭代循环，持续改进 prompt 质量。 | 80% | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| auto_category | Web Backend | web-backend | 70% | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
Embed Badge
Add to your README:
