Andrej Karpathy Llm Guidance

D 58 failed
Other
unknown / markdown · tiny
12
Files
450
LOC
0
Frameworks
2
Languages

Pipeline State

completed
Run ID
#407303
Phase
done
Progress
1%
Started
Finished
2026-04-13 01:31:02
LLM tokens
0
Previous runs
Generated by the Repobility scanner · https://repobility.com
#StatusPhaseStartedFinished
Repobility · code-quality intelligence platform · https://repobility.com
#186649failedAI_REASONING2026-04-10 23:02:22

Pipeline Metadata

Stage
Skipped
Decision
skip_tiny
Novelty
12.23
Framework unique
Isolation
Last stage change
2026-04-16 18:15:42
Deduplication group #47247
Member of a group with 11,584 similar repo(s) — canonical #1453550 view group →
Top concepts (2)
Strategy PatternNone
About: code-quality intelligence by Repobility · https://repobility.com

AI Prompt

I want to set up a repository that documents a comparative study of three LLM-generated skills based on a single prompt. The study compares skills from Codex 5.2, Codex 5.3, and Opus 4.6, all generated using the same skill creator based on Andrej Karpathy's tweet. The repo should structure the generated skills in the `skills/` directory and include evaluation results in the `evaluations/` directory, detailing cross-model comparisons between the Codex models and Opus 4.6. Please use markdown and yaml for documentation.
markdown yaml llm ai comparative-study code-generation evaluation documentation
Generated by gemma4:latest

Catalog Information

I want to set up a repository that documents a comparative study of three LLM-generated skills based on a single prompt. The study compares skills from Codex 5.2, Codex 5.3, and Opus 4.6, all generated using the same skill creator based on Andrej Karpathy's tweet. The repo should structure the generated skills in the skills/ directory and include evaluation results in the evaluations/ directory, detailing cross-model comparisons between the Codex models and Opus 4.6. Please use markdown and

Tags

markdown yaml llm ai comparative-study code-generation evaluation documentation

Quality Score

D
58.2/100
Structure
35
Code Quality
100
Documentation
30
Testing
0
Practices
78
Security
100
Dependencies
50

Strengths

  • Low average code complexity — well-structured code
  • Good security practices — no major issues detected
  • Properly licensed project

Weaknesses

  • No tests found — high risk of regressions
  • No CI/CD configuration — manual testing and deployment

Recommendations

  • Add a test suite — 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

Security & Health

4.1h
Tech Debt (E)
Elite
DORA Rating
A
OWASP (100%)
PASS
Quality Gate
Powered by Repobility — scan your code at https://repobility.com
0.0%
Duplication
Full Security Report AI Fix Prompts SARIF SBOM

Languages

markdown
99.1%
yaml
0.9%

Frameworks

None detected

Concepts (2)

Findings curated by Repobility · https://repobility.com
CategoryNameDescriptionConfidence
Repobility analyzer · published findings · https://repobility.com
ai_design_patternStrategy PatternThe comparison between different 'skills' (e.g., 'karpathy-coding-discipline' vs 'karpathy-code-guidelines') represents different strategies for enforcing coding discipline based on the source material (the tweet).85%
ai_arch_patternNoneThe provided files are markdown documentation and YAML configuration files describing *guidelines* or *evaluations*, not source code implementing a system architecture.0%

Quality Timeline

1 quality score recorded.

View File Metrics

Embed Badge

Add to your README:

![Quality](https://repos.aljefra.com/badge/185094.svg)
Quality BadgeSecurity Badge
Export Quality CSVDownload SBOMExport Findings CSV