danielmiessler/Fabric vs multica-ai/andrej-karpathy-skills
danielmiessler/Fabric scores higher overall: 68/100 (B-tier) against 61/100 (Experimental-tier). danielmiessler/Fabric leads on reliability, skill leverage, documentation; multica-ai/andrej-karpathy-skills leads on safety, adoption. Scored 2026-07-07, methodology v1.0.
Dimension by dimension
| Dimension | fabric | karpathy-skills |
|---|---|---|
| Reliability | 62 | 60 |
| Skill Leverage | 74 | 70 |
| Documentation | 78 | 68 |
| Maintenance | 80 | 50 |
| Safety / Governance | 58 | 62 |
| Evaluation Readiness | 48 | 35 |
| Composability | 72 | 55 |
| Adoption (capped) | 86 | 90 |
| Overall | 68 · B | 61 · Experimental |
The entries
A large library of named, reusable prompt patterns with a CLI for piping content through them. Prompt-layer infrastructure: patterns without…
A single CLAUDE.md distilling Andrej Karpathy's public observations on LLM coding pitfalls into instruction-file rules. An instruction set,…
Frequently asked questions
danielmiessler/Fabric or multica-ai/andrej-karpathy-skills?
danielmiessler/Fabric scores higher overall (68 vs 61, methodology v1.0). But they are the same category, so the dimension table below is the real answer.
How is this comparison generated?
Both scorecards come from the same public rubric with evidence notes, scored by the same editorial process. This page presents them side by side; it adds no new judgments beyond the scores themselves.