llama.cpp
Repository: llama.cpp
Author: ggml-org · Source status: Clear source
Score 92Clear source
Manual reviewLLM inference in C/C++
Score basis：Clear source · Risk needs review · Universal
Author unclaimed
Universal
103.6K
Compare skills
Pick 2–4 skills and compare what really matters: fit, risk, install effort, and community signal.
Comparison matrix
Highlights show current best; tooltip explains diff/best rules.
SAS-v2.1 diff rules / risk tag notes
Start with the matrix. Open this section when you need to understand audit grades, top threats, control gaps, and best-value highlights.
Suggested baseline
Search to add skills, or paste 2–4 comma-separated slugs.
How differences are detected
A row is marked different when selected skills have distinct values. Only-differences mode hides rows that are identical.
How best values are highlighted
Audit score, evidence confidence, trust score, and community signal prefer higher values; execution risk and install friction prefer lower values.
How to read risk tags
Risk tags come from SAS-v2.1 public-evidence signals and point to command, network, secret, context, or supply-chain items to review before install.
Selected audit signals
LLM-Jailbreaks
Execution risk：High
Threat tags：prompt injection, tool poisoning, unexpected code execution
Control gaps：missing license, broad permissions, shell without guardrails
ccNexus
Execution risk：High
Threat tags：unexpected code execution, data exfiltration, human approval gap
Control gaps：missing license, broad permissions, shell without guardrails
one-api
Execution risk：High
Threat tags：unexpected code execution, data exfiltration, human approval gap
Control gaps：missing license, broad permissions, shell without guardrails
| Dimension | LLM-Jailbreaks | ccNexus | one-api |
|---|---|---|---|
| SAS-v2.1 pre-install audit | |||
Threat tags | prompt injection, tool poisoning, unexpected code execution | unexpected code execution, data exfiltration, human approval gap | unexpected code execution, data exfiltration, human approval gap |
Evidence confidence | 67% | 65% | 65% |
| Source & provenance | |||
Provenance | langgptai/LLM-Jailbreaks | lich0821/ccNexus | songquanpeng/one-api |
Category | Automation & Workflows | Dev & Engineering | Automation & Workflows |
Freshness | |||
| Risk & trust | |||
Trust score | 92 | 82 | 92 |
Audit signals | |||
| Install & compatibility | |||
Install friction | 75 | 40 | 75 |
| Community | |||
Stars | 594 | 816 | 31.9K |
Repository: LLMs-from-scratch
Author: rasbt · Source status: Clear source
Implement a ChatGPT-like LLM in PyTorch from scratch, step by step
Score basis：Clear source · Risk needs review · Universal
Repository: quivr
Author: QuivrHQ · Source status: Clear source
Opiniated RAG for integrating GenAI in your apps 🧠 Focus on your product rather than the RAG.
Score basis：Clear source · Risk needs review · Universal
Repository: GPT_API_free
Author: chatanywhere · Source status: Clear source
Free ChatGPT&DeepSeek API Key，免费ChatGPT&DeepSeek API。免费接入DeepSeek API和GPT4 API，支持 gpt | deepseek | claude | gemini | grok 等排名靠前的常用大模型。
Score basis：Clear source · Risk needs review · Universal
Repository: andrej-karpathy-skills
Author: forrestchang · Source status: Clear source
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
Score basis：Clear source · Risk needs review · Universal
2025-04-13 |
2026-03-23 |
2026-01-09 |
No explicit signals |
metadata-only |
Permission hints | repository clone | repository clone, local runtime dependencies | repository clone |
|---|