Compare skills
Pick 2–4 skills and compare what really matters: fit, risk, install effort, and community signal.
Selected skills (2/4)
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
harmony
Execution risk：High
Threat tags：unexpected code execution, data exfiltration, human approval gap
Control gaps：missing license, broad permissions, shell without guardrails
scholar-rag
Execution risk：High
Threat tags：unexpected code execution, data exfiltration, memory context poisoning
Control gaps：missing license, broad permissions, shell without guardrails
| Dimension | harmony | scholar-rag |
|---|---|---|
| SAS-v2.1 pre-install audit | ||
Audit grade | C · Review first | C · Review first |
Execution risk | High | High |
Threat tags | unexpected code execution, data exfiltration, human approval gap | unexpected code execution, data exfiltration, memory context poisoning |
Control gaps | missing license, broad permissions, shell without guardrails | missing license, broad permissions, shell without guardrails |
Permission summary | Permission review, Network, Command | Permission review, Network, Command |
Evidence confidence | 65% | 67% |
| Source & provenance | ||
Provenance | openai/harmony | PangHu1020/scholar-rag |
Category | Automation & Workflows | Knowledge & RAG |
Freshness | 2026-04-09 | |
| Risk & trust | ||
Trust score | 92 | 82 |
Audit signals | metadata-only | No explicit signals |
Permission hints | ||
| Install & compatibility | ||
Supported tools | Universal | Universal |
Install method | script-backed | script-backed |
Install friction | ||
| Community | ||
Stars | 4.3K | 22 |
Repository: CLIP
Author: openai · Source status: Clear source
CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image
Score basis：Clear source · Risk needs review · Universal
Repository: litellm
Author: BerriAI · Source status: Clear source
Python SDK, Proxy Server (AI Gateway) to call 100+ LLM APIs in OpenAI (or native) format, with cost tracking, guardrails, loadbalancing and logging.
Score basis：Clear source · Risk needs review · Universal
Repository: claude-code-router
Author: musistudio · Source status: Clear source
Use Claude Code as the foundation for coding infrastructure, allowing you to decide how to interact with the model while enjoying updates from Anthropic.
Score basis：Clear source · Risk needs review · Universal
repository clone |
repository clone, local runtime dependencies |
40 |
