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
openai-cookbook
Execution risk：High
Threat tags：unexpected code execution, data exfiltration, human approval gap
Control gaps：missing license, broad permissions, shell without guardrails
harmony
Execution risk：High
Threat tags：unexpected code execution, data exfiltration, human approval gap
Control gaps：missing license, broad permissions, shell without guardrails
new-api
Execution risk：High
Threat tags：unexpected code execution, data exfiltration, human approval gap
Control gaps：missing license, broad permissions, shell without guardrails
| Dimension | openai-cookbook | harmony | new-api |
|---|---|---|---|
| SAS-v2.1 pre-install audit | |||
Audit grade | C · Review first | C · Review first | C · Review first |
Execution risk | High | High | High |
Threat tags | unexpected code execution, data exfiltration, human approval gap | unexpected code execution, data exfiltration, human approval gap | unexpected code execution, data exfiltration, human approval gap |
Control gaps | missing license, broad permissions, shell without guardrails | missing license, broad permissions, shell without guardrails | missing license, broad permissions, shell without guardrails |
Permission summary | Permission review, Network, Command | Permission review, Network, Command | Permission review, Network, Command |
Evidence confidence | 65% | 65% | 65% |
| Source & provenance | |||
Provenance | openai/openai-cookbook | openai/harmony | QuantumNous/new-api |
Category | Automation & Workflows | Automation & Workflows | Automation & Workflows |
Freshness | |||
| Risk & trust | |||
Trust score | 92 | 92 | 92 |
| Install & compatibility | |||
Supported tools | Universal | Universal | Universal |
Install method | script-backed | script-backed | script-backed |
Install friction | |||
| Community | |||
Stars | 72.7K | 4.3K | 26.6K |
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: langextract
Author: google · Source status: Clear source
A Python library for extracting structured information from unstructured text using LLMs with precise source grounding and interactive visualization.
Score basis：Clear source · Risk needs review · Universal
2026-04-14 |
2026-04-09 |
2026-04-13 |
metadata-only |
metadata-only |
metadata-only |
Permission hints | repository clone | repository clone | repository clone |
|---|
75 |
75 |
75 |
