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
Repository: haystack
Author: deepset-ai · Source status: Clear source
Open-source AI orchestration framework for building context-engineered, production-ready LLM applications.
Score basis：Clear source · Low risk signals · Universal
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
OpenViking
Execution risk：High
Threat tags：unexpected code execution, identity privilege abuse, data exfiltration
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
security-ownership-map
Execution risk：High
Threat tags：data exfiltration, human approval gap
Control gaps：missing license, broad permissions, network without allowlist
| Dimension | OpenViking | scholar-rag | security-ownership-map |
|---|---|---|---|
| SAS-v2.1 pre-install audit | |||
Threat tags | unexpected code execution, identity privilege abuse, data exfiltration | unexpected code execution, data exfiltration, memory context poisoning | 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, network without allowlist |
Permission summary | Permission review, Network, Secrets, Command | Permission review, Network, Command | Permission review, Network, Command |
Evidence confidence | 69% | 67% | 67% |
| Source & provenance | |||
Provenance | volcengine/OpenViking | PangHu1020/scholar-rag | openai/skills/tree/main/skills/.curated/security-ownership-map |
Category | Knowledge & RAG | Knowledge & RAG | Data & Analytics |
Freshness | |||
| Risk & trust | |||
Trust score | 79 | 82 | 82 |
Audit signals | writes files | No explicit signals | writes files |
| Install & compatibility | |||
Supported tools | Universal | Universal | Claude, Codex, Cursor, Universal |
Install method | script-backed | script-backed | registry-install |
Install friction | |||
| Community | |||
Stars | 21.9K | 22 | 7.3K |
Repository: prompt-in-context-learning
Author: EgoAlpha · Source status: Clear source
Awesome resources for in-context learning and prompt engineering: Mastery of the LLMs such as ChatGPT, GPT-3, and FlanT5, with up-to-date and cutting-edge updates.
Score basis：Clear source · Low risk signals · Universal
Repository: Buddy
Author: is-leeroy-jenkins · Source status: Clear source
An AI for federal financial management designed to support Financial Analysts, Managers, and Policy Professionals.
Score basis：Clear source · High risk signals · Universal
2026-04-10 |
2026-04-06 |
2026-02-11 |
repository clone, local runtime dependencies |
repository clone, local runtime dependencies |
registry access, remote metadata pull, runtime dependencies may be required |
40 |
40 |
50 |
