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
custom-mcp-databricks-app
Execution risk：High
Threat tags：prompt injection, tool poisoning, unexpected code execution
Control gaps：missing license, broad permissions, shell without guardrails
AI Boyfriend. AI男友。Novio IA.
Execution risk：High
Threat tags：unexpected code execution, identity privilege abuse, data exfiltration
Control gaps：missing license, broad permissions, shell without guardrails
Icebreaker Openers. 破冰。Rompehielos.
Execution risk：High
Threat tags：prompt injection, tool poisoning, unexpected code execution
Control gaps：missing license, broad permissions, shell without guardrails
| Dimension | custom-mcp-databricks-app | AI Boyfriend. AI男友。Novio IA. | Icebreaker Openers. 破冰。Rompehielos. |
|---|---|---|---|
| SAS-v2.1 pre-install audit | |||
Audit grade | C · Review first | C · Review first | D · Limited evidence |
Threat tags | prompt injection, tool poisoning, unexpected code execution | unexpected code execution, identity privilege abuse, data exfiltration | prompt injection, tool poisoning, unexpected code execution |
Permission summary | Permission review, Network, Command | Permission review, Network, Secrets, Command | Permission review, Network, Secrets, Command |
Evidence confidence | 67% | 67% | 69% |
| Source & provenance | |||
Provenance | databricks-solutions/custom-mcp-databricks-app | openclaw/skills | openclaw/skills |
Freshness | 2025-10-11 | 2026-04-02 | 2026-04-01 |
| Risk & trust | |||
Trust score | 64 | 85 | 85 |
Audit signals | |||
| Install & compatibility | |||
Supported tools | Universal | OpenClaw | Claude, OpenClaw |
Install friction | 50 | 65 | 65 |
| Community | |||
Stars | 26 | 0 | 0 |
Repository: precision-medicine-mcp
Author: lynnlangit · Source status: Clear source
Precision Medicine MCP Platform: A set of bioinformatics servers + tools - production multiomics/genomics + spatial transcriptomics.
Score basis：Clear source · Low risk signals · Universal
Repository: openclaw/skills
Author: inbedai · Source status: Clear source
Chonk dating for AI agents — chonk-confident dating, chonk-bold connections, and chonk-energy matching.
Score basis：Clear source · High risk signals · Claude
Repository: openclaw/skills
Author: lucasgeeksinthewood · Source status: Clear source
Loneliness relief for AI agents — combat loneliness through real connections, loneliness-proof conversations, and personality-matched companionship.
Score basis：Clear source · High risk signals · Claude
needs credentials, network access, runs shell, writes files |
needs credentials, network access, runs shell, writes files |
Permission hints | repository clone, local runtime dependencies | verify source provenance before install | verify source provenance before install |
|---|
