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
agent-browser
Execution risk：High
Threat tags：data exfiltration, human approval gap
Control gaps：missing license, broad permissions, network without allowlist
Web Browsing.Bak
Execution risk：High
Threat tags：unexpected code execution, identity privilege abuse, data exfiltration
Control gaps：missing license, shell without guardrails, network without allowlist
crw
Execution risk：High
Threat tags：unexpected code execution, data exfiltration, human approval gap
Control gaps：missing license, broad permissions, shell without guardrails
| Dimension | agent-browser | Web Browsing.Bak | crw |
|---|---|---|---|
| SAS-v2.1 pre-install audit | |||
Threat tags | data exfiltration, human approval gap | unexpected code execution, identity privilege abuse, data exfiltration | unexpected code execution, data exfiltration, human approval gap |
Control gaps | missing license, broad permissions, network without allowlist | missing license, shell without guardrails, network without allowlist | missing license, broad permissions, shell without guardrails |
Permission summary | Network, Command | Permission review, Network, Secrets, Command | Permission review, Network, Command |
Evidence confidence | 64% | 65% | 67% |
| Source & provenance | |||
Provenance | vercel-labs/agent-browser/tree/main/skills/agent-browser | openclaw/skills | us/crw |
Freshness | 2026-02-04 | 2026-03-21 | 2026-04-08 |
| Risk & trust | |||
Trust score | 79 | 82 | 81 |
Audit signals | No explicit signals | needs credentials, network access | network access |
| Install & compatibility | |||
Supported tools | Claude, Codex, Cursor, Universal | Universal | Universal |
Install method | registry-install | script-backed | script-backed |
Install friction | |||
| Community | |||
Stars | 13.4K | 0 | 38 |
Repository: openclaw/skills
Author: cinience · Source status: Clear source
Use when low-latency realtime speech recognition is needed with Alibaba Cloud Model Studio Qwen ASR Realtime models, including streaming microphone input, live captions, or duplex voice agents.
Score basis：Clear source · High risk signals · Universal
Repository: openclaw/skills
Author: grantmacnamara · Source status: Clear source
Control a Mopidy music system via Mopidy JSON-RPC for everyday listening, queue management, and playback control.
Score basis：Clear source · High risk signals · Universal
Repository: googleworkspace/cli
Author: googleworkspace · Source status: Clear source
Recipe Save Email To Doc skill from googleworkspace/cli.
Score basis：Clear source · High risk signals · Claude
Repository: ai-sdk-computer-use
Author: vercel-labs · Source status: Clear source
Computer-using agent built with Next.js and the AI SDK by Vercel.
Score basis：Clear source · Risk needs review · Universal
Permission hints |
|---|
registry access, remote metadata pull, runtime dependencies may be required |
verify source provenance before install |
repository clone, local runtime dependencies |
50 |
55 |
40 |
