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
openclaw-optimize
Execution risk：High
Threat tags：unexpected code execution, data exfiltration, memory context poisoning
Control gaps：missing license, broad permissions, shell without guardrails
skill-seekers
Execution risk：High
Threat tags：unexpected code execution, identity privilege abuse, data exfiltration
Control gaps：missing license, broad permissions, shell without guardrails
Agent Relay Orchestrator
Execution risk：High
Threat tags：unexpected code execution, identity privilege abuse, data exfiltration
Control gaps：missing license, broad permissions, shell without guardrails
| Dimension | openclaw-optimize | skill-seekers | Agent Relay Orchestrator |
|---|---|---|---|
| SAS-v2.1 pre-install audit | |||
Audit grade | C · Review first | D · Limited evidence | C · Review first |
Threat tags | unexpected code execution, data exfiltration, memory context poisoning | unexpected code execution, identity privilege abuse, data exfiltration | unexpected code execution, identity privilege abuse, data exfiltration |
Permission summary | Permission review, Network, Command | Permission review, Network, Secrets, Command | Permission review, Network, Secrets, Command |
Evidence confidence | 67% | 71% | 67% |
| Source & provenance | |||
Category | Operations & Infra | Dev & Engineering | Integrations & Connectors |
Freshness | 2026-03-29 | 2026-04-04 | 2026-03-29 |
| Risk & trust | |||
Trust score | 85 | 88 | 85 |
Audit signals | network access, runs shell, writes files | needs credentials, network access, runs shell, writes files | needs credentials, network access, runs shell, writes files |
| Install & compatibility | |||
Supported tools | OpenClaw | Claude, Cursor, Windsurf | Claude, OpenClaw |
Install friction | 50 | 65 | 65 |
Repository: openclaw/skills
Author: jpengcheng523-netizen · Source status: Clear source
Provides monitoring and alerting for agent abnormal behavior metrics with Prometheus and Grafana support, including P99 latency, error rates, anomaly detection, and custom alert rules.
Score basis：Clear source · High risk signals · Universal
Repository: openclaw/skills
Author: james-le-twelve-labs · Source status: Clear source
Search inside videos, generate summaries, and analyze video content using TwelveLabs video understanding AI.
Score basis：Clear source · High risk signals · OpenClaw
Repository: openclaw/skills
Author: robin-marv · Source status: Clear source
Snapshot and back up OpenClaw brain files (AGENTS.md, SOUL.md, MEMORY.md, memory/, etc.) to an offsite git repository — like a lobster shedding its shell, leaving behind a perfect copy before growing.
Score basis：Clear source · High risk signals · OpenClaw
Permission hints | verify source provenance before install | verify source provenance before install | requires binary: node, requires binary: claude, requires binary: kind: node, target os: macos, target os: linux, verify source provenance before install |
|---|
