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.
Score-basis 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
Pre-install score, evidence completeness, 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
mcp-context-forge
Execution risk：High
Threat tags：unexpected code execution, data exfiltration, memory context poisoning
Control gaps：missing license, broad permissions, shell without guardrails
accessibility-scanner
Execution risk：High
Threat tags：unexpected code execution, data exfiltration, human approval gap
Control gaps：missing license, broad permissions, shell without guardrails
GLM-OCR-SDK
Execution risk：High
Threat tags：unexpected code execution, identity privilege abuse, data exfiltration
Control gaps：missing license, broad permissions, shell without guardrails
| Dimension | mcp-context-forge | accessibility-scanner | GLM-OCR-SDK |
|---|---|---|---|
| Pre-install decision | |||
Pre-install score | 66 · Manual review | 66 · Manual review | 60 · Manual review |
Score basis | Clear source, High execution risk, Universal | Clear source, High execution risk, Universal | Clear source, High execution risk, OpenClaw |
Threat tags | unexpected code execution, data exfiltration, memory context poisoning | unexpected code execution, data exfiltration, human approval gap | unexpected code execution, identity privilege abuse, data exfiltration |
Permission summary | Permission review, Network, Command | Permission review, Network, Command | Permission review, Network, Secrets, Command |
Evidence completeness | 67% | 65% | 67% |
| Source & provenance | |||
Provenance | IBM/mcp-context-forge | github/accessibility-scanner | openclaw/skills |
Category | Operations & Infra | Agent & Tools | Productivity & Docs |
Freshness | |||
| Risk & permission signals | |||
Audit signals | No explicit signals | metadata-only | needs credentials, network access, runs shell, writes files |
Permission hints | repository clone, local runtime dependencies | repository clone | requires binary: python, verify source provenance before install |
| Install & compatibility | |||
Supported tools | Universal | Universal | OpenClaw |
Install friction | 40 | 75 | 65 |
| Community | |||
Stars | 3.5K | 260 | 0 |
Repository: kubeshark
Author: kubeshark · Source status: Clear source
eBPF-powered network observability for Kubernetes.
Score basis：Clear source · High execution risk · Universal · Evidence completeness 67%
Repository: skillhub
Author: iflytek · Source status: Clear source
Self-hosted, open-source agent skill registry for enterprises.
Score basis：Clear source · High execution risk · Universal · Evidence completeness 67%
Repository: watson-online-store
Author: IBM · Source status: Clear source
Learn how to use Watson Assistant and Watson Discovery.
Score basis：Clear source · High execution risk · Universal · Evidence completeness 65%
Repository: eval-assist
Author: IBM · Source status: Clear source
EvalAssist is an open-source project that simplifies using large language models as evaluators (LLM-as-a-Judge) of the output of other large language models by supporting users in iteratively refining evaluation criteri…
Score basis：Clear source · High execution risk · Universal · Evidence completeness 65%
Repository: ELM-Python-Client
Author: IBM · Source status: Clear source
Python client for IBM Enterprise Lifecycle Management applications with example commandline applications for OSLC Query export to CSV from DOORS Next (DN/DNG), Enterprise Workflow Management (EWM/RTC) and Enterprise Tes…
Score basis：Clear source · High execution risk · Universal · Evidence completeness 67%
2026-04-08 |
2026-04-14 |
2026-04-02 |
