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
Repository: pydantic-ai
Author: pydantic · Source status: Clear source
AI Agent Framework, the Pydantic way Topics: agent-framework, genai, llm, pydantic, python.
Score basis：Clear source · High execution risk · Universal · Evidence completeness 65%
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
赛博算命 Skill
Execution risk：Low
Threat tags：data exfiltration, supply chain, human approval gap
Control gaps：missing license, missing install docs, broad permissions
OMNI — All-In-One Master Skill
Execution risk：High
Threat tags：unexpected code execution, identity privilege abuse, data exfiltration
Control gaps：missing license, broad permissions, shell without guardrails
vscode-ext-commands
Execution risk：High
Threat tags：unexpected code execution, data exfiltration, human approval gap
Control gaps：missing license, broad permissions, shell without guardrails
| Dimension | 赛博算命 Skill | OMNI — All-In-One Master Skill | vscode-ext-commands |
|---|---|---|---|
| Pre-install decision | |||
Pre-install score | 92 · Manual review | 88 · Manual review | 82 · Manual review |
Score basis | Clear source, Low execution risk, Claude | Clear source, High execution risk, Claude | Clear source, High execution risk, Claude |
Execution risk | Low | High | High |
Threat tags | data exfiltration, supply chain, human approval gap | unexpected code execution, identity privilege abuse, data exfiltration | unexpected code execution, data exfiltration, human approval gap |
Control gaps | missing license, missing install docs, broad permissions | missing license, broad permissions, shell without guardrails | missing license, broad permissions, shell without guardrails |
Permission summary | Network | Permission review, Network, Secrets, Command | Permission review, Network, Command |
Evidence completeness | 60% | 67% | 65% |
| Source & provenance | |||
Provenance | jinchenma94/bazi-skill | openclaw/skills | github/awesome-copilot |
Category | Vertical & Solutions | Data & Analytics | Productivity & Docs |
Freshness | |||
| Risk & permission signals | |||
Audit signals | No explicit signals | needs credentials, network access, runs shell, writes files | runs shell |
Permission hints | No explicit hints | verify source provenance before install | local skill installation, workspace file updates |
| Install & compatibility | |||
Supported tools | Claude Code, Claude | Claude, Codex, OpenClaw | Claude, Codex, Cursor, Windsurf |
Install method | source-link | script-backed | instruction-only |
Install friction | |||
| Community | |||
Stars | 986 | 0 | 28.9K |
Repository: n8n
Author: n8n-io · Source status: Clear source
Fair-code workflow automation platform with native AI capabilities.
Score basis：Clear source · High execution risk · Universal · Evidence completeness 65%
Repository: dify
Author: langgenius · Source status: Clear source
Production-ready platform for agentic workflow development.
Score basis：Clear source · High execution risk · Universal · Evidence completeness 65%
2026-04-18 |
2026-04-02 |
2026-04-09 |
62 |
65 |
70 |
