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: gemini-cli
Author: google-gemini · Source status: Clear source
An open-source AI agent that brings the power of Gemini directly into your terminal.
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
codex
Execution risk：High
Threat tags：unexpected code execution, data exfiltration, human approval gap
Control gaps：missing license, broad permissions, shell without guardrails
ansible
Execution risk：High
Threat tags：unexpected code execution, data exfiltration, human approval gap
Control gaps：missing license, broad permissions, shell without guardrails
mcp-integration
Execution risk：High
Threat tags：data exfiltration, memory context poisoning, human approval gap
Control gaps：missing license, broad permissions, network without allowlist
| Dimension | codex | ansible | mcp-integration |
|---|---|---|---|
| Pre-install decision | |||
Pre-install score | 66 · Manual review | 66 · Manual review | 72 · Manual review |
Score basis | Clear source, High execution risk, Universal | Clear source, High execution risk, Universal | Clear source, High execution risk, Claude |
Execution risk | High | High | High |
Threat tags | unexpected code execution, data exfiltration, human approval gap | unexpected code execution, data exfiltration, human approval gap | data exfiltration, memory context poisoning, human approval gap |
Control gaps | missing license, broad permissions, shell without guardrails | missing license, broad permissions, shell without guardrails | missing license, broad permissions, network without allowlist |
Permission summary | Permission review, Network, Command | Permission review, Network, Command | Permission review, Network, Command |
Evidence completeness | 65% | 65% | 65% |
| Source & provenance | |||
Provenance | openai/codex | ansible/ansible | anthropics/claude-code/tree/main/plugins/plugin-dev/skills/mcp-integration |
Category | Agent & Tools | Agent & Tools | Operations & Infra |
Freshness | |||
| Risk & permission signals | |||
Audit signals | metadata-only | metadata-only | network access |
Permission hints | repository clone | repository clone | registry access, remote metadata pull, runtime dependencies may be required |
| Install & compatibility | |||
Supported tools | Universal | Universal | Claude, Codex, Cursor, Universal |
Install method | script-backed | script-backed | registry-install |
Install friction | |||
| Community | |||
Stars | 75.1K | 68.4K | 65.5K |
Repository: PaddleOCR
Author: PaddlePaddle · Source status: Clear source
Turn any PDF or image document into structured data for your AI.
Score basis：Clear source · High execution risk · Universal · Evidence completeness 65%
Repository: cline
Author: cline · Source status: Clear source
Autonomous coding agent right in your IDE, capable of creating/editing files, executing commands, using the browser, and more with your permission every step of the way.
Score basis：Clear source · High execution risk · Universal · Evidence completeness 67%
Repository: nx
Author: nrwl · Source status: Clear source
The Monorepo Platform that amplifies both developers and AI agents.
Score basis：Clear source · High execution risk · Universal · Evidence completeness 65%
Repository: whisper
Author: openai · Source status: Clear source
Robust Speech Recognition via Large-Scale Weak Supervision
Score basis：Clear source · High execution risk · Universal · Evidence completeness 65%
2026-04-14 |
2026-04-14 |
2026-02-04 |
75 |
75 |
50 |
