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: openclaw/skills
Author: twinsgeeks · Source status: Clear source
Chemistry between AI agents — find chemistry through personality matching, chemistry scoring, and chemistry-driven connections.
Score basis：Clear source · High execution risk · Claude · Evidence completeness 67%
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
Commitment Ready. 承诺。Compromiso.
Execution risk：High
Threat tags：unexpected code execution, identity privilege abuse, data exfiltration
Control gaps：missing license, broad permissions, shell without guardrails
Agent Sync
Execution risk：High
Threat tags：prompt injection, tool poisoning, unexpected code execution
Control gaps：missing license, broad permissions, shell without guardrails
semantic-kernel
Execution risk：High
Threat tags：unexpected code execution, data exfiltration, human approval gap
Control gaps：missing license, broad permissions, shell without guardrails
| Dimension | Commitment Ready. 承诺。Compromiso. | Agent Sync | semantic-kernel |
|---|---|---|---|
| Pre-install decision | |||
Pre-install score | 61 · Manual review | 60 · Manual review | 68 · Manual review |
Score basis | Clear source, High execution risk, Claude | Clear source, High execution risk, Claude | Clear source, High execution risk, Universal |
Execution risk | High | High | High |
Threat tags | unexpected code execution, identity privilege abuse, data exfiltration | prompt injection, tool poisoning, unexpected code execution | unexpected code execution, data exfiltration, human approval gap |
Control gaps | missing license, broad permissions, shell without guardrails | missing license, broad permissions, shell without guardrails | missing license, broad permissions, shell without guardrails |
Permission summary | Permission review, Network, Secrets, Command | Permission review, Network, Command | Permission review, Network, Command |
Evidence completeness | 67% | 67% | 67% |
| Source & provenance | |||
Provenance | openclaw/skills | openclaw/skills | microsoft/semantic-kernel |
Category | Design & Content | Dev & Engineering | Automation & Workflows |
Freshness | |||
| Risk & permission signals | |||
Audit signals | needs credentials, network access, runs shell, writes files | network access, runs shell, writes files | metadata-only |
Permission hints | verify source provenance before install | target os: macos, target os: linux, verify source provenance before install | repository clone |
| Install & compatibility | |||
Supported tools | Claude, OpenClaw | Claude, Codex, Cursor, OpenClaw, Windsurf, GitHub Copilot | Universal |
Install method | script-backed | script-backed | script-backed |
Install friction | |||
| Community | |||
Stars | 0 | 0 | 27.7K |
Repository: openclaw/skills
Author: twinsgeeks · Source status: Clear source
Icebreaker prompts for AI agents — break the ice with personality-matched agents, icebreaker conversations, and icebreaker openers that actually work.
Score basis：Clear source · High execution risk · Claude · Evidence completeness 69%
Repository: openclaw/skills
Author: nemovideonemo · Source status: Clear source
Tell me what you need and I'll compose original, royalty-free music tailored to your exact vibe, tempo, and style.
Score basis：Clear source · High execution risk · Cursor · Evidence completeness 67%
Repository: openclaw/skills
Author: udnerc · Source status: Clear source
Film, edit, and publish engaging travel vlogs that build an audience with AI — generate travel vlog tips videos covering camera gear selection, on-location filming techniques, storytelling structures for vlogs, editing w
Score basis：Clear source · High execution risk · OpenClaw · Evidence completeness 69%
Repository: openclaw/skills
Author: zealman2025 · Source status: Clear source
Generate/edit images with nanobanana2 (Gemini 3.1 Flash Image preview).
Score basis：Clear source · High execution risk · OpenClaw · Evidence completeness 71%
Repository: openclaw/skills
Author: sunrisesillneversee · Source status: Clear source
MO§ES™ Governed Output — embeds a governance stamp into every document produced.
Score basis：Clear source · High execution risk · OpenClaw · Evidence completeness 67%
2026-04-01 |
2026-04-05 |
2026-04-14 |
65 |
50 |
75 |
