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
Commitment for AI agents — find agents ready for commitment, commitment compatibility, and commitment-level 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
Eps
Execution risk：High
Threat tags：unexpected code execution, data exfiltration, human approval gap
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
BitNet
Execution risk：High
Threat tags：unexpected code execution, data exfiltration, human approval gap
Control gaps：missing license, broad permissions, shell without guardrails
| Dimension | Eps | semantic-kernel | BitNet |
|---|---|---|---|
| Pre-install decision | |||
Pre-install score | 65 · Manual review | 68 · Manual review | 66 · Manual review |
Evidence completeness | 65% | 67% | 65% |
| Source & provenance | |||
Provenance | openclaw/skills | microsoft/semantic-kernel | microsoft/BitNet |
Category | Design & Content | Automation & Workflows | Automation & Workflows |
Freshness | |||
| Risk & permission signals | |||
Audit signals | network access, runs shell, writes files | metadata-only | metadata-only |
Permission hints | verify source provenance before install | repository clone | repository clone |
| Install & compatibility | |||
Install friction | 50 | 75 | 75 |
| Community | |||
Stars | 0 | 27.7K | 38.2K |
Repository: openclaw/skills
Author: yuan-huicheng · Source status: Clear source
Send multimedia content to Feishu (Lark) via API.
Score basis：Clear source · High execution risk · Universal · Evidence completeness 67%
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: zmofei · Source status: Clear source
Expert guidance on validating, optimizing, and ensuring quality of Mapbox styles through validation, accessibility checks, and optimization.
Score basis：Clear source · High execution risk · Universal · Evidence completeness 65%
Repository: openclaw/skills
Author: cinience · Source status: Clear source
Use when generating human-like speech audio with Model Studio DashScope Qwen TTS models (qwen3-tts-flash, qwen3-tts-instruct-flash).
Score basis：Clear source · High execution risk · Universal · Evidence completeness 67%
Repository: openclaw/skills
Author: crecendow · Source status: Clear source
禅道自动记工时技能。用户描述今天做了什么事，自动搜索匹配任务，确认后调用禅道API记录工时。支持智能匹配、自动重新登录、正确计算剩余工时。使用 recordworkhour 接口，适配禅道 21.x 开源版。
Score basis：Clear source · High execution risk · Universal · Evidence completeness 67%
2026-03-25 |
2026-04-14 |
2026-03-10 |
