Skill comparison
Compare agent skills before installing.
Comparing 4 skills
Use this as a shortlist, then open the skill detail page before adopting.
Decision summary
Unilm is the strongest overall pick here because it has a 100/100 readiness score and fits Workflow automation.
Strongest overall
Unilm
Use this as a leading candidate, then validate the README and install path in your own agent stack.
Fastest prototype
Unilm
Best first install candidate based on install readiness and adoption.
Freshest repo
Deepdoctection
Most recent maintenance signal among this shortlist.
| Signal | LiLT Official PyTorch implementation of LiLT: A Simple yet Effective Language-Independent Layout Transformer for Structured Document Understanding (ACL 2022) | Donut Official Implementation of OCR-free Document Understanding Transformer (Donut) and Synthetic Document Generator (SynthDoG), ECCV 2022 | Deepdoctection A Repo For Document AI | Unilm Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities |
|---|---|---|---|---|
| Quality | 52/100 Needs review | 79/100 Strong | 100/100 Excellent | 100/100 Excellent |
| Decision verdict | 42/100 Needs manual review Do a manual repository review before adding this to an agent workflow. | 81/100 Strong shortlist Shortlist this skill and compare it with close alternatives before production adoption. | 100/100 Production-ready Use this as a leading candidate, then validate the README and install path in your own agent stack. | 100/100 Production-ready Use this as a leading candidate, then validate the README and install path in your own agent stack. |
| Adoption | 366 stars 0 installs | 6.9K stars 0 installs | 3.2K stars 0 installs | 22K stars 0 installs |
| Freshness | Oct 31, 2022 | Jul 11, 2024 | Jun 12, 2026 | Jan 23, 2026 |
| Use-case fit | ||||
| Stack fit | ||||
| Platform hints | Python, Document AI, Claude Code | Python, Document AI, Claude Code | Python, OCR, Claude Code | Python, Document AI, Claude Code |
| Warnings | Repository looks stale · No OpenAgentSkill engagement data yet | Repository looks stale · No OpenAgentSkill engagement data yet | No OpenAgentSkill engagement data yet | No OpenAgentSkill engagement data yet |
| Best for | Document processing workflows · Claude Code teams · builders willing to evaluate younger projects | Document processing workflows · Claude Code teams · teams that value GitHub adoption signals | Document processing workflows · Claude Code teams · teams that value GitHub adoption signals | Workflow automation workflows · Claude Code teams · teams that value GitHub adoption signals |
| Not ideal for | teams that require actively maintained dependencies · production agents without a repository review | teams that require actively maintained dependencies · production agents without a repository review | teams that need a vendor-supported SLA · high-compliance environments without internal security review | teams that need a vendor-supported SLA · high-compliance environments without internal security review |
| OpenAgentSkill engagement | 0 views 0 install copies | 0 views 0 install copies | 0 views 0 install copies | 0 views 0 install copies |
| Install | $ npx skills add jpWang/LiLT | $ npx skills add clovaai/donut | $ npx skills add deepdoctection/deepdoctection | $ npx skills add microsoft/unilm |