Skill comparison

Compare agent skills before installing.

Put high-signal skills side by side and inspect quality, adoption, freshness, install readiness, use-case fit, and warnings in one place.

Comparing 4 skills

Use this as a shortlist, then open the skill detail page before adopting.

Add more skills

Decision summary

LLMs From Scratch is the strongest overall pick here because it has a 100/100 readiness score and fits GitHub automation.

Strongest overall

LLMs From Scratch

Use this as a leading candidate, then validate the README and install path in your own agent stack.

Fastest prototype

LLMs From Scratch

Best first install candidate based on install readiness and adoption.

Freshest repo

Cog

Most recent maintenance signal among this shortlist.

SignalGlide

🐦 A open blazing-fast simple model gateway for rapid development of production GenAI apps

Prompt Engineering

22 prompt engineering techniques with hands-on Jupyter Notebook tutorials, from fundamental concepts to advanced strategies for leveraging LLMs.

Cog

Containers for machine learning

LLMs From Scratch

Implement a ChatGPT-like LLM in PyTorch from scratch, step by step

Quality
48/100
Needs review
100/100
Excellent
100/100
Excellent
100/100
Excellent
Decision verdict
38/100
Needs manual review

Do a manual repository review before adding this to an agent workflow.

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.

100/100
Production-ready

Use this as a leading candidate, then validate the README and install path in your own agent stack.

Adoption161 stars
0 installs
7.6K stars
0 installs
9.4K stars
0 installs
97K stars
0 installs
FreshnessAug 12, 2024Jun 11, 2026Jun 12, 2026Jun 2, 2026
Use-case fit
Stack fit
Platform hintsGo, MLOps, Claude CodeJupyter Notebook, Machine Learning, Claude Code, OpenAI AgentsGo, Machine Learning, Claude CodeJupyter Notebook, Machine Learning, Claude Code, OpenAI Agents
WarningsRepository looks stale · No OpenAgentSkill engagement data yetNo OpenAgentSkill engagement data yetNo OpenAgentSkill engagement data yetNo OpenAgentSkill engagement data yet
Best forCoding agents workflows · Claude Code teams · builders willing to evaluate younger projectsCoding agents workflows · Claude Code teams · teams that value GitHub adoption signalsCoding agents workflows · Claude Code teams · teams that value GitHub adoption signalsGitHub automation workflows · Claude Code teams · teams that value GitHub adoption signals
Not ideal forteams that require actively maintained dependencies · production agents without a repository reviewteams that need a vendor-supported SLA · high-compliance environments without internal security reviewteams that need a vendor-supported SLA · high-compliance environments without internal security reviewteams that need a vendor-supported SLA · high-compliance environments without internal security review
OpenAgentSkill engagement0 views
0 install copies
0 views
0 install copies
0 views
0 install copies
0 views
0 install copies
Install
$ npx skills add EinStack/glide
$ npx skills add NirDiamant/Prompt_Engineering
$ npx skills add replicate/cog
$ npx skills add rasbt/LLMs-from-scratch