A
Prompt-Engineering-Guide
83.9
80,149 stars · MIT
AI Agents
taste-skill leads by 13.3 · clear
A
83.9
80,149 stars · MIT
B · leads
97.2
117,459 stars · MIT
Prompt-Engineering-Guide versus taste-skill is a AI Agents comparison assembled from public repository metrics, the license on file, and whether each product can be self-hosted. Prompt-Engineering-Guide is written mainly in MDX; taste-skill is written mainly in JavaScript. The composite score is 83.9 for Prompt-Engineering-Guide and 97.2 for taste-skill.
taste-skill has 117,459 GitHub stars to Prompt-Engineering-Guide's 80,149, a gap of 37,310 (1.47×). Forks are 8,790 for Prompt-Engineering-Guide and 7,858 for taste-skill. On the log scale used inside this pair, adoption is 97 versus 100, and the fork community is 100 versus 99.
Push history: Prompt-Engineering-Guide was last pushed on 11 March 2026 (250 days ago), and taste-skill was last pushed on 08 November 2026 (8 days ago). Open issues stand at 300 for Prompt-Engineering-Guide (0.004 per star) and 10 for taste-skill (0.000 per star). Issue-health scores are 96 and 96; activity scores are 36 and 92.
Both Prompt-Engineering-Guide and taste-skill are listed as MIT. A permissive grant. A company can usually ship it inside a commercial product and keep its own application code private, provided it keeps the copyright notice. The license score is therefore level at 96 versus 96, and the decision moves to adoption, activity, and hosting. This is a procurement signal, not legal advice.
In AI Agents, both Prompt-Engineering-Guide (80,149 stars) and taste-skill (117,459 stars) are marked self-hostable. Deploy scores are 100 and 100. Running either one means you own upgrades, backups, and the license duties that follow a modified copy. Pricing labels on file: Prompt-Engineering-Guide is open source, taste-skill is open source.
The lead is split. Prompt-Engineering-Guide is furthest ahead on fork community (100 to 99), while taste-skill is furthest ahead on recent activity (92 to 36). Choose the dimension a rollout cannot compromise on.
taste-skill finishes ahead at 97.2 against Prompt-Engineering-Guide at 83.9, a 13.3 point clear margin under the published weights.
Scores are computed inside this pair only. Method and weights.
Bars are scaled within the row. Higher is stronger. Open issues are a raw count, so that row has no bar.
| Signal | Prompt-Engineering-Guide | taste-skill |
|---|---|---|
| GitHub stars | 80,149 | 117,459 |
| Forks | 8,790 | 7,858 |
| Open issues | 300 | 10 |
| Adoption | 97 | 100 |
| Activity | 36 | 92 |
| Community | 100 | 99 |
| Issue health | 96 | 96 |
| License | 96 | 96 |
| Self-hosting | 100 | 100 |
| Composite | 83.9 | 97.2 |
🐙 Guides, papers, lessons, notebooks and resources for prompt engineering, context engineering, RAG, and AI Agents.
Agent skills that give coding agents taste: art direction, reference images and a browser check instead of generic AI pages
taste-skill has more GitHub stars: 117,459 versus 80,149 for Prompt-Engineering-Guide. The gap is 37,310 stars.
taste-skill was pushed more recently: 08 November 2026 versus 11 March 2026 for Prompt-Engineering-Guide. That is 242 days apart.
Yes. This catalog marks both Prompt-Engineering-Guide and taste-skill as self-hostable. Confirm each project's deploy docs before you plan a migration.
Prompt-Engineering-Guide is listed as MIT, which this catalog treats as a permissive grant. A company can usually ship it inside a commercial product and keep its own application code private, provided it keeps the copyright notice. taste-skill is listed as MIT, which this catalog treats as a permissive grant. A company can usually ship it inside a commercial product and keep its own application code private, provided it keeps the copyright notice. Read both grants before you embed either codebase in a hosted product. This is not legal advice.
taste-skill scores 97.2 and Prompt-Engineering-Guide scores 83.9. This page calls that a clear lead for taste-skill.