Side-by-side comparison · skills
eval-engineering vs review
What we have checked about each, line by line. Every value shows where it came from and when we last confirmed it.
Skills
eval-engineering
Inspect an agent repository and optional traces, interview the user, write reviewed Task Specs, build and audit Harbor tasks, and bootstrap reusable project World Knowledge…
Skills
review
"Extend with llm, stabilise with code" - Prompts when you're exploring, Python when you're certain. Workers and tools form one function space—refactor between them.
Checked facts
Line by line
| Measure | eval-engineering | review |
|---|---|---|
| Security check (static checks) | 100 out of 100 | 100 out of 100 |
| Days since the last commit | 0 | 257 |
| GitHub forks | 111 | 4 |
| GitHub stars | 1,340 | 21 |
| Installs | 5.3K | Not checked yet |
| Days to a first reply on issues | 58.2 | Not checked yet |
| Open issues | 2 | 0 |
| Releases in the last 90 days | 0 | 0 |
A line appears only when at least one record has a value we confirmed from a source. Values we have not confirmed are left out, never guessed. Records of different types share fewer lines.
Add a third
Compare with one more record
How this works
Share it, or build your own
This page works for any two or three records in the directory, of any type. The link stays the same whichever order you name them in, so you can share it as it is. Change the records in the address, for example /directories/vs/claude-code-vs-cursor, or start from our editorial comparisons.