EveryInc/compound-engineering-plugin, tested in 1 task class
Skills from EveryInc/compound-engineering-plugin were tested in 1 kind of task. Results come one kind of task at a time, and never added up into one number.
Across the classes it was tested in
How many task classes each result fell in. Counts of classes, not scores.| What happened | Classes | Which |
|---|
| Made worse | 1 | Code review |
|---|
We do not add these together. A skill-authoring score is a share of requirements met. A voice score is how often a blind reader preferred it. They are different measurements of different things, so a single number over both would be a figure neither test produced. The numbers are on the skill pages, where each was measured.
Per model
GPT-5 mini
GPT-5 mini: classes by result.| What happened | Classes | Which |
|---|
| No reliable difference | 1 | Code review |
|---|
Gemini 3.1 Flash Lite
Gemini 3.1 Flash Lite: classes by result.| What happened | Classes | Which |
|---|
| Made worse | 1 | Code review |
|---|
Each model is named by the string the vendor actually served, not by the one the run requested.
Coverage, class by class
What was done in each class for this repository. The full grid is on the coverage page.| Class | State | What that means |
|---|
| Skill authoring | No qualifying skill | We looked through this repository for this kind of task and found nothing that met the bar we publish. |
|---|
| Accessibility audit | No qualifying skill | We looked through this repository for this kind of task and found nothing that met the bar we publish. |
|---|
| Spec writing | No qualifying skill | We looked through this repository for this kind of task and found nothing that met the bar we publish. |
|---|
| On-page audit | No qualifying skill | We looked through this repository for this kind of task and found nothing that met the bar we publish. |
|---|
| Voice | No qualifying skill | We looked through this repository for this kind of task and found nothing that met the bar we publish. |
|---|
| Code review | Tested | We ran this one. The same tasks were done with the skill loaded and again without it, and the numbers are on that skill's own page. |
|---|
| Test writing | Not verified | We have not checked. Nothing has been written down either way, and this site is not claiming anything about it. |
|---|
Identity pins
Every skill from this repository that holds a slot, and the commit its arm was given.| Class | Path | Commit | Content hash | Date tested |
|---|
| Code review | skills/ce-code-review | c9c10f8c7541 | bd5c9fac33fb | not yet tested |
|---|
Licence status, per pin
What the licence check found beside each set of pinned bytes, run against that pin's own commit.| Pinned bytes | Licence | Licence file | Checked at |
|---|
| skills/ce-code-review slot | MIT | LICENSE | c9c10f8c7541 2026-08-31 |
|---|
We record the licence for each file we tested, not for the whole repository. Some repositories have no licence at the top and license each skill folder on its own, and one of the files here has no licence at all. Each row is a check against that file's own commit. A row reading not recorded means we have not run the check on those bytes yet. A row reading no licence file means we ran it and found none. Nothing here is guessed from a repository name.
- skills/ce-code-review: MIT at the repository root. No licence file exists inside the pinned skill directory, so the root grant governs these bytes. Read per candidate directory by the 2026-08-31 recon, section 5, and re-confirmed against the GitHub contents API for this pin.