rampstackco/claude-skills, tested in 6 task classes

Skills from rampstackco/claude-skills were tested in 6 kinds of task. Given one kind of task at a time, and never added up into one number for the repository.

Across the classes it was tested in

How many task classes each result fell in. Counts of classes, not scores.
What happenedClassesWhich
Helped clearly1Spec writing (paired)
Helped on some4Skill authoring, Accessibility audit, On-page audit, Voice
No reliable difference2Spec writing (deterministic), 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

Claude Haiku 4.5

Claude Haiku 4.5: classes by result.
What happenedClassesWhich
Helped clearly3Skill authoring, Accessibility audit, Spec writing (paired)
No reliable difference3Spec writing (deterministic), On-page audit, Voice

GPT-5 mini

GPT-5 mini: classes by result.
What happenedClassesWhich
Helped clearly2Skill authoring, Spec writing (paired)
No reliable difference5Accessibility audit, Spec writing (deterministic), On-page audit, Voice, Code review

Gemini 3.1 Flash Lite

Gemini 3.1 Flash Lite: classes by result.
What happenedClassesWhich
Helped clearly3Spec writing (paired), On-page audit, Voice
Helped a little, under our bar1Skill authoring
No reliable difference3Accessibility audit, Spec writing (deterministic), 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.
ClassStateWhat that means
Skill authoringTestedWe 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.
Accessibility auditTestedWe 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.
Spec writingTestedWe 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.
On-page auditTestedWe 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.
VoiceTestedWe 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.
Code reviewTestedWe 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 writingNo qualifying skillWe looked through this repository for this kind of task and found nothing that met the bar we publish.

Identity pins

Every skill from this repository that holds a slot, and the commit its arm was given.
ClassPathCommitContent hashDate tested
Skill authoringskills/skill-creation-walkthrough0479242522548d539bb7a9772026-08-30
Accessibility auditskills/accessibility-audit0479242522547b564cd314772026-08-30
Spec writingskills/pm-spec-writing04792425225479637738ca622026-08-30
On-page auditskills/seo-onpage047924252254045b5110b9c92026-08-30
Voiceskills/brand-voice04792425225405eb2402e3e22026-08-30
Code reviewskills/code-review-weba67dd34c609fa27bba135184not 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 bytesLicenceLicence fileChecked at
skills/skill-creation-walkthrough slotNot recordednoneNot recorded
skills/accessibility-audit slotNot recordednoneNot recorded
skills/pm-spec-writing slotNot recordednoneNot recorded
skills/seo-onpage slotNot recordednoneNot recorded
skills/brand-voice slotNot recordednoneNot recorded
skills/code-review-web slotNot recordednoneNot recorded

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.

Everything on this page is worked out at build time from the runs we committed. We publish only the file we tested and where it came from. No description, no README, no star count, no install line.