Systems Research Notes Experience About Email LinkedIn GitHub Playbook
V1 · Validating

Marketing Skills Standard

An evaluation protocol for AI marketing tools.

Every "best AI marketing skills" list ranks by GitHub stars — which measures popularity, not whether the output is any good. This is a fixed, versioned rubric that scores real outputs with quoted evidence for every deduction, so a comparison is reproducible instead of a vibe.

How it works

Every skill is tested against the same standard brief for its capability, then scored across six fixed dimensions. The one rule that doesn't bend: every deduction needs a quoted line from the actual output. Not "this feels generic" — the sentence that made it generic.

The check

Before an evaluation is published, a CI check recalculates the overall score from its six dimension scores and verifies the numbers agree — so the score can't quietly drift from the evidence it's supposed to be built on. It already caught a real arithmetic slip in one of the evaluations before it shipped.

Initial results — MSS v1, LinkedIn post writing

kostja94/marketing-skills LinkedIn Post Writing 8.05
mysticaltech/marketingskills LinkedIn Post Writing 7.50
gooseworks-ai/goose-skills LinkedIn Post Writing 7.15

Preliminary — full write-ups with quoted evidence are in the repo's EVALUATIONS/ directory.

Ask my CV