Learning and careers decision

SkillPass

A small team or single senior engineer can reproduce the core async interview and report export in a few months, but matching SkillPass's GDPR/hosting claims, voice UX polish, and paid-plan polish is nontrivial; a narrow, usable replacement is realistic but the full product experience and trust signals are harder to replicate.

Visit website

Built by Kevin Baur, who ships 3 products in this index

You pay

$79/mo

$948/yr

Read off the official pricing page.

You’d pay instead

$100one-off120 h to build

$50/mo6 h/mo upkeep

On cash alone, building overtakes the subscription at 1 seat.

No open-source build does this yet

Nothing published replaces this one, so a replacement starts from an empty file. Here is what it would have to cover.

What a replacement has to do

  • Invite departing employee → guided async interview (text + optional voice) → store responses → generate structured handover report (PDF/JSON) using prompts/templates → allow download/unlock

What it still won’t have

  • Polished UX, templates and copywriting optimized for handovers
  • Branded/custom report generation and built-in priority support
  • The vendor-managed GDPR attestation, EU-hosted infrastructure, and explicit AES-256 statement
  • Ongoing product improvements, monitoring, and uptime guarantees

What remains hard

  • Product polish and ongoing maintenance
Read the build prompt

First-year cost

Keep paying

Paying is—cheaper in year one.

On cash alone, building overtakes the subscription at 1 seat.

Paid seatsseats

Money you would actually spend

Keep paying
—

Subscription price × seats × 12

Build it
—

AI build —APIs + hosting —

Time you would spend

—

—

What you would spend

What we assumed

The verdict above measures whether you could build it. This one is only about money.

Runnable build prompt

Not run yet
Build a minimal SkillPass-style service using React frontend, FastAPI backend, Postgres, and deployment on a single small cloud VM (or managed app service). Core features in scope: 1) invite flow that creates a one-time async interview link; 2) interview UI supporting typed answers and voice recording uploads; 3) transcription pipeline using a hosted speech-to-text API; 4) role-specific question generation via prompt templates and an LLM API; 5) compile answers into a structured JSON and exportable PDF report; 6) basic auth for report access and simple audit logs. Out of scope: multi-tenant billing, branded/custom report themes, enterprise SLA, and advanced analytics. Include error handling, input validation, unit tests for backend logic, and end-to-end test for the interview→report flow.
How we checked3 sources · 2/3 runs agreed · evidence score 58

How the score was reached

  • Partly verdict base52
  • 3 cited sources+3
  • Price verified on pricing page+3
  • Evidence score58

The base comes from the verdict. Everything under it is a check that either happened or did not, and each one is a fact frozen in this record rather than a judgement made at render time - so the same evidence always produces the same number.

How scoring works →

Cited sources · 3

Every page the run actually retrieved.

Integrity checks

What held up, and what did not.

✓ Price read off the page! 2 of 3 runs agreed; the verdict is the majority✓ Citations limited to fetched pages! 1 moat recorded