Automation & Ops Skill
Client Onboarding
Onboard a new customer, set up a new client project, or initialize FAZ 1 for a customer.
$15
Verification Gate
Automatic completion verification gate.
An automatic completion gate that runs before any task is declared done. It applies a nine-point verification checklist: build, runtime, edge cases, regression, visual proof, claim labeling, trust gaps, and automatic-fail detection, and returns a hard PASS/FAIL verdict so unverified or overclaimed work never ships.
$15 one-time
Add to a kit → Prices include 20% VAT. · Forged on real agency work · one-time, no lock-in
- Type Skill
- Category Automation & Ops
- Delivery Email · instant
- License One-time
Inside the run · no black box
See the actual work before you buy it.
"Done" is a verdict, not a feeling. Nine gates stand between a finished task and the right to claim it, and a single auto-fail condition blocks the claim outright:
- Build gate first: type check, production build and lint must all come back with zero errors; cheap checks run before expensive ones, and the first fail already decides the verdict.
- Runtime gate on the live system: the production URL is hit for real, and not just for a 200 response; the specific symptom the fix claims to solve is what actually gets tested.
- Edge cases: at least two alternate scenarios run every time, like empty data, a logged-out user or a different language.
- Regression and visual pass: neighbouring features get re-checked so the fix didn't break what already worked, and UI work gets screenshots at three breakpoints.
- Claim audit: every assertion is tagged as verified, inferred, assumed or not verified; an unproven claim stated in confident language counts as an automatic fail.
- Final verdict: a line-per-item PASS/FAIL report; any single auto-fail condition (no rollback path, untested production change, output that looks good but cannot be measured) blocks the done claim until fixed.
One power source. 6 lines out.
verification-gate · core
core active · 6 lines
- ✓ final check before decla…
Final check before declaring a task or fix complete
- ✓ pre-deploy quality gate
Pre-deploy quality gate ahead of production
- ✓ automated gate before a
Automated gate before a pull request merge
- ✓ phase-transition checkpo…
Phase-transition checkpoint in multi-phase projects
- ✓ catching overclaim before
Catching overclaim before a status report goes out
- ✓ verifying a fix targets
Verifying a fix targets its specific symptom, not just HTTP 200
Yours to keep.
Drag time forward. Watch what stays.
Forever
That's what owning means.
The rented stack
ai writing tool: subscription
expired · access lostanalytics suite: subscription
expired · access lostdesign platform: subscription
expired · access lost(nothing left)
Your forge
-
Tasks can't be closed until live, symptom-level proof exists
license: perpetual -
Overclaiming is caught by enforced VERIFIED/INFERRED/ASSUMED labeling
license: perpetual -
Regressions surface before users do, with neighbor-feature checks
license: perpetual -
Every completion carries a clear PASS/FAIL verdict and remediation action
license: perpetual
subscriptions expire · deeds don't
Everything in the box.
Pick a piece up. Watch it work.
Nine-point checklist: build, runtime, edge cases, limits, regression, and more
6 parts · one working system · ships instantly by email
This wasn't forged for everyone.
- Not for you if you'd rather rent a tool than own one.
- Not for you if you want someone else to run your stack.
- Not for you if you're happy guessing.
Builders and teams who want an enforced final gate that blocks unverified, overclaimed, or regression-risk work from being called done.
then this was forged for you.Works with
Universal by design: these run in any AI. Delivered in the open Agent Skills + MCP format (native in Claude); ChatGPT, Gemini, Cursor and Copilot adapt the same files their own way.
- Claude Native format
- ChatGPT Adapts via open standards
- Gemini Adapts via open standards
- Cursor Adapts via open standards
- Copilot Adapts via open standards
Catch what's on your mind.
the air is clear. nothing between you and the forge.
catch a spark: the forge will answer
-
I'm a solo developer shipping small fixes, isn't a nine-point gate overkill?
The gate scales to the change. Config-only, migration, and documentation changes go through explicit exception handling instead of the full checklist, while anything touching runtime behavior still gets symptom-level proof. Solo work is where unverified 'done' claims slip through most easily.
-
How does it actually catch overclaiming instead of trusting my word?
Two mechanisms. Every assertion must carry a VERIFIED, INFERRED, or ASSUMED label, and verification targets the specific symptom the fix claims to solve rather than a bare HTTP 200. If live proof is missing or a label is inflated, the verdict is FAIL with a remediation action.
-
Once the verdict comes back FAIL, will the gate also write the remediation for me?
No. The gate blocks the completion claim and returns a per-item PASS/FAIL with what's missing, but writing the fix and re-running the gate is your job. It's a referee, not a repair crew.
-
How is it delivered?
By email right after purchase: ready to run, downloaded instantly, no setup wait.
-
One-time or subscription?
A one-time purchase; no subscription or hidden fees. VAT (20%) is included.
-
Can I get a refund?
As a digital product, it can’t be refunded once downloaded. That’s why we show exactly what’s inside and who it’s for, right here.