Development Skill
Angular Migration
Migrate from AngularJS to Angular using hybrid mode, incremental component rewriting, and…
$15
Prime Architect
Read-only 7-dimension system auditor
A read-only chief architect that scans every dimension of a project, surfaces invisible cross-dimension links, and returns a prioritized reality map with the highest-leverage opportunities. It deliberately cannot edit anything: the output is a dispatch plan: findings ranked by impact against effort, each one named to the specialist who should execute it, so the scan ends in decisions, not a report that sits.
$79 one-time
Add to a kit → Prices include 20% VAT. · Forged on real agency work · one-time, no lock-in
- Type Agent
- Category Development
- Delivery Email · instant
- License One-time
Inside the run · no black box
See the actual work before you buy it.
This auditor carries no write tools by design. It sweeps a project across seven dimensions, hunts the cross-dimension chains where one missing schema becomes rising acquisition cost, and returns a dispatch plan instead of touching anything.
- Reads the system rule index, the rules covering the dimensions under review and recent audit reports first, so it never rediscovers known gaps that are already on the open audit list.
- Runs a strictly read-only structural scan: project context, package and config files, source tree, file structure and the live site. It deliberately has no write tools, so it cannot mutate anything while auditing.
- Sweeps the project across seven dimensions (UI/UX, code, SEO, marketing, security, FinOps, psychology) with a key question per dimension, doing the structural pass itself and marking data-heavy dimensions for a specialist to deepen later.
- Hunts cross-dimension chains, its signature output: a missing schema cascades into AI-search invisibility, organic decline and rising acquisition cost; a slow page hits not just UX but quality score and ad cost. Single-dimension findings are considered incomplete.
- Prioritizes every opportunity with an impact times ease score and surfaces only the top three, each backed by structural evidence like a grep match, an HTTP status or a file tree count. Anything it could not verify structurally stays labeled as inference.
- Returns a dispatch plan instead of dispatching: each work item names the right agent or team and carries a complete mission brief (goal, scope, out of scope, done criteria, verification) that the main thread can apply as-is. The agent itself never spawns other agents.
One power source. 5 lines out.
prime-architect · core
core active · 5 lines
- ✓ a 360 health scan of a s…
A 360 health scan of a site or system
- ✓ finding what is missing
Finding what is missing across SEO, speed, data and UX
- ✓ prioritizing opportuniti…
Prioritizing opportunities by impact and effort
- ✓ tracing a cross-dimension
Tracing a cross-dimension chain (schema → AEO → traffic → CAC)
- ✓ producing a dispatch blu…
Producing a dispatch blueprint for specialists
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
-
See the whole system, not one symptom at a time
license: perpetual -
Spend effort where it actually moves the needle
license: perpetual -
Catch hidden links a single-domain review misses
license: perpetual -
A prioritized plan instead of a scattered to-do list
license: perpetual
subscriptions expire · deeds don't
Everything in the box.
Pick a piece up. Watch it work.
Seven-dimension read-only scans across product, tech, SEO, data, ops, finance and growth
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.
Owners who want the full picture before deciding where to invest.
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 suspect my site has problems but cannot name them, is this the right starting point?
That is its exact use case. It runs a read-only scan across seven dimensions: product, tech, SEO, data, ops, finance and growth, and returns a reality map that separates what exists from what is assumed. You come out with named, ranked findings instead of a vague feeling that something is off.
-
How does it prioritize findings instead of dumping a 50-item list on me?
Every finding is scored as impact times (10 minus effort), producing a top-3 opportunity shortlist, and the scan looks for cross-dimension chains a single-domain review misses, like speed feeding CWV feeding quality score feeding CPC. The output is a dispatch plan naming which specialist should execute each item.
-
Will it fix anything it finds?
No, and that is deliberate. It is read-only by design with zero file edits; the deliverable is the plan, not the patch. Each finding is assigned to the specialist who should execute it, so the audit role and the execution role never blur.
-
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.