Custom builds by Wondel.ai
We build the skills you already use.
Now we'll build yours.
Custom Claude skills, subagents and MCP integrations — from the team behind the open-source wondelai/skills. Shipped to production, not demoed.
1,956 stars on GitHubFor teams who want senior-level Claude work shipped — not another impressive demo.
---
name: acme-support-triage
description: Triage inbound support tickets the
way our senior team does — classify, draft, escalate.
---
## When to use
Every new ticket that lands in the queue.
## Steps
1. Classify: billing · bug · feature · churn-risk
2. Pull account history via the Zendesk MCP.
3. Draft a reply in our voice, and cite the doc.
4. Escalate churn-risk to #cs-leads.02 The problem
Impressive in the demo.
Gone by the pilot.
Most AI projects die in the gap between impressive and shipped.
03 What we build
Three layers of one system.
Skills, agents and the plumbing that connects them — built against evals, shipped into your stack.
Custom Skills
Your team's know-how, packaged as skills Claude loads every session.
Custom Agents & subagents
Reviewers, debuggers, data-scientists — agents scoped to do one job well.
MCP & internal libraries
Secure connectors into your systems, plus a library that compounds.
MCP is the hands, Skills are the know-how, subagents are the orchestration — a serious build usually needs all three.
04 The proof is public
You've already used our work.
Founded by Michał Jaskólski — built and sold two companies, shipped consumer products to 4M+ users a month. This studio ships the open skills you can already read, star and run.
05 How we work
Eval-driven, from day one.
Discovery
We map the time-consuming, repeatable workflows — the tasks where your team pastes the same context every single time.
Baseline & evals
Before a line of code, we run Claude without the skill, document where it fails, and turn those failures into evals. Evals become the source of truth.
Design & build
We pick the right primitive — Skill, subagent, MCP, hook or Agent-SDK app — and build against the evals, not vibes.
Ship to production
Version-controlled, integrated with your tools, and deployed where your team already works — not left behind in a notebook.
Iterate & maintain
We watch real usage, expand the evals, and keep everything current as the models and your needs move.
Evals are the deliverable, not an afterthought.
06 Engagements
Start small. Scale what works.
Sprints and builds are fixed-scope, fixed-price; the retainer is a fixed monthly fee. Bring a workflow to the 15-minute call and you’ll leave with a price range — the scope, timeline and price follow in writing before any work starts.
Skill / Agent Sprint
Fixed price · fixed scope
A paid proof of concept that de-risks the jump from pilot to production.
Most chosen
Custom Build
Fixed price · per milestone
A production build — skills, agents and the MCP plumbing that connects them.
Skills-Library-as-a-Service
Fixed fee · retainer
An evolving internal library of skills and agents that compounds every month.
Fixed-price engagements, quoted after a 15-minute call. Shipped to production, or you don't pay the final milestone.
07 Straight answers
The questions you're actually asking.
01 Is this just prompting?
No. The work is evals and context engineering — defining what “good” means, then designing skills, tool scoping and model routing to hit it repeatably. Prompting is the easy 10%.
02 How much does it cost?
It depends on the workflow, so we quote after a 15-minute scoping call instead of publishing a rate card. Sprints and builds are fixed-scope and fixed-price — a Sprint is the smallest unit, a Build is billed by milestone — and the Library retainer is a fixed monthly fee. On the call you get a price range; the scope, timeline and price follow in writing before any work starts. Prefer email? Send the workflow to support@wondel.ai and we’ll reply with a range.
03 What happens on the scoping call?
Fifteen minutes. You describe the workflow that eats your team’s time; we tell you whether it’s a skill, an agent or an MCP job, what a first sprint would cover, and a price range. No slides, nothing to prepare — and if it isn’t a fit, we’ll say so on the call.
04 Who maintains it after launch?
You can, or we do. The Library retainer keeps your evals green, expands coverage, and handles model upgrades so nothing quietly drifts.
05 Is our data and security safe?
We treat a skill like installing software: least-privilege subagents, MCP servers scoped to exactly what they need, and secrets kept off surfaces that never require them.
06 Are we locked into Claude?
Skills are built on the open agentskills.io standard, so the know-how stays portable to other compatible agents. You own the artifacts either way.
You'll leave with a price range. Scope, timeline and price follow in writing.
Bring one workflow to a 15-minute call.
Fixed-price engagements, quoted after a 15-minute call. Shipped to production, or you don't pay the final milestone.