Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Guide developers through creating and updating MCP apps. Covers the full lifecycle: brainstorming ideas against UX guidelines, bootstrapping projects, implementing tools/views, debugging, running dev servers, deploying and connecting apps to ChatGPT. Use when a user wants to create or update a MCP app, MCP server or use the Skybridge framework.
.claude/skills/alpic-ai-mcp-app-builder/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-09 | ✗→✓ | ▲ Improved | -31% | 0% |
| case-10 | ✗→✓ | ▲ Improved | -10% | 0% |
| case-11 | ✗→✓ | ▲ Improved | -13% | 0% |
| case-14 | ✗→✓ | ▲ Improved | -19% | 0% |
| case-15 | ✗→✓ | ▲ Improved | -10% | 0% |
Those are conversational experiences that extend AI assistants through tools and custom UI views. They're built as MCP servers invoked during conversations.
⚠️ The app is consumed by two users at once: the human and the AI Assistant LLM. They collaborate through the view—the human interacts with it, the LLM sees its state. Internalize this before writing code: the view is your shared surface.
SPEC.md keeps track of the app's requirements and design decisions. Keep it up to date as you work on the app.
No SPEC.md? → Read discover.md first. Nothing else until SPEC.md exists.
SPEC.md exists? → Read SPEC.md, then follow architecture.md to design the change. Update SPEC.md, then read the relevant Implementation references below before writing code.
Migrating from Skybridge < 0.36.x? → Read migrate-to-v1.md first. Users may reference skybridge >= 0.36.x as v1.
Migrating from Skybridge 1.x to 2.x? → Fetch the v2.0.0 release notes first and follow them.
Building an ecommerce app? → Read ecommerce.md first.
Design or evolve UX flows and API shape → architecture.md
Full API docs: https://docs.skybridge.tech/api-reference.md
Release notes & changelog: https://skybridge.tech/changelog.md
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 22,271 | 14,534 | -35% | 1 | 1 | 0% | 3,052 | 1,074 | -65% | 0 | 0 | — |
case-02 | fail→fail | 24,662 | 17,897 | -27% | 1 | 1 | 0% | 3,290 | 1,875 | -43% | 0 | 0 | — |
case-03 | fail→fail | 25,335 | 25,675 | +1% | 1 | 1 | 0% | 3,641 | 4,761 | +31% | 0 | 0 | — |
case-04 | pass→pass | 18,523 | 14,335 | -23% | 1 | 1 | 0% | 2,340 | 2,581 | +10% | 0 | 0 | — |
case-05 | pass→pass | 14,435 | 11,337 | -21% | 1 | 1 | 0% | 1,775 | 2,178 | +23% | 0 | 0 | — |
case-06 | pass→pass | 10,583 | 15,762 | +49% | 1 | 1 | 0% | 2,179 | 3,094 | +42% | 0 | 0 | — |
case-07 | fail→fail | 16,726 | 12,603 | -25% | 1 | 1 | 0% | 1,954 | 2,247 | +15% | 0 | 0 | — |
case-08 | fail→fail | 14,464 | 9,596 | -34% | 1 | 1 | 0% | 1,625 | 1,633 | +0% | 0 | 0 | — |
case-09 | fail→pass | 17,405 | 2,982 | -83% | 1 | 1 | 0% | 1,980 | 1,362 | -31% | 0 | 0 | — |
case-10 | fail→pass | 19,862 | 12,946 | -35% | 1 | 1 | 0% | 2,398 | 2,149 | -10% | 0 | 0 | — |
case-11 | fail→pass | 17,007 | 8,283 | -51% | 1 | 1 | 0% | 1,827 | 1,584 | -13% | 0 | 0 | — |
case-12 | fail→fail | 16,687 | 7,769 | -53% | 1 | 1 | 0% | 1,851 | 1,229 | -34% | 0 | 0 | — |
case-13 | fail→fail | 20,143 | 12,672 | -37% | 1 | 1 | 0% | 2,576 | 2,090 | -19% | 0 | 0 | — |
case-14 | fail→pass | 18,858 | 11,779 | -38% | 1 | 1 | 0% | 2,414 | 1,967 | -19% | 0 | 0 | — |
case-15 | fail→pass | 13,659 | 7,161 | -48% | 1 | 1 | 0% | 1,383 | 1,244 | -10% | 0 | 0 | — |
case-16 | fail→pass | 15,012 | 7,264 | -52% | 1 | 1 | 0% | 1,755 | 1,242 | -29% | 0 | 0 | — |
case-17 | fail→pass | 14,008 | 6,861 | -51% | 1 | 1 | 0% | 1,503 | 1,121 | -25% | 0 | 0 | — |
case-18 | fail→pass | 18,878 | 7,007 | -63% | 1 | 1 | 0% | 2,386 | 1,189 | -50% | 0 | 0 | — |
case-19 | fail→pass | 15,979 | 7,017 | -56% | 1 | 1 | 0% | 1,826 | 1,229 | -33% | 0 | 0 | — |
case-20 | fail→pass | 14,758 | 6,939 | -53% | 1 | 1 | 0% | 1,603 | 1,158 | -28% | 0 | 0 | — |
case-21 | fail→pass | 18,226 | 7,409 | -59% | 1 | 1 | 0% | 2,106 | 1,199 | -43% | 0 | 0 | — |
case-22 | fail→pass | 14,888 | 10,379 | -30% | 1 | 1 | 0% | 1,619 | 1,867 | +15% | 0 | 0 | — |
case-23 | pass→pass | 14,365 | 7,439 | -48% | 1 | 1 | 0% | 1,448 | 1,249 | -14% | 0 | 0 | — |
case-24 | fail→pass | 18,701 | 7,065 | -62% | 1 | 1 | 0% | 2,117 | 1,149 | -46% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 24 cases were attempted, and 22 counted toward the lift figure. The other 2 produced results that are not comparable between the two arms, so they are excluded from the headline rather than averaged into it. The headline lift of +54 percentage points is the difference between those two pass rates over the 22 comparable cases.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
| Model | Method | Date | Lift |
|---|---|---|---|
| gemini-3.6-flash | verified | 8/17/2026 | +64% |
| gemini-3.6-flash | verified | 8/12/2026 | +64% |
Other measured skills in the registry, with their headline benchmark lift.