Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add OutSystems/outsystems-mcp --skill outsystems-design-to-appgit clone --depth 1 https://github.com/OutSystems/outsystems-mcpWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/outsystems/outsystems-mcp/outsystems-design-to-app)<a href="https://agentmods.dev/skills/outsystems/outsystems-mcp/outsystems-design-to-app"><img src="https://agentmods.dev/badge/skills/outsystems/outsystems-mcp/outsystems-design-to-app/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/outsystems/outsystems-mcp/outsystems-design-to-app"><img src="https://agentmods.dev/badge/skills/outsystems/outsystems-mcp/outsystems-design-to-app.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00222 | $0.11885 |
| Opus 5.5 | $0.00089 | $0.04754 |
| Sonnet 5.5 | $0.00044 | $0.02377 |
| Haiku 4.5 | $0.00022 | $0.01188 |
Grade A, and why
outsystems-design-to-app scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 427 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Beta Feature. This skill is a Beta Feature: a non-final OutSystems capability provided to collect customer feedback. It can change significantly, including through breaking changes, or be discontinued. The first time you use this skill in a conversation, tell the user it's a Beta Feature and share https://www.outsystems.com/legal/beta-features-agreement.
OutSystems Design-to-App
Turn a design source (Figma, screenshot, HTML mockup, or front-end code) into a working OutSystems app via the OutSystems MCP / Mentor. The skill bridges three things a vanilla LLM does poorly on its own: design extraction, OutSystems UI domain knowledge, and Mentor invocation discipline. It authors an anatomy-first spec (a per-screen widget-tree of real blocks with inline styles), gates every visual element through a real OutSystems UI block, and drives Mentor in tight batches.
Load the main outsystems skill before Step 1: session, polling and publish rules come from it (read the live tool catalog, one Mentor session per task, cursor polling and waiting from a fresh context where your harness offers one, confirm before every tenant write). This skill adds only what is specific to building from a design; where the two seem to differ, the main skill wins.
Prerequisites
- The
outsystemsMCP server connected and authenticated, per the mainoutsystemsskill. - Mentor enabled on the tenant (this skill drives Mentor).
- Figma MCP server connected if the design source is a Figma URL (its design-context, variables and screenshot tools, whatever your toolset calls them). For HTML / image / code sources, the Figma MCP is not required.
- A target app. Either an existing app the user names, or a new Web app the skill creates (after confirmation) from the standard template; see Steps 1 and 5.
When NOT to use
- Just running Mentor with a free-form prompt (no design source, no spec discipline needed): drive Mentor directly with your prompt.
- Building from a written brief or spec with no design or code: this skill does not apply; build it with Mentor directly, following the main
outsystemsskill. - Adding non-visual features to an existing app (logic, data, integrations, no design source): drive Mentor directly with your prompt. Adding a screen from a design to an existing app is in scope: see "Adding a screen to an existing app" under Step 1.
- Auditing / reviewing an existing app: drive Mentor directly with your prompt.
What ships with it
45 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- agents/openai.yaml 298 B
- assets/enriched-blueprint.json 30 KB
- references/design-capture.md 18 KB
- references/gotchas/duplicate-buttons.md 1.6 KB
- references/gotchas/icon-coverage-checklist.md 4.0 KB
- references/gotchas/icon-translation-figma.md 3.7 KB
- references/gotchas/INDEX.md 4.7 KB
- references/gotchas/iterative-deployments.md 2.0 KB
- references/gotchas/publish-validator-rejections.md 1.4 KB
- references/gotchas/spa-section-visibility.md 2.4 KB
- references/gotchas/spa-shell-fallback-fidelity.md 2.9 KB
- references/gotchas/svg-icon-baking.md 2.0 KB
- references/gotchas/tablerecords-seeding.md 4.2 KB
- references/gotchas/theme-collisions.md 2.8 KB
- references/gotchas/widget-link-slot.md 2.2 KB
- references/outsystems-ui/charts.md 3.0 KB
- references/outsystems-ui/layouts.md 6.6 KB
- references/outsystems-ui/maps.md 4.2 KB
- references/outsystems-ui/patterns/adaptive.md 6.8 KB
- references/outsystems-ui/patterns/content.md 13 KB
- references/outsystems-ui/patterns/interaction.md 22 KB
- references/outsystems-ui/patterns/navigation.md 12 KB
- references/outsystems-ui/patterns/numbers.md 6.4 KB
- references/outsystems-ui/patterns/utilities.md 5.9 KB
- references/outsystems-ui/styles-and-utilities.md 12 KB
- references/outsystems-ui/ui-reference.md 27 KB
- references/screen-guides/app-type-styling.md 888 B
- references/screen-guides/calendar.md 2.7 KB
- references/screen-guides/component-selection.md 3.1 KB
- references/screen-guides/dashboard.md 3.2 KB
- references/screen-guides/design-system.md 3.5 KB
- references/screen-guides/detail-view.md 3.1 KB
- references/screen-guides/edit-form.md 3.5 KB
- references/screen-guides/gallery-grid.md 2.9 KB
- references/screen-guides/inbox-notifications.md 3.0 KB
- references/screen-guides/kanban.md 2.9 KB
- references/screen-guides/list-table.md 3.1 KB
- references/screen-guides/map-view.md 3.0 KB
- references/screen-guides/master-detail.md 2.2 KB
- references/screen-guides/reusable-blocks.md 2.2 KB
- references/screen-guides/settings.md 2.6 KB
- references/screen-guides/states-and-feedback.md 4.6 KB
- references/screen-guides/timeline.md 3.0 KB
- references/screen-guides/wizard.md 2.6 KB
- references/workflow.md 6.6 KB
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 4d ago Changed · +9 lines f8308a239178
- 6d ago First seen · 418 lines · 222 tokens per session scan A 1443670f1a79
outsystems-design-to-app is a skill published in the GitHub repository OutSystems/outsystems-mcp (40 stars, last pushed today), licensed MIT. It adds 222 tokens to every session and 11,885 once invoked, about $0.0009 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-08.
Other skills, from other repositories
sage-review
Deep, platform-neutral code review for PRs and CRs in ONE thorough single pass — design reasoning (Problem Worth Solving & Solution Fit) as one dimension alongside the 9 code-level dimensions, with chain-of-consequences, self-critique, and draft-only comments. The single app-owned source of truth.
design-critique
Run a heuristic evaluation of a UI design (image, HTML, Figma, URL, or flow) the way an experienced designer would. Evaluates 4 categories (Visual & hierarchy, Usability & interaction, Accessibility, Content) using recognized frameworks, NN/g 0-4 severity, and evaluability-aware prioritization that never judges what…
dashboard-template
Kiro Crew repo only: load this when a task will author or change a dashboard page. A page never ships alone: the same PR carries its TypedDict contract, its provider, and a parity test that the two agree. Scaffold all four from one field list; read numbers from an existing fold, never type them.
theme-pack-authoring
Build, validate, and install Kiro Crew theme packs -- pack anatomy, the 56-variable palette, role-tagged fonts, the overrides.css allowlist (what installs vs what actually renders), and the install-verify cycle. Use when the user wants to create or edit a theme pack.
image-authoring
Author images and diagrams as code — SVG, Pillow, Excalidraw, mermaid. Load when asked to draw, illustrate, or make an image, icon, logo, poster, or diagram.
frontend-design-workflow
Workflow for frontend features and visual/product design changes — present mockup options before code, build on the project's design system, capture the right evidence (screenshots vs video), run a new-user usability review. Use when building or changing UI, styling, layout or animation.