Borrowing it
Nothing to install: this file belongs to MAIAS-project/maias. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/MAIAS-project/maias/main/.claude/skills/maias-create/SKILL.mdgit clone --depth 1 https://github.com/MAIAS-project/maiasWrote 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/maias-project/maias/maias-create)<a href="https://agentmods.dev/skills/maias-project/maias/maias-create"><img src="https://agentmods.dev/badge/skills/maias-project/maias/maias-create/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/maias-project/maias/maias-create"><img src="https://agentmods.dev/badge/skills/maias-project/maias/maias-create.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 | $0.00057 | $0.01154 |
| Opus 5 | $0.00028 | $0.00577 |
| Sonnet 5 | $0.00011 | $0.00231 |
| Haiku 4.5 | $0.00006 | $0.00115 |
Grade A, and why
maias-create 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 10d 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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
maias-create
Turn an app description into a valid MAIAS document.
Ground rules
- Read
docs/spec/llms.txtfirst — it is the authoritative condensed spec (document shape, element taxonomy, hard rules, canonical form). Do not author from memory. - Never hand-verify — the toolchain is the referee:
./node_modules/.bin/maias validate <file>andmaias fmt --write. (If the binary is missing:npm install && npm run build.) - Study one example in
examples/that resembles the requested app (todo_listfor CRUD,social_networkfor feeds/tabs,ecommercefor catalogues/journeys,calculatorfor single-screen).
Process
-
Design before YAML. From the description, decide:
- the 2–5 primary screens (tab bar) — what the user lives in;
- the journeys (flows): each with an entry screen and an ordered screen list;
- secondary screens: details (with
:parampaths), forms (usuallypresentation: modal), settings; - which screens are gated (
auth: required) and which are shareable (deep_link: true+app.deep_links.scheme).
End the design step by showing the user a structure preview in chat — tab bar, flows, and screens as an indented tree in the exact format
maias treeprints (hand-drawn; no file exists yet). It is the contract you verify in step 5. Proceed after showing it unless the request was ambiguous — don't gate on confirmation. Format:Recipe Box — 9 screens, 3 flows Tab bar: Discover · My Recipes · Shopping Flow: discover — Browse and search recipes. ├─ discover Discover (list, tab) ├─ search Search (search) └─ recipe_detail Recipe (detail, deep_link) back→discover -
Write the document at the user-requested path (default
<app_name>.maias.yamlin the project root). Every screen and flow gets a realdescription— intent travels with structure. Give data-bearing screensstates(empty/loading/error) anddata.reads/writesusing a consistent app-wide key vocabulary. Links follow elements first (spec §4.2): anything with an on-screen affordance is an element withtarget;navigation.secondaryonly for links not laid out. -
Validate and iterate:
maias validate <file>until zero errors; then resolve warnings you introduced by accident (unreachable screens usually mean a missing link, not a missing warning-suppression). Deliberate warnings are fine — say so. -
Canonicalise and re-verify:
maias fmt <file> --write, thenmaias fmt <file> --checkand a finalmaias validate(fmt rewrites content — reorders lists, refolds scalars — so verify after it, not before). -
Summarise with the deterministic tree: run
maias tree <file>and show its output — this is the toolchain's version of your step-1 preview; if they differ structurally, reconcile before finishing (the document is the truth, but an unintended difference means you drifted from the agreed design). Offermaias diagram <file>for a Mermaid flowchart of the screen graph — it renders in GitHub, Claude, and Obsidian with no install (--flow <name>scopes large apps). -
Offer to open it in the MAIAS Browser (
npm run web --workspace maias-browser, then pick the file from the menu).
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.
- 10d ago First seen · 52 lines · 57 tokens per session scan A 81ee1f6972b9
maias-create is a skill published in the GitHub repository MAIAS-project/maias (1 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 57 tokens to every session and 1,154 once invoked, about $0.0003 per session on Opus 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 2026-08-31.
Other skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ralph with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.
make-resume
A Chinese-language tool for creating editable HTML resumes that can be changed in a browser and printed to PDF. It uses available resume templates when they are installed and otherwise provides a simpler fallback.