Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/skyciv/skyciv-ai-skillsnpx agentmods add skills/skyciv/skyciv-ai-skills/cloudcad-apiWrote 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/skyciv/skyciv-ai-skills/cloudcad-api)<a href="https://agentmods.dev/skills/skyciv/skyciv-ai-skills/cloudcad-api"><img src="https://agentmods.dev/badge/skills/skyciv/skyciv-ai-skills/cloudcad-api/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/skyciv/skyciv-ai-skills/cloudcad-api"><img src="https://agentmods.dev/badge/skills/skyciv/skyciv-ai-skills/cloudcad-api.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00237 | $0.04411 |
| Opus 5.5 | $0.00095 | $0.01764 |
| Sonnet 5.5 | $0.00047 | $0.00882 |
| Haiku 4.5 | $0.00024 | $0.00441 |
Grade A, and why
cloudcad-api 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 14d 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 — 228 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CloudCAD API — 2D drawings
Build a CloudCAD drawing as a JSON object (cad_data), send it with cloudcad.model.create, then
store it with cloudcad.file.save. This skill covers the cad_data schema and the
cloudcad.model / cloudcad.file namespaces.
Prerequisite: auth,
optionsand the{ auth, options, functions }envelope are inskyciv-api-v3. NoS3D.session.startis needed.cloudcad.model.createopens its own CloudCAD session (verified: without it, create returns "CloudCAD session successfully created." and a followingsaveworks). AddingS3D.session.startfirst does no harm but adds about 6 s.
Units: every coordinate and every length setting is real-world millimetres, whatever
settings.canvasLengthUnits says. That setting ("mm", "cm", "m", "ft", "in") only
changes how dimension labels are displayed. Verified: a 7315.2 mm line with
canvasLengthUnits: "ft" is labelled 24.0 ft.
Workflow
- Draw at true size, in mm, with y negative going up (see Coordinates). Never scale geometry to fit a page.
- Pick a plot scale and size the
attributeStylesfor it. Every length-valued style setting is printed mm × scale, e.g.dimensionTextSize: 378at 1:100 prints at 3.78 mm (see Sizing). - Wrap the drawing in the default page + title block, unless the user asked for bare
geometry. Translate the content into the template's safe zone; do not scale it. See
references/pages-and-title-blocks.md. - Lint, then send
cloudcad.model.create+cloudcad.file.savein one request.createaccepts anything and returnsstatus: 0, even{}or{"canvases": "nope"}, so astatus: 0proves nothing. Run the linter (Bundled tools) and look at a render (Verifying). - Give the user the
dataURL returned bysave.
In Node, scripts/cad_helpers.js does steps 2–4: emptyCanvas, text, hatch,
rectCloud/revisionCloud, attributeStyle(plotScale),
wrapInTitleBlock({ canvas, plotScale }) and lint(cad_data). Opt-in structural data uses
s3dMember, s3dSupport, s3dColumn, s3dPlate and s3dRoot.
What ships with it
12 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.
- assets/all-elements.json 116 KB
- assets/images/axis-dashdot.svg 1.5 KB
- assets/images/block-transform.svg 1.8 KB
- assets/images/dimension-angle.svg 1.5 KB
- assets/images/dimension-linear.svg 1.6 KB
- assets/images/revision-clouds.svg 1.9 KB
- assets/title-block-a2.json 49 KB
- assets/Title-Block-Example.json 126 KB
- references/elements.md 13 KB
- references/pages-and-title-blocks.md 6.1 KB
- references/s3d-mapping.md 8.8 KB
- scripts/cad_helpers.js 18 KB runs code
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.
- 14d ago Changed · -939 lines · +237 tokens per session 1ecf490e2cc9
- 2mo ago First seen · 1,167 lines · 0 tokens per session scan A 3f1e02f1c337
cloudcad-api is a skill published in the GitHub repository skyciv/skyciv-ai-skills (11 stars, last pushed 15d ago), licensed MIT. It adds 237 tokens to every session and 4,411 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 2026-08-31.
Other skills, from other repositories
browserwing-executor
Control browser automation through HTTP API. Supports page navigation, element interaction (click, type, select), data extraction, accessibility snapshot analysis, screenshot, JavaScript execution, and batch operations.
dstack-prototyping
Use with the dstack skill for model-serving work when the image, serving command, resources, backend/fleet choice, or service behavior is not proven. Guides task-first prototyping on real hardware, choosing fleets/backends that can reuse idle instances and caches, checking vLLM/SGLang sources, and verifying the final…
ranui
Build or modify products using ranui web components or ranui/builder. Resolve the installed component APIs, theme tokens, form behavior and lifecycle contracts before implementation.
sequence-diagrams
Create animated sequence diagrams showing interactions between participants using the Excalimate MCP server. Use when asked to visualize API call sequences, message flows, protocol handshakes, request/response patterns, authentication flows, or communication between services, users, and systems.
form-list-layout
Configure what a form and a list look like — sysuiform, sysuisection and sysuielement for forms; sysuilist, sysuilistelement and sysuirelatedlist for lists; sysfilter for saved filters. Views, why a field must exist in the dictionary first, and what snowcreatemenu really writes.
spine-design
Produce a system design doc — components, data flow, decisions made, tradeoffs, failure modes. Not a list of options. An actual design with calls made. Use when asked for "system design for", "architect this", "how should we build", or "design the backend".