Borrowing it
Nothing to install: this file belongs to adobecom/da-express-milo. 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/adobecom/da-express-milo/stage/.claude/skills/author-page-from-figma/SKILL.mdgit clone --depth 1 https://github.com/adobecom/da-express-miloWrote 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/adobecom/da-express-milo/author-page-from-figma)<a href="https://agentmods.dev/skills/adobecom/da-express-milo/author-page-from-figma"><img src="https://agentmods.dev/badge/skills/adobecom/da-express-milo/author-page-from-figma/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/adobecom/da-express-milo/author-page-from-figma"><img src="https://agentmods.dev/badge/skills/adobecom/da-express-milo/author-page-from-figma.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Tool Misuse · line 513 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- medium Data Exfiltration · line 419 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
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 | $0.00085 | $0.05317 |
| Opus 5 | $0.00043 | $0.02658 |
| Sonnet 5 | $0.00017 | $0.01063 |
| Haiku 4.5 | $0.00009 | $0.00532 |
Grade A, and why
author-page-from-figma scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
> to the DA admin API via `curl POST` to `admin.da.live/source/...` How it starts
The opening of the file, as written. The whole thing — 541 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Author Page from Figma Skill
You are authoring a DA (Document Authoring) page for an existing Adobe Express block, using a Figma design purely as the content source. This skill never designs or invents an authoring structure — that decision belongs to the block's own code. Your job is to find the block's real, already-established authoring pattern and variant set, then pour the Figma content into it.
Critical rules
- Never invent authoring structure. The table shape (rows, columns,
rowspan/colspan, header format) must be copied from a real example — nala test fixture, kitchen sink page, or (last resort) reasoned from code — never assembled from a generic template. Seeagents/block-structure-resolver.md.- Never invent variant class names. A variant is a code fact. Match against the block's actual known variants; never write a plausible-sounding class that isn't confirmed to exist. See
references/variant-matching.md.- The block name in Figma rarely matches the code name exactly. Always resolve and confirm against the real block folder list in
express/code/blocks/. Seereferences/block-name-matching.md.- Not all visible Figma text is authorable content. Some blocks source UI text from
/express/placeholders.jsonviareplaceKey/replaceKeyArrayinstead of the DOM. Detect this before authoring so that text isn't duplicated or misplaced. Seereferences/placeholder-detection.md.- Assets are downloaded from Figma locally, then uploaded directly to the DA admin API via
curl POSTtoadmin.da.live/source/...with multipart form data. Never embed images as base64 in DA HTML.- Never default to screenshot-cropping for images. Try
get_design_contexton the image's own (instance) node ID first —download_assets/get_screenshotonly resolve a component's default fill, not an instance override. See Phase 5.metadataandsection-metadataare not interchangeable — one is page-wide, one is per-section. Seereferences/metadata-conventions.md.- A section's own background (color/gradient/image behind the whole section, not a card or media slot) is usually not part of the block's own table — it goes through
section-metadata'sbackgroundkey instead. A block whose code has no background reference at all is exactly the case this is most likely to be missed for. Seereferences/metadata-conventions.md.- The HTML references assets using their final
content.da.liveURLs (dot-prefixed shadow folder convention).- Link URLs use
https://www.adobe.com/as a placeholder. Link display text must match Figma.- Heading levels and body sizes are determined by visual heuristics since Express Figma designs do not use
--s2a-typography-*tokens.
What ships with it
8 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.
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 · 541 lines · 85 tokens per session scan A 96119c175638
author-page-from-figma is a skill published in the GitHub repository adobecom/da-express-milo (6 stars, last pushed today), licensed Apache-2.0. It adds 85 tokens to every session and 5,317 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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.