agentleFS
PageproPagepro/nexity/.agents/skills/product-mock/SKILL.md

product-mock

Skill19 starsChanged 12 days agoMITView on GitHub

Add, change or re-export an HTML-rendered product mock for a project with tools/product-mocks and pnpm mocks:build. Use for a new product screen, changes to an existing one, or fresh PNGs for Sanity.

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 3 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Don't restyle a screen with the marketing palette, Mona Sans or the card-frame double border.

    line 56
  2. Distinctive:

    Don't bake the panel's outer border or rounded corners into the PNG.

    line 58
  3. Distinctive:

    Don't export at the window's size.

    line 59
  4. Very specific:

    Don't use real brand logos in a screen.

    line 61
  5. Very specific:

    Don't commit tools/product-mocks/out/ (git-ignored).

    line 63

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Product mock

The generator lives in tools/product-mocks/ and the root script pnpm mocks:build runs it. If that directory is missing, this skill does not apply; product images are ordinary Sanity image assets.

test -d tools/product-mocks && echo "product mocks: yes" || echo "product mocks: no"

The product images on the site are HTML mocks in tools/product-mocks/, rendered on the product tokens (the dashboard, product.py) and placed on the tinted dune panel (mocks.py). pnpm mocks:build writes the gallery tools/product-mocks/out/index.html; each panel has a Save PNG button that renders it at the Sanity asset size. The full guide, with the rules, is docs/guides/product-mocks.md. Read it first.

Input

What the user wants: a new screen (which capability, which numbers), a change to an existing one, or just a re-export. Which split-section row it is for decides the alignment (right when the image sits on the right of the row, left otherwise) and the tint (peach, sage, rose, cycling with the row index).

Steps

  1. Read tools/product-mocks/mocks.py and, for dashboard changes, tools/product-mocks/dashboard.py. Find the closest existing screen; winloss() is the simplest template.
  2. Write the screen as name(pins=True, align="right") from the existing atoms (frame, metric, hbar, area, tag, the .app utility classes). Product tokens only (--p-*); never a marketing token, never a new colour. Real copy, no lorem ipsum, and only names from the invented Meridian world in BRAND.md (no real companies or people). Two pins naming the capabilities the site's bullet list mentions, right-side pins kept inside the panel (right:.75rem).
  3. Register it in DIVES and GALLERY. New lucide icon? Run node tools/product-mocks/extract-icons.mjs <name> (needs web/node_modules).
  4. Build and check: pnpm mocks:build, open the gallery in a browser, look at both variants at a normal window width. Content must fit the 4:3 panel at the export width (680px); if the gallery says the panel is taller, cut a row.
  5. Export: click Save PNG for each variant. Files are named meridian-<slug>-<right|left>-1360x1020.png (hero/dashboard: …-2880x1605.png). The export drops the outer hairline and corners on purpose: the site draws them in code (HeroSection, SplitSections). Never add a border to the PNG.
  6. Hand over: tell the user which Sanity field each file goes to (row image, hero productImage, CTA image) and the alt text to use. In local dev, deleting web/.next/dev/cache/fetch-cache and restarting shows the new asset.

Don't

  • Don't restyle a screen with the marketing palette, Mona Sans or the card-frame double border. Screens look like the product, the panel looks like the site.
  • Don't bake the panel's outer border or rounded corners into the PNG.
  • Don't export at the window's size; the button already renders at a fixed design width so the file is exactly 1360×1020 or 2880×1605.
  • Don't use real brand logos in a screen. tools/product-mocks/assets/ holds fictional integration marks; add new ones the same way.
  • Don't commit tools/product-mocks/out/ (git-ignored).

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.