pe-brand-assets SKILL.md skillA
pe-brand-assets from backnotprop/product-engineering is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add backnotprop/product-engineering/pe-brand-assets@git:20260826.fdc4ed2Pins git:20260826.fdc4ed2 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- backnotprop/product-engineering
- Path
skills/pe-brand-assets/SKILL.md- Versions recorded
- 2
- Latest version
- git:20260826.fdc4ed2, committed Aug 26, 2026
- First version recorded
- Aug 26, 2026
- Size
- 5,362 bytes
- Repository stars
- 25
- License
- Apache-2.0
Create standalone visual assets that stay on brand — SVG illustrations for articles and blog posts, repo and social/OG images, logo and identity work, on-brand concept images for features. Authors SVG in code. Reads the project's brand truth (DESIGN.md, style guides, a brand/ folder) first and refuses to invent brand values. Triggers on brand asset, on-brand, SVG illustration, article image, header image, og image, social card, repo image, logo, brand kit, identity, tagline panel. Not for UI…
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Brand Assets Standalone assets that belong to the brand, authored as SVG in code and exported to raster where the destination requires it. ## The workflow 1. **Locate brand truth — or stop.** Read, in order: `DESIGN.md` (the pe-design skill's understand mode owns its format), any style guide, and a `brand/` folder (logos, fonts, reference assets) if present. Index what exists: palette tokens, type choices, radii/shape language, existing marks and motifs. If none of these exist, do not invent a brand — offer to run pe-design·understand first, or proceed only with values the user supplies in the conversation, labeled as provisional. 2. **Derive the asset's rules.** Colors come only from the brand palette (cite the token names). Type in the asset is the brand's faces. Shapes follow the recorded shape language. The metaphor comes from the identity method (`references/identity-method.md`). **Restraint is the default register**: the strongest brand asset is often type set well on a quiet ground. Marks, shapes, and illustration must earn their way in — propose the typographic answer first, and add a drawn element only when the user …
Read the whole file at its exact version.
How to install
mdr add backnotprop/product-engineering/pe-brand-assets@sha256:1a5ca8c74917a081The line at the top of this page pins the label git:20260826.fdc4ed2, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_j4uplghh7xxydtom)
4 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 2 versions of this file, all committed on Aug 26, 2026.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260826.fdc4ed2 latest | 2026-08-26 | fdc4ed2 | 5,362 B | A | view · diff |
| git:20260826.4e34f3c | 2026-08-26 | 4e34f3c | 4,487 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (5362 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
backnotprop/product-engineering · 25 stars · license Apache-2.0 · pushed 2026-08-30 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_j4uplghh7xxydtom GET https://markdownregistry.com/api/v1/resolve?ref=backnotprop/product-engineering/pe-brand-assets GET https://markdownregistry.com/api/v1/blob/1a5ca8c74917a0814ea164797dbcf5f6a191d2f2af855307bd6939a7d1acc416
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.