studio-grade SKILL.md skillB
studio-grade from arjunkshah12345-hash/studio-grade is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add arjunkshah12345-hash/studio-grade/studio-grade@git:20261020.c45b7f0Pins git:20261020.c45b7f0 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- B, 16 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- arjunkshah12345-hash/studio-grade
- Path
studio-grade/SKILL.md- Versions recorded
- 7
- Latest version
- git:20261020.c45b7f0, committed Oct 20, 2026
- First version recorded
- Oct 14, 2026
- Size
- 25,269 bytes
- Repository stars
- 4
- License
- MIT
Agency-grade web design for websites, landing pages, marketing sites, product launches, portfolios, e-commerce, and redesigns. Built from measured teardowns of 99 live sites shipped by top studios (basement.studio, Bakken & Bæck, Work & Co, AREA 17, Instrument, Exo Ape, Locomotive, Lusion, Immersive Garden, Unseen, Malvah, The First The Last, and others) plus in-house teams like Linear, Stripe, Vercel, and Apple. Use it whenever a frontend's visual quality matters, or when the user asks for…
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
# Studio Grade: design like the studios that win This skill comes from measuring live client work, not from taste. We loaded 99 sites in headless Chrome at 1440px and 390px, read their computed styles and mined their JS bundles for motion values. The sites were shipped by about 40 studios (the evidence list is in `references/evidence.md`). Every number below is a measured range from real sites. When this file says "64px", it means the median of Linear, Vercel, Ramp, and Raycast, not a guess. The finding behind all of it: **top-tier work is *disciplined* in a very specific, measurable way. AI-generated work is *noisy* in a very specific, measurable way.** Discipline is about count (one idea, one type system, one colour logic), not volume. Some of the best sites studied are quiet (Totême, Aesop); some are loud (Lando Norris, MindMarket, Norton, Obama). This skill teaches discipline at every volume and bans noise. …
Read the whole file at its exact version.
How to install
mdr add arjunkshah12345-hash/studio-grade/studio-grade@sha256:127cdcf51174f962The line at the top of this page pins the label git:20261020.c45b7f0, 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_goflknv3qickckgk)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 7 versions of this file, between Oct 14, 2026 and Oct 20, 2026, more than one a day.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261020.c45b7f0 latest | 2026-10-20 | c45b7f0 | 25,269 B | B | view · diff |
| git:20261020.4b02d69 | 2026-10-20 | 4b02d69 | 25,204 B | B | view · diff |
| git:20261020.7fe8609 | 2026-10-20 | 7fe8609 | 23,893 B | B | view · diff |
| git:20261017.a0bb893 | 2026-10-17 | a0bb893 | 23,893 B | B | view · diff |
| git:20261017.875a354 | 2026-10-17 | 875a354 | 23,796 B | B | view · diff |
| git:20261014.b2bbf92 | 2026-10-14 | b2bbf92 | 23,751 B | B | view · diff |
| git:20261014.61d6436 | 2026-10-14 | 61d6436 | 23,560 B | B | view |
Audit of the latest version
- fail: No script tag (matched: <script)
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (25269 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
Starting a new one? Use a template for SKILL.md on mdpantry, which passes every one of these checks and says what to change in it.
Source
arjunkshah12345-hash/studio-grade · 4 stars · license MIT · pushed 2026-10-20 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_goflknv3qickckgk GET https://markdownregistry.com/api/v1/resolve?ref=arjunkshah12345-hash/studio-grade/studio-grade GET https://markdownregistry.com/api/v1/blob/127cdcf51174f962428443179bd5789e784e6369c1d17fbb0b88e2752fd4c62c
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.