design-grilling
Skill0 starsChanged 34 days agoMITView on GitHub
Interview method for drawing out brand, taste, and design requirements from someone who is not a designer. Use when a graphic skill needs to ask the user about their brand, preferences, or a brief.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- rob-alexa/claude-skillstheir own version, first seen Aug 23, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- rob-alexa/claude-skills★ 1same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository15 other files it gives its agents.
- AGENTS.mdAGENTS.md
- ask-designerSkill
- brand-contextSkill
- brand-imageSkill
- brand-intakeSkill
- brand-systemSkill
- color-systemSkill
- design-briefSkill
- design-craftSkill
- design-critiqueSkill
- design-routesSkill
- grill-brandSkill
- logo-labSkill
- make-graphicSkill
- type-systemSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 32
No design jargon without a one-line gloss.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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.
Files
Design grilling
Interview the human relentlessly until the brand or brief is clear. Map the subject as a design tree: every decision branches into the decisions that hang off it.
Work the tree in rounds. The frontier is every decision whose prerequisites are settled. Ask the frontier in one round, at most five questions, numbered, each with your recommended answer. Wait for the answers, recompute the frontier, ask the next round. A question that depends on another open question in the same round belongs to a later round.
❓ **Q1** - **<title>**: <question, with a one-line gloss for any design term>
➡️ <your recommended answer and why, in one line>Facts are yours, decisions are theirs
Competitors, font availability, platform sizes, and anything in their files you look up yourself. Never ask the human for what a search or a file read can settle. Put each decision to them and wait.
Show, don't tell
Taste is hard to say and easy to point at. When a question stalls, make the choice visible: two or three contrasting options as swatches, type specimens, or small mocks rendered in HTML, then ask "which feels more like you?". Contrast beats description: pick options that differ on one axis at a time.
Evidence over adjectives
When the human names or shows something they like or dislike, ask what exactly pulls them: shape, weight, spacing, color, mood, one attribute. Record the attribute with the item. "I like Nike" is trivia; "I like how one bold shape carries the whole brand" is a design requirement.
Plain language
No design jargon without a one-line gloss. Reply in the user's language. "I don't know" is an answer: turn it into a visible probe, or defer the decision with a default and a reason.
Done
The session is done when the frontier is empty: every branch is decided, deferred with a reason, or not applicable, and nothing was silently assumed. Write each round as it closes, not at the end, into the file the calling skill names (the brand memory for brand work, the brief for a brief). Read the summary back in plain words and get an explicit yes before acting on it.
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
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.