design-guard
Skill1 starsChanged 5 months agoNo licenceView on GitHub
Use this skill whenever the user starts designing a UI / view / screen / feature with Claude that will later go to Figma and then to a developer. Triggers include: "kreni na dizajn", "radimo dizajn task", "počni dizajn za X", "dizajniraj ekran/view", "design task", "/design-guard", "prebacujemo u Figmu", "pre nego što pošaljem u Figmu", or any request to produce or iterate on UI / screens / prototypes. This skill enforces an anti-slop contract: it pins the task scope, forbids invented content / states / data, forces every new idea to be flagged as an explicit proposal, and ends by producing a handoff manifest (proposals + placeholders + scope confirmation) that gates the prototype → Figma transition. Always use this skill at the start of any design / UI work — don't just start generating screens inline.
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.
No licence file, so all rights are reserved — read it at the source. We count its rules but don't quote them. Read them on GitHub.
≈ “Common” is an estimate: at least 1 in 5 of the 308,232 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.
In this repository216 other files it gives its agents.
- ab-test-analysisSkill
- a-b-test-designSkill
- accessibility-auditSkill
- accessibility-generalSkill
- accessibility-test-planSkill
- aesthetic-usabilitySkill
- affinity-diagramSkill
- ai-design-patternsSkill
- analyze-feature-requestsSkill
- anchor-linksSkill
- animateSkill
- animation-principlesSkill
- ansoff-matrixSkill
- aria-live-regionsSkill
- audio-videoSkill
- axe-rulesSkill
- beachhead-segmentSkill
- bourdieu-distinctionSkill
- brainstorm-experiments-existingSkill
- brainstorm-experiments-newSkill
- brainstorm-ideas-existingSkill
- brainstorm-ideas-newSkill
- brainstorm-okrsSkill
- bug-reportingSkill
- business-designSkill
- business-modelSkill
- card-sort-analysisSkill
- case-studySkill
- charts-graphsSkill
- ci-cdSkill
- click-test-planSkill
- cohort-analysisSkill
- color-contrastSkill
- color-systemSkill
- competitive-analysisSkill
- competitive-battlecardSkill
- competitor-analysisSkill
- component-specSkill
- content-designSkill
- content-strategySkill
- create-prdSkill
- critique-brand-consistencySkill
- critique-compositionSkill
- critique-typographySkill
- critique-visual-hierarchySkill
- customer-journey-mapSkill
- customgpt-designSkill
- dark-mode-designSkill
- dashboard-datavizSkill
- data-table-uxSkill
- data-visualizationSkill
- design-briefSkill
- design-critiqueSkill
- design-debt-auditSkill
- design-impact-reportingSkill
- design-negotiationSkill
- design-principlesSkill
- design-qa-checklistSkill
- design-rationaleSkill
- design-review-processSkill
- The first 60 shown.
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.

