ui-communication-designer
Skill1 starsChanged 4 months agoMITView on GitHub
Clarify the flow or copy for one UI screen or journey. Use for copy rewrites, interaction diagnosis, flow restructuring, or communication-focused critique.
In this repository18 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- artgen-scaffoldSkill
- decideSkill
- devtools-ux-auditSkill
- frontend-aesthetic-directorSkill
- run-adaptiveSkill
- run-analysisSkill
- run-ciSkill
- run-committeeSkill
- run-flowSkill
- run-generalSkill
- run-modernizeSkill
- run-pipelineSkill
- run-simpleSkill
- run-specSkill
- run-uxSkill
- ui-ux-workflowSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
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 14
Do not claim rendered behavior, accessibility results, responsive behavior, or viewport evidence that was not observed.
- Distinctive: line 40
Use a full flow review for a multi-screen critique, redesign handoff, material flow change, or explicit scored review.
≈ “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
UI Communication Designer
Design the conversation before designing the screen. Explain UI problems through clarity, effort, trust, predictability, and recovery rather than aesthetic preference.
Boundary and Pairing
- Consume supplied artifacts or existing
$run-uxfindings; this skill does not collect browser evidence. - Do not claim rendered behavior, accessibility results, responsive behavior, or viewport evidence that was not observed.
ui-ux-workflowis a compatible next step for a broader conceptual bundle or wireframe.frontend-aesthetic-directoror another implementation workflow may consume approved work when separately authorized.
These pairings are descriptive. Do not automatically invoke another skill, workflow, or agent.
Communication Without Visual Clutter
Use the shortest wording that preserves the task, affected object, consequence, and recovery. Do not stack an eyebrow, heading, subtitle, helper paragraph, badge, and tooltip to repeat the same message. Keep necessary labels and risk information; visual simplicity is not permission to remove meaning. Distinguish global actions, selected-item actions, and field feedback in the supplied structure rather than adding explanatory panels by default.
For affected localized UI, preserve terminology, translation keys, and supported locale intent. Note long-label or wrapping risks as inference unless observed. Do not solve layout by hardcoding shorter English copy, inventing status/metrics, or claiming a rewrite has been visually verified.
Choose the Depth
Compact or copy only
Use a compact response for one copy or component question. For an explicit copy-only request that preserves the flow, diagnose the supplied text and return the requested rewrite with only the context needed to use it. Do not require a revised flow, wireframe, full review, rubric, or score.
Identify the target user, immediate task, platform, success outcome, supplied evidence, and material risk. Ask only if a missing fact would change the requested copy or task flow; otherwise make the smallest safe assumption and label it.
Use user language and put critical wording on the control or adjacent label. Make errors identify the affected object, the problem, and the next action. Make cost, data use, irreversible actions, and other commit points predictable. Do not blame the user or add warnings and confirmations without a material reason.
Finish when the requested copy or bounded diagnosis is actionable, its use context and evidence boundary are clear, and no unsupported scoring, flow change, or implementation has been added.
Full flow review
Use a full flow review for a multi-screen critique, redesign handoff, material flow change, or explicit scored review. Before producing it, read references/output-template.md and follow its workflow, communication rules, response contract, and finish conditions. Do not produce a full review from this summary alone.
For scoring, also read references/rubric.md before scoring. Score only dimensions supported by supplied artifacts or observed findings; mark unsupported dimensions not assessed, state confidence, and never fabricate a total from missing evidence. A score or reviewer preference does not authorize redesign, implementation, or another repair round.
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.

