deepseek-harness: Skill for Claude Code

.agents/skills/dsh-responsive-ui/SKILL.md

dsh-responsive-ui is a skill for Claude Code, Codex from deepseek-ai/deepseek-harness. It costs 47 tokens per session (671 once invoked), scanned A, original, MIT.

A responsive-interface guide for DeepSeek Harness, covering layouts at narrow widths, wrapping and truncating text, mobile controls, tooltips, keyboard use, and focus.

In plain words
What is it for?
Use it when building or reviewing client pages that must work on small screens, especially around titles, buttons, menus, tooltips, and keyboard navigation.
Why use it?
It helps prevent cramped screens from hiding actions, clipping content, creating horizontal scrolling, or making controls inaccessible.

Skill for Claude CodeCodex ✓ vendor

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is deepseek-ai/deepseek-harness's own configuration. It tells Claude Code and Codex how to work on deepseek-harness itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything deepseek-harness configures →

About the project

DeepSeek Harness is an open-source framework for building and running AI agents, organized so that its functionality is provided through plugins. Developers use it to launch agent workflows through a local web interface or from source, while the catalogue add-ons extend the harness as plugins.

deepseek-ai/deepseek-harness · 250,433 stars · on GitHub · deepseek.com

Reuse

Borrowing it

Nothing to install: this file belongs to deepseek-ai/deepseek-harness. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/deepseek-ai/deepseek-harness/master/.agents/skills/dsh-responsive-ui/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/deepseek-ai/deepseek-harness

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for dsh-responsive-ui

README.md
[![agentmods](https://agentmods.dev/badge/skills/deepseek-ai/deepseek-harness/dsh-responsive-ui/github.svg)](https://agentmods.dev/skills/deepseek-ai/deepseek-harness/dsh-responsive-ui)
Your own site
<a href="https://agentmods.dev/skills/deepseek-ai/deepseek-harness/dsh-responsive-ui"><img src="https://agentmods.dev/badge/skills/deepseek-ai/deepseek-harness/dsh-responsive-ui/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for dsh-responsive-ui

Your own site · 80×15
<a href="https://agentmods.dev/skills/deepseek-ai/deepseek-harness/dsh-responsive-ui"><img src="https://agentmods.dev/badge/skills/deepseek-ai/deepseek-harness/dsh-responsive-ui.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 47 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 671 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00047 $0.00671
Opus 5.5 $0.00019 $0.00268
Sonnet 5.5 $0.00009 $0.00134
Haiku 4.5 $0.00005 $0.00067

Measured yesterday against content hash 602b43fdebfb, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

dsh-responsive-ui scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.agents/skills/dsh-responsive-ui/SKILL.md · 55 lines

How it starts

The opening of the file, as written. The whole thing — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Responsive client UI

1. Minimum viewport

Use a viewport width of 390 CSS px as the primary acceptance minimum. There must be no unintended overlap, clipping, page-wide horizontal scrolling, or inaccessible primary actions. Below 390px, layout requirements may be relaxed.

2. Decision order

  1. First adjust space allocation or wrap elements onto another line; then consider text truncation, icon-only controls, or moving icons into the More menu.
  2. Primary actions and primary states must not be omitted.
  3. Do not hide conflicts through global clipping, reducing all font sizes, or shrinking click targets.
  4. Reduce font sizes only when specifically required by product design.

3. Text truncation

  1. Truncated content must be fully available on a secondary page or by opening a menu. Example: Session statistics below the input box.
  2. Truncation must not lose errors or other key information.
  3. Prefer single-line truncation for tab navigation, visible selectors, buttons, tags, and similar components.
  4. Important information that is not available on another page must be displayed in full without truncation.

4. Titles

  1. Prefer displaying page titles in full. Move the action area onto another line when necessary. Example: the Plugins page's title wrapping behavior.
  2. Prefer natural wrapping for card titles. If the number of lines is limited, the full title must remain available to view.

5. Icon-only controls

  1. Reducing a control to an icon requires both:
    • The icon clearly conveys its meaning, or the operation is familiar to users.
    • A tooltip appears on hover; add one if needed.
  2. Do not reduce “More account information” to an icon, because it navigates to a separate page.
  3. The model selector in the input box can be reduced to an icon because users see it frequently and can open its menu to switch models.
  4. Another example is the linked conversation in an automation task.

6. Mobile hover behavior

  1. Enable mouse-hover effects only on devices that support hovering. Use @media (hover: hover), not viewport width, to determine this.
  2. Tapping on a phone must not leave behind backgrounds, highlights, or action-button visibility intended only for hover.
  3. Preserve normal selected, enabled, and pressed states, as well as focus indicators for keyboard interaction.
  4. Try to preserve focus when the width changes, unless the focused element disappears from the page as a result.

Read the full file on GitHub · 55 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. yesterday First seen · 55 lines · 47 tokens per session scan A 602b43fdebfb

Subscribe to this mod's changes

dsh-responsive-ui is a skill published in the GitHub repository deepseek-ai/deepseek-harness (250,433 stars, last pushed today), licensed MIT. It adds 47 tokens to every session and 671 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-15.

Related

Other skills, from other repositories

better-typography

Web typography from choosing fonts to spacing, wrapping and accessibility. Use when picking or pairing typefaces, configuring variable fonts or OpenType features, setting up a type scale, checking heading hierarchy, styling text in components, truncating text, styling underlines, selection, placeholders or carets, or…

CanglongCl/dsh-web-review · 159 tokens

better-colors

OKLCH color space and color usage for web projects. Convert hex/rgb/hsl to oklch, generate palettes, check contrast, handle gamut boundaries, theme with Tailwind v4, and apply color with meaning. Triggers on oklch, color conversion, palette generation, contrast ratio, gamut, display p3, design tokens, semantic color…

CanglongCl/dsh-web-review · 103 tokens

better-ui

Design engineering principles for making interfaces feel polished. Use when building UI components, reviewing frontend code, implementing animations, hover states, shadows, borders, micro-interactions, enter/exit animations, choosing or reviewing icons, or any visual detail work. Triggers on UI polish, design details…

CanglongCl/dsh-web-review · 99 tokens

html-flowchart-anthropic

Create and revise pure HTML/CSS flowcharts using an Anthropic-inspired design language. Use when Codex needs to produce process diagrams, decision trees, pipelines, or system flows that should share warm ivory backgrounds, transparent dashed grouping containers, pastel node fills, SF Pro-style sans-serif labels…

yzlnew/infra-skills · 87 tokens

frontend-design-system

Use this skill to generate or audit design systems, check visual consistency, and review PRs that touch styling. Use when generating or auditing a design system, checking visual consistency, or reviewing a PR that touches styling.

gongyijie85/dsh-ecc · 47 tokens

design-system

Use this skill to generate or audit design systems, check visual consistency, and review PRs that touch styling. Use when generating or auditing a design system, checking visual consistency, or reviewing a PR that touches styling.

gongyijie85/dsh-ecc · 46 tokens