Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add tranfu-labs/tranfu-skills --skill ui-ecosystemgit clone --depth 1 https://github.com/tranfu-labs/tranfu-skillsWrote 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.
[](https://agentmods.dev/skills/tranfu-labs/tranfu-skills/ui-ecosystem)<a href="https://agentmods.dev/skills/tranfu-labs/tranfu-skills/ui-ecosystem"><img src="https://agentmods.dev/badge/skills/tranfu-labs/tranfu-skills/ui-ecosystem/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.
<a href="https://agentmods.dev/skills/tranfu-labs/tranfu-skills/ui-ecosystem"><img src="https://agentmods.dev/badge/skills/tranfu-labs/tranfu-skills/ui-ecosystem.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00160 | $0.03592 |
| Opus 5 | $0.00080 | $0.01796 |
| Sonnet 5 | $0.00032 | $0.00718 |
| Haiku 4.5 | $0.00016 | $0.00359 |
Grade A, and why
ui-ecosystem 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 9d ago.
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.
How it starts
The opening of the file, as written. The whole thing — 299 lines — stays where its author put it; the contents beside it link to each section on GitHub.
UI Ecosystem
Purpose
Use this skill to make UI implementation borrow the right frontend ecosystem instead of inventing every visual and interaction detail from scratch.
The protected result is: after frontend technical/design selection is complete, Codex must actively recommend, install when authorized, and use compatible MCPs, plugins, skills, component libraries, design systems, templates, icon sets, motion libraries, and official examples that improve UI beauty, polish, and implementation reliability.
This skill complements strategy and reference-project workflows. It does not choose the whole product strategy. It runs after enough frontend direction exists to map tools to the selected ecosystem.
For creation rationale and naming evidence, see references/creation-rationale.md only when auditing or evolving this skill.
Run Modes
Choose one mode before acting:
recommend-only: inspect frontend choices and produce aUI_ECOSYSTEM_PACKET; do not edit files or install dependencies.implement-with-ecosystem: recommend, install when authorized, and use selected ecosystem tools during frontend implementation.audit-existing-ui: inspect an existing UI and identify missing ecosystem leverage; only edit when the user asks for fixes.
If the user asks to "完善", "实现", "做页面", "改 UI", "提升美观", "不要手搓", or equivalent after frontend selection is known, default to implement-with-ecosystem. If the user only asks "推荐", "分析", "看看可用工具", or equivalent, default to recommend-only.
Hard Rules
- MUST produce a
UI_ECOSYSTEM_PACKETbefore frontend code edits or dependency installation. - MUST inspect the current project stack before recommending tools; do not recommend from memory alone.
- MUST use
tool_searchbefore claiming MCP/plugin/skill availability or absence. - MUST use current official documentation for any selected framework, UI kit, component registry, MCP, plugin, CLI, or SDK when implementation depends on its API.
- MUST prefer already installed project libraries and existing design-system primitives before adding new dependencies.
- MUST install and use selected tools only when the user requested implementation/tool use or the task clearly authorizes dependency installation.
- MUST report what was adopted, activated, absorbed, spiked, rejected, and what remains hand-rolled.
- NEVER invent MCP, plugin, or skill names.
- NEVER copy code from reference projects or templates unless license compatibility and adoption scope are checked.
- NEVER let ecosystem tooling override project rules, design constraints, accessibility requirements, or existing component ownership.
- NEVER stop at a raw recommendation list when the user asked to implement; use the selected ecosystem in the actual UI work and verify the rendered result.
What ships with it
7 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 9d ago First seen · 299 lines · 160 tokens per session scan A 7ed1b9708367
ui-ecosystem is a skill published in the GitHub repository tranfu-labs/tranfu-skills (2 stars, last pushed 2d ago), licensed MIT. It adds 160 tokens to every session and 3,592 once invoked, about $0.0008 per session on Opus 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 2026-09-03.
Other skills, from other repositories
chakra-ui-builder
Build responsive, accessible UI components and layouts using Chakra UI v3, install or configure Chakra UI in new and existing projects, and design scalable themes using tokens, semantic tokens, recipes, and slot recipes. Use this skill whenever a user asks to build, create, or generate any UI component, page, form…
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ultragoal with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
frontend-visual-qa
Audits already-rendered web, landing-page, HTML deck/slide, browser tool/game, dashboard/admin, design-system, and desktop UIs using real-browser or native-app journeys, inspected screenshots, DOM geometry, responsive or projection viewports, and a bundled Playwright sweep. Use after UI implementation to find…
prototype-web
A clickable, high-fidelity web product prototype with navigation, a hero section, feature cards, steps, social proof, and optional pricing. It is designed to resemble a finished landing page while remaining a prototype.
refactoring-ui
Audit and fix visual hierarchy, spacing, color, and depth in web UIs. Use when the user mentions "my UI looks off" (or amateur/unprofessional), "fix the design", "Tailwind styling", "color palette", "visual hierarchy", "design system", "spacing scale", or "component styling". Also trigger when building consistent…
animation-principles
Apply animation principles — easing, staging, follow-through — to one specific UI motion. Use when tuning how an animation feels. For product-wide duration and easing tokens use motion-system (design-systems); for a full interaction spec use micro-interaction-spec.