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 lovstudio/skills --skill wechat-ui-paritygit clone --depth 1 https://github.com/lovstudio/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/lovstudio/skills/wechat-ui-parity)<a href="https://agentmods.dev/skills/lovstudio/skills/wechat-ui-parity"><img src="https://agentmods.dev/badge/skills/lovstudio/skills/wechat-ui-parity/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/lovstudio/skills/wechat-ui-parity"><img src="https://agentmods.dev/badge/skills/lovstudio/skills/wechat-ui-parity.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 | $0.00063 | $0.00915 |
| Opus 5.5 | $0.00025 | $0.00366 |
| Sonnet 5.5 | $0.00013 | $0.00183 |
| Haiku 4.5 | $0.00006 | $0.00092 |
Grade A, and why
lov-wechat-ui-parity 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 24d 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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
微信界面还原 · WeChat UI Parity
Express canonical WeChat meaning through the product's existing visual system without introducing a parallel component language.
Triggers
Activate when
- 用户说“按微信官方改这个组件”“还原微信聊天体验”“头像/气泡/菜单语义不对”。
- 用户给出已经明确分类的微信对象及官方参考，要求实现交互和视觉表现。
- The user asks to build the WeChat UI behavior, fix official UI parity, or refine a WeChat-compatible component.
Do not activate when
- 原始消息仍未正确分类，或者参与者、状态和正文来源尚未确定；先运行语义模块。
- 用户要品牌官网、海报或不以微信体验为基准的独立视觉创作。
Workflow (MANDATORY)
Step 1: Map meaning to component grammar
Classify the object before styling:
- user-authored message;
- system event or timeline separator;
- rich card or embedded content;
- media object;
- status, action, toggle, navigation, selection, or destructive control;
- transient feedback or diagnostic state.
Use the adjacent shared primitive whenever the same meaning already exists.
Step 2: Match official hierarchy
Compare and implement:
- alignment and conversation-flow ownership;
- avatar, sender label, bubble, surface, tail, icon, timestamp, and metadata;
- typography, line height, wrapping, emoji baseline, spacing, radius, and color;
- grouping across neighboring messages and time gaps;
- long content, missing assets, unknown type, loading, failure, and deletion states.
Absence is part of the contract. Do not show an avatar, bubble, title, chip, or button merely because the generic message component has one.
Step 3: Preserve product consistency
- Reuse tokens and primitives; add the smallest semantic modifier needed.
- Keep peer actions in one control grammar. Move crowded secondary actions into an extensible menu.
- Keep explanatory copy in secondary text, tooltip, popover, or diagnostic detail.
- Do not expose reverse-engineering intent or raw protocol language in user copy.
- Make error detail copyable and include stable debug context.
Step 4: Implement interaction states
Verify normal, hover, focus, pressed, selected, loading, disabled, error, and missing-content states. Preserve keyboard order, accessible names, selection, context menu behavior, link safety, and IME composition for any input.
What ships with it
1 file 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.
- 24d ago First seen · 103 lines · 63 tokens per session scan A 0342617490ce
lov-wechat-ui-parity is a skill published in the GitHub repository lovstudio/skills (72 stars, last pushed 6d ago), licensed MIT. It adds 63 tokens to every session and 915 once invoked, about $0.0003 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 2026-09-26.
Other skills, from other repositories
openai-frontend-design
Use for new frontend applications, dashboards, games, creative websites, hero sections, and visually driven UI from scratch, or when the user explicitly asks for a redesign/restyle/modernization. Builds from clean, airy, high-taste, readable image-generated concept design with section-specific references, faithful…
ultralytics-branding
This skill should be used when creating Ultralytics-branded content of any kind, including PDF, PPTX, Canva, or Google Slides presentations, DOCX documents, marketing or newsletter HTML emails, social media post copy or visuals, website or landing page designs, and dataset or model result visuals. Provides official…
shadcn
Current best-practices guide for shadcn/ui applications. Before applying primitive-specific guidance, inspect whether the checked-in components use Radix UI or Base UI; current shadcn supports both (Base UI is the default for new projects) and their composition APIs differ. Component installs and upgrades go through…
poster-style-transfer
Analyze an uploaded or local reference poster, extract its reusable design system, and transpose that system to an original poster with a new theme, title, subtitle, or campaign copy.
grill-design
Decide a UI design by building several genuinely different working prototypes and comparing them side by side, in rounds, until the choice is locked. Use when asked to "grill the design", "design this screen", "show me options", "prototype some variants", "what should this look like", "I can't decide on a layout".
web-design-guidelines
Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "review UX", or "check my site against best practices".