qiaomu-design
joeseesun/qiaomu-design on GitHub: JavaScript, AI Engineering, Prompt & Scaffold, Build agent workflow (SDK), Agent-ready APIs, Design, Prompt engineering, Webdev.
joeseesun/qiaomu-design is ranked 16,602 with 582 stars.
joeseesun/qiaomu-design is ranked 16,602 among these 8 peers; omarcusdev/zap-gpt-free is ranked 16,607.
| Name | Rank | Metrics |
|---|---|---|
| ZubeidHendricks/youtube-mcp-server | 16,566 |
|
| christopherkarani/Swarm | 16,571 |
|
| KeyValueSoftwareSystems/agent-opfor | 16,579 |
|
| vivekVells/mcp-pandoc | 16,592 |
|
| omarcusdev/zap-gpt-free | 16,607 |
|
| outsmartchad/onchain-dex-cli | 16,608 |
|
| texttron/hyde | 16,610 |
|
| hatayama/unity-cli-loop | 16,620 |
|
| Parameter | Value |
|---|---|
| Language | JavaScript |
| Category | AI Engineering |
| Subcategory | Prompt & Scaffold, Build agent workflow (SDK) |
| Keywords | Agent-ready APIs, Design, Prompt engineering, Webdev |
| Stars | 582 |
| Forks | 47 |
| Contributors | 1 |
| Created date | 2026-03-02 |
| Updated date | 2026-10-14 |
| Stars in 1 day | 0 |
| Stars in 7 days | 5 |
| Rank | 16,602 |
| Previous rank | 16,394 |
| Rank change | -208 |
| 7-day stars rank | 5,774 |
| Previous 7-day stars rank | 5,313 |
| 7-day stars rank change | -461 |
| Total stars rank | 17,191 |
| Previous total stars rank | 17,161 |
| Total stars rank change | -30 |
| Country | China |
An opinionated Agent Skill for visual direction, implementation, and browser-based UI verification. It combines visual direction, implementation, and browser-based verification in one opinionated workflow. Install Then ask your Agent-Skills-compatible client: . What you get **Explicit executor routing**: the current agent implements by default. K3 or any other external model is used only when the user explicitly requests it in the current task. **Style fitting room**: 4 mutually-divergent direction mockups (real fonts/colors/layout) in . Pick by
click or keys, confirm with dial values and optional notes, then the local preview server reports the selection back to the current workflow. **Anti-slop bans**: no AI-purple gradients, no Inter, no italics, no centered-hero clichés, no "revolutionary/seamless" copy. **Chinese typography rules**: system font stack first, subset decorative CJK webfonts (5-20 MB otherwise), CJK spacing/punctuation/line-height discipline. **Motion craft** (Emil Kowalski system) and **engineering checklist** (Vercel WIG): easing/durations/stagger, a11y, focus traps
, destructive-action guards. md library** (Stripe, Linear, Apple…, Google Stitch format) for "make it like X" requests. **Pre-flight gate**: a hard checklist; nothing ships if any item fails. **Self-evolution**: feedback is recorded as events, abstracted into evidence-backed candidate rules, explicitly approved, published to the preferences ledger, and verified or rolled back when it causes regressions. Verified The first controlled comparison covered 6 variants × 7 tasks × 42 generated pages; the public follow-up expands to 8 variants × 10
tasks × 80 generated pages. The screenshots above link to interactive case pages. This evidence applies to those cases and mechanisms; every future project still needs its own tests and visual verification. Limits Requires an Agent-Skills-compatible client. The fitting room is a local HTML preview served by a tiny local callback server; if the server cannot start, it falls back to a static file and asks the user to reply with the selected direction. qiaomu-design does not inject
Qiaomu profile widgets into generated pages by default. md library is distilled from public sites for reference, not endorsement.
How many stars and forks are recorded?
joeseesun/qiaomu-design has 582 stars and 47 forks.
What is the repository rank?
joeseesun/qiaomu-design is ranked 16,602.
What language and category are recorded?
joeseesun/qiaomu-design has 582 stars, uses JavaScript and belongs to AI Engineering.
Which repository is closest in rank?
joeseesun/qiaomu-design is compared with omarcusdev/zap-gpt-free, ranked 16,607 with 582 stars.