# 任天真AI设计室 (@maisiehello) on xiaohongshu

- id: koinon:creator:xiaohongshu_maisiehello
- url: https://koinonlink.com/kol/xiaohongshu/maisiehello
- schema_version: 1.3

## Identity
- platform: xiaohongshu
- handle: maisiehello
- platform_url: https://www.xiaohongshu.com/user/profile/5ed681d00000000001006d82
- website: xhsdiscover://message/userPublicGroupList?user_id=5ed681d00000000001006d82&username=TA
- country: China
- entity_type: creator
- person_id: Cross-platform identity not resolved for this creator.

## Reach
- followers: 4600
- posts_observed: 1
- verified: false
- size_tier: nano

## Engagement
- status: not_collected
- status_note: Engagement has not been collected for this creator yet. This is a gap in our collection, NOT a statement that the creator has no engagement. Follower count is known, so it is measurable.
- unit_note: engagement_rate and peak_post_engagement_rate are ratios (0-1); avg_interactions_per_post and best_post_interactions are absolute counts. Read status before reading any number: a null rate has several different causes and status says which one applies here.

## Content
- category: software
- subcategory: devtools
- category_confidence: 0.9
- category_source: derived_from_recent_content
- topics: Vibe Coding与AI设计工作流, Agentic UX设计法则, UI提示词与风格控制, 设计系统与DESIGN.md, Figma动效与多模态交互, 从静态设计转向微应用/按需生成UI
- bio: 陪你一起探索AI时代的工作方式

💻 AI-native Designer ｜Learn in public
🛠️ AI设计工作流 | Vibe Coding 实战经验
👾希望能跟和大家一起多多交流~

## Audience (inferred)
- status: present
- description: Product/UI designers (mainly in-house designers at big tech companies and indie developers aiming to build independent products), learning AI-native design workflows
- roles: design
- seniority: practitioner
- pain_points: AI-generated UIs often lack sophistication and professional tone, Hard to consistently control design systems and visual coherence using only text prompts or prompts, Traditional Figma static mockups can no longer capture Agentic dynamic interactions, Need to quickly master CLI, .md files, and automation skills to rebuild their workflows
- posts_analysed: 42
- confidence: 0.75

## Commercial (inferred)
- audience_buyer_fit: 0.9
- promotion_intent: 0.9
- open_to_collaboration: false
- contact: Koinon does not publish creator contact details.

## Quality signals
- authenticity_score: 58
- authenticity_basis: platform_default
- credibility_score: 40
- flagged_for_review: false
- koinon_bd_grade: A — measures Koinon partner-outreach fit, not creator quality
- interpretation: Signals for triage, not verdicts. A flag means the profile is worth a manual check.

## Evidence
- [xiaohongshu_maisiehello#ee2becca] 设计师如何使用Codex?可交付工作流附提示词 / AI设计不是随便丢一句「帮我做个界面」，而是先把说明书写清楚，再让工具按流程干活。 (https://www.xiaohongshu.com/user/profile/5ed681d00000000001006d82)
- [xiaohongshu_maisiehello#6b824a08] 这篇把一套可复用的 Codex 设计流程拆成 6 步——
- [xiaohongshu_maisiehello#7f823314] ① 写 agents.md 设计说明书（色板、字号、明确不 / 大厂设计师的Vibe Coding笔记 | 附指令 / 作为一名在大厂搬砖多年的产品设计师，最近也在玩 Vibe Coding。
- [xiaohongshu_maisiehello#b50d24e5] 我发现很多独立开发者最头疼的不是功能实现，而是：“为什么我做出来的东西像个demo?” 🤯
- [xiaohongshu_maisiehello#53e11ba5] 其实，高级感不是靠天赋，而是 / 给AI写Prompt不会描述风格？关键词直接抄 / 独立开发者用AI做产品
- [xiaohongshu_maisiehello#29cef0bd] 最卡脖子的一步不是代码
- [xiaohongshu_maisiehello#bba77a5a] 是跟AI说"我要什么风格"时——词穷
- [xiaohongshu_maisiehello#dadc4037] "简洁一点""好看一点""高级感" AI听完一脸懵，你拿到的东西也不对

## Provenance
Every inferred field below carries how it was produced. Facts stay facts; inferences stay inferences.

- audience.description: source_type=ai_inferred, confidence=0.75, freshness_days=33, method=llm_persona_from_recent_content
- audience.roles: source_type=ai_inferred, confidence=0.75, freshness_days=33, method=llm_persona_from_recent_content
- audience.seniority: source_type=ai_inferred, confidence=0.75, freshness_days=33, method=llm_persona_from_recent_content
- commercial.audience_buyer_fit: source_type=ai_inferred, confidence=0.6, freshness_days=0, method=llm_scorer — Relative signal within Koinon indexing, not a market-wide score.
- commercial.promotion_intent: source_type=ai_inferred, confidence=0.6, freshness_days=0, method=llm_scorer
- quality.anomaly_flags: source_type=heuristic, confidence=0.5, freshness_days=58, method=profile_snapshot_and_engagement_ratio_heuristic — Means "worth a manual check", NOT confirmed fraud. Flags can be wrong and are not a verdict about the person.
- quality.authenticity_score: source_type=heuristic, confidence=0.25, freshness_days=0, method=Fixed value 58, pending engagement collection. Not a measurement. — The input set differs by platform; do not compare this score across platforms.
- quality.koinon_bd_grade: source_type=ai_inferred, confidence=0.5, freshness_days=58, method=llm_partner_fit_classifier + fit_score >= 0.5 => A; >= 0.35 => B; else C. authenticity is not an input. — Koinon partner-outreach fit, not creator quality.
- reach.followers: source_type=observed, confidence=0.95, freshness_days=58, method=platform_profile

## Freshness
- profile_checked_days_ago: 58
- content_analysed_days_ago: 0
- audience_updated_days_ago: 33

## AI retrieval
- indexing_requests: 1
- user_triggered_requests: 0
- note: Being indexed in bulk is not the same as being retrieved to answer a question.

## This profile
- Claim or correct: https://koinonlink.com/claim?k=xiaohongshu_maisiehello
- Request removal: https://koinonlink.com/claim?k=xiaohongshu_maisiehello
- Terms: https://koinonlink.com/for-ai