Back to search
huatu-skill
SkillWorks with Claude CodeGitHub
Turn articles, research, notes, data, or existing drafts into clear Xiaohongshu carousel images or self-contained ELI5 visual explainer HTML. Use for 小红书图文、小红书轮播图、信息卡片、知识型笔记、研究型长图, responsive mechanism explainers, local PNG/HTML rendering, and checks for typography, hierarchy, overflow, sources, simplification boundaries, and safe self-contained delivery.
Safety scan
A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.
Checked today
Badge for your README
Markdown
[](/listings/ythx-101--huatu-skill)HTML
<a href="/listings/ythx-101--huatu-skill"><img src="/api/listings/ythx-101--huatu-skill/badge.svg" alt="findsafeskills safety rating" /></a>Install
i
What was scanned
The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.
SKILL.md · Manifest · 229 lines
- ---
- name: huatu-skill
- description: Turn articles, research, notes, data, or existing drafts into clear Xiaohongshu carousel images or self-contained ELI5 visual explainer HTML. Use for 小红书图文、小红书轮播图、信息卡片、知识型笔记、研究型长图, responsive mechanism explainers, local PNG/HTML rendering, and checks for typography, hierarchy, overflow, sources, simplification boundaries, and safe self-contained delivery.
- ---
- # 画图 Skill
- Build a carousel that helps the reader understand the meaning — before it looks coherent, before it passes the rules. A deck succeeds when the layout itself makes a relationship, mechanism, or judgment easier to see than the text alone would. Treat model interpretation, information architecture, visual hierarchy, deterministic rendering, and visual QA as one workflow. Constraints are guardrails, not goals: they prevent accidents, but a content-specific visual thesis creates meaning. When a rule and the reader's comprehension conflict, the rule yields.
- ## Deliver a product, not a demo
- Huatu has two product modes. In **carousel mode**, the final product is the rendered PNG set; HTML is the deterministic preview layer and JSON is the editable source. In **ELI5 HTML mode**, one self-contained responsive HTML file is the final product; browser screenshots and QA JSON are evidence. Neither mode may substitute a preflight result for the target artifact. Read [references/delivery-standard.md](references/delivery-standard.md) before creating or repairing either product.
- Use state words precisely: `concept`, `draft`, `candidate`, `release`, or `blocked`. Never call work complete when browser rendering, target-artifact inspection, or blocking-finding resolution is still pending. `--check-only` proves static/schema validity only. A render failure is `blocked`, not a license to hand off an unverified artifact.
- ## Choose the task path
- - Choose **ELI5 HTML mode** when the user wants one responsive visual mechanism explainer rather than numbered carousel images. Read and follow [references/eli5-html-mode.md](references/eli5-html-mode.md), then use `assets/eli5-explainer-starter.html` and `scripts/check_explainer.py`. Do not apply the carousel JSON/render workflow to this mode.
- - Otherwise choose **carousel mode** and continue below. For 知识型、机制型或研究型内容,默认选择 `mixed`(图文交替),并同时阅读 [references/image-led-design.md](references/image-led-design.md) 与 [references/diagram-system.md](references/diagram-system.md);只有用户显式要求全文字时才选择 `editorial`。
- - For source material or a long article, extract the thesis and build a slide-by-slide narrative.
- - For an existing outline or JSON spec, preserve the argument and improve page roles, density, and components.
- - For existing images, inspect every image first. Diagnose hierarchy, spacing, contrast, consistency, clipping, and sequence before rebuilding.
- - For a critique-only request, stop after the annotated diagnosis and prioritized fixes. Do not render unless requested.
- Read [references/content-blueprints.md](references/content-blueprints.md) when deciding the story sequence. For reference-driven or visually ambitious work, read [references/model-interpretation.md](references/model-interpretation.md) and write the design manifest before styling. When photographs, illustrations, collage, expressive objects, or material texture could carry meaning, also read [references/image-led-design.md](references/image-led-design.md). Read [references/kami-design.md](references/kami-design.md) (默认主题 v2.0 法则与 tokens), [references/design-contract.md](references/design-contract.md), [references/layout-system.md](references/layout-system.md), [references/visual-qa-rubric.md](references/visual-qa-rubric.md), and [references/delivery-standard.md](references/delivery-standard.md) before choosing styles or doing visual QA. Read [references/spec-format.md](references/spec-format.md) before writing a render spec.
- ## ELI5 HTML path
- For this mode, create 3–7 semantic scenes with one concept and one dominant inline SVG/figure per scene. Keep copy short, name facts and sources, and include an explicit simplification boundary. The file must use inline CSS/SVG only: no JavaScript, remote dependency, analytics, request-capable resource, credential, private identifier, host secret, or QR code.
- Run static preflight, then real Chromium validation:
- ```bash
- python3 <skill-dir>/scripts/check_explainer.py explainer.html --check-only
- python3 <skill-dir>/scripts/check_explainer.py explainer.html --output-dir explainer-qa
- ```
- The browser run is mandatory and must pass at 390×844 and 1365×768, producing `qa.json`, `preview-mobile.png`, and `preview-desktop.png` with no unsafe request attempt, horizontal overflow, browser error, or visible text below 12px. Inspect the HTML and both full-page screenshots after the last change. Deliver HTML as the product and QA/screenshots as evidence. Moshi/iPhone preview and release approval remain parent/human-owned; never start a public or persistent preview server.
- The numbered workflow below is the carousel path.
- ## 1. Establish the content contract
- Identify:
- - audience and desired reader action;
- - one-sentence thesis;
- - facts, quotes, and sources that may be presented as verified;
- - desired slide count, defaulting to 6–10 for a dense educational carousel;
- - author/footer text and any provided brand constraints.
- Infer these from supplied material when safe. Ask the human only when a missing choice would materially change the result. Never invent a statistic, quotation, source, credential, or platform rule to fill a layout.
- ## 2. Write the narrative before styling
- Create a storyboard with exactly one sentence per slide describing that slide's job. Give each slide one dominant message and select only the components needed to prove it.
- Prefer this rhythm for research-style content:
- 1. promise or tension;
- 2. evidence of relevance;
- 3. distinction or comparison;
- 4. mechanism or framework;
- 5. value, consequence, or case data;
- 6. disagreement or limitation;
- 7. the author's judgment and decision threshold;
- 8. deeper implication or local context;
- 9. conclusion and reader-specific action.
- Shorten or merge roles when fewer pages are appropriate. Do not force nine pages when the material cannot support them.
- ## 3. Interpret the content visually
- For reference-driven work, set `referenceDriven: true` and create a concise `designManifest`. The manifest records:
- - one visual thesis and intended emotional progression;
- - a semantic metaphor or a reason to use none;
- - one or two meaningful motifs;
- - deck rhythm, contrast plan, and type strategy;
- - one composition intent per slide;
- - recent habits and visual clichés to avoid;
- - why this direction fits this specific content.
- This is an inspectable design brief, not hidden reasoning. Use it to make decisions and later judge whether the render delivered the intended meaning.
- Choose a `visualMode` before choosing blocks:
- - `editorial` when language and evidence should remain primary;
- - `mixed` when image and structure should alternate;
- - `image-led`, `photo-diary`, `object-study`, or `poetic-poster` when a visual anchor should carry the page before explanatory text.
- 知识型、机制型和研究型内容默认使用 `mixed`;只有用户显式选择 `editorial` 时才改为全文字路径。任何非 `editorial` 模式的 manifest **必须**包含简短的 `materialSystem`、`imageCadence` 与逐页 `visualAnchor` 计划,不能只写一个模式名称。Do not satisfy this step by placing generic AI decoration behind existing cards. Each image needs a semantic role: hero, evidence, atmosphere, texture, motif, or transition.
- Before a full deck, create three two-page directions that differ in interpretation and composition—not merely colors. Prefer metaphor-led, typographic/editorial, and diagram/spatial directions when appropriate. Compare them with:
- ```bash
- python3 <skill-dir>/scripts/compare_directions.py direction-a.json direction-b.json direction-c.json
- ```
- If comparison reports `distinct: false`, revise the concepts or compositions before asking the human to choose a direction. As soon as a direction is selected, perform a real browser render of its two-page candidate. This is the runtime smoke test: discover missing Playwright/Chromium or broken local assets before writing the entire deck. If the smoke render cannot run, mark the release path `blocked` and report the exact prerequisite.
- ## 4. Apply a bounded visual system
- Use a 1080×1350 canvas unless the user specifies another target. For a single 3:4 cover (e.g. Xiaohongshu 封面), set the top-level `canvas` field to `{"width": 1080, "height": 1440}` and render a one-slide poster spec. **Default theme is Kami (v2.0)**: warm parchment canvas, ink-blue accent, warm-gray text scale, serif-led hierarchy (weight 500, no pseudo-bold), hairline borders, whisper-only shadows, no default italics, no yellow marker wash. Full rules, tokens, and anti-patterns live in `references/kami-design.md`. The old brick-red / pale-yellow default is retired.
- When to keep Kami: the default — especially when the user wants 高级感 / 文档感 / 克制 / 正式 / 专业. When to override the theme explicitly: the user asks for high-saturation, playful, or "小红书爆款" visual energy; then provide a custom `theme` in the spec, never by silently reverting the defaults.
- Keep these constraints as guardrails, not a fixed template:
- - one dominant headline per slide;
- - two to four content modules per slide;
- - no more than three highlight phrases per slide unless a table requires emphasis;
- - source labels smaller than body copy but still legible;
- - generous bottom clearance for platform overlays and pagination;
- - alternating dense and light pages across the sequence.
- For mixed or image-led decks:
- - begin with the image-text relationship, not a component quota;
- - avoid three consecutive pages that all require reading before seeing;
- - include a low-text visual pause when the narrative can support one;
- - limit the material vocabulary to two or three coherent treatments;
- - preserve asymmetry, cropping, and negative space when they improve the idea;
- - use original, user-provided, licensed, or public-domain assets only, and record provenance outside the slide when needed.
- Choose composition primitives because they express a relationship. Available archetypes are starting points (`editorial`, `poster`, `split`, `diagram`, `timeline`, `custom`); primitives may be combined within safe bounds. A custom composition must explain why breaking the normal grid helps the content.
- Abstract visual principles from references. Do not copy another creator's text, watermark, avatar, account name, signature, or distinctive identity treatment.
- ## 5. Create the render spec
- Copy [assets/starter-carousel.json](assets/starter-carousel.json) into the working output directory and replace its original example content. Keep user material outside the Skill directory.
- Use only the supported block types documented in [references/spec-format.md](references/spec-format.md), including the local-only `image` block. Treat all content as plain text; never insert user text into the HTML template as executable markup. Image sources must be local PNG, JPEG, WebP, or SVG paths relative to the spec or absolute local paths; remote URLs are rejected.
- For `mixed` or `image-led` specs, these are hard requirements:
- - 每张图先写一句关系命题:这张图让读者比读段落更快看见的流程、对比、趋势或分层是什么([references/diagram-system.md](references/diagram-system.md) 的一句话测试)。过不了测试就不画;
- - 知识型 deck 优先至少 2 张图卡(diagram 计入),但以一句话测试为准:内容只撑得住 0–1 张真有教学增量的图时,宁缺毋滥,不要为凑配额补装饰图;
- - 每张图必须有语义明确的 `alt` 与 schema 合法的 `role`,并在规划中承担 hero、evidence、annotate、contrast、echo 或 transition 之一,不能只负责装饰;
- - [assets/diagrams/](assets/diagrams/) 模板是候选不是默认:先按内容关系决定结构,再从模板里选最接近的作起点改写;内容被迫适配模板节点数时,删除、合并或重排节点,保留关系本身。
- Run structural validation before rendering:
- ```bash
- python3 <skill-dir>/scripts/render_carousel.py carousel.json --output-dir rendered --check-only
- ```
- Fix every reported spec error before continuing.
- ## 6. Render deterministically
- Render the deck with the bundled HTML/CSS template:
- ```bash
- python3 <skill-dir>/scripts/render_carousel.py carousel.json --output-dir rendered
- ```
- The renderer writes:
- - `carousel.html`, the editable local preview;
- - `slide-01.png`, `slide-02.png`, and so on;
- - `qa.json`, including dimensions and overflow results.
- - `design-manifest.json` for interpreted decks.
- For interpreted decks, it also compares a non-sensitive visual fingerprint with the most recent five entries in `design-history.jsonl` beside the spec. This produces a review warning rather than prohibiting justified reuse. Pass `--no-history` only for fixtures or reproducible tests.
- If Playwright or a Chromium browser is unavailable, report the exact missing prerequisite and mark the release `blocked`. Do not silently replace the renderer with AI-generated text images, and do not present HTML/JSON as the finished image product.
- ## 7. Perform visual QA
- Read `qa.json`, then inspect the rendered PNGs visually. For a deck of ten pages or fewer, inspect every page. Review the PNGs before reading the manifest or author rationale. At minimum verify:
- Comprehension probes come first — each is blocking, with the same weight as overflow:
- - whether the slide still carries mood or meaning when its explanatory copy is covered (遮文仍懂);
- - whether every image and diagram adds a teaching increment: it makes a flow, comparison, trend, or layer visible faster than the paragraph would (教学增量,diagram 一句话测试);
- - whether every image card has a visual anchor and first reading target visible within one second at 1× phone size.
- Then structure and craft:
- - title hierarchy and line breaks;
- - no clipped or overlapping text;
- - readable source labels and table cells;
- - consistent margins, rules, card radii, and page numbers;
- - restrained highlighting and accent usage;
- - sequence-level density and rhythm;
- - accurate author/footer text;
- - absence of copied identity elements;
- - semantic role, focal point, crop, and provenance of every image;
- - whether the image adds a relationship or proof instead of repeating nearby text;
- - whether every image is non-decorative and has a named semantic job;
- - absence of generic AI visual clichés used only as decoration;
- - coherence of paper, ink, grain, tape, shadow, or other material treatments;
- - sequence-level image cadence: no accidental return to a wall of text after an image-led opening;
- - semantic fit between each page and its recorded composition intent;
- - meaningful variation from recent decks without random novelty;
- - at least one deliberate moment of contrast or surprise that serves the argument.
- Diagram budget conformance is suggested, not blocking: `references/diagram-system.md` 的复杂度预算(节点数、字号档、宽度档)是默认参考,内容关系需要时允许偏离,偏离要在 manifest 里写一句理由。理解失败永远优先于预算合规。
- Read the three statuses separately: `structurally_valid` means the page did not break; `veg_review_required` remains true until review; `visually_approved` is never granted by the renderer. Do not accept a deck that merely passes overflow checks. Visual balance, awkward orphan lines, misleading emphasis, and a manifest that the render fails to express still require judgment. Revise the JSON and rerender until both automated and visual checks pass.
- After the last content, SVG, theme, or layout change, rerender the whole deck and inspect every PNG again. Write `qa-summary.md` using the review contract. A previous PASS becomes stale as soon as any source changes.
- ## 8. Deliver the release bundle
- Run the fail-closed delivery gate after final visual QA:
- ```bash
- python3 <skill-dir>/scripts/check_delivery.py carousel.json \
- --output-dir rendered \
- --qa-summary qa-summary.md
- ```
- Do not report a carousel `release` unless it exits `0` with `release_ready: true`. Otherwise report `blocked` or `candidate` and name the exact unmet gate.
- Return:
- - release state (`release`, `candidate`, or `blocked`);
- - the storyboard;
- - the editable JSON spec and local source assets;
- - the HTML preview as the deterministic rendering layer;
- - the rendered PNG directory as the final product;
- - `qa.json`, `qa-summary.md`, and the delivery-check result;
- - the design manifest and any reviewed recent-similarity warning;
- - optional post caption and hashtags only when requested.
- Keep publishing separate. Uploading or posting to Xiaohongshu is an external action and requires explicit authorization at action time.
README.md · README · 186 lines
- # 画图 Skill
- 画图 Skill(huatu-skill)是一个面向 Codex 等支持 `SKILL.md` 的 AI Agent 的视觉叙事 Skill:帮内容创作者把长文、研究笔记和草稿,做成可编辑、可验证的小红书图文轮播(1080×1350 PNG 信息卡片),或一个自包含的 ELI5 一页式 HTML 视觉解释器;本地渲染,交付前有 fail-closed 质检。
- English: an agent skill (`SKILL.md`) that turns articles and research into Xiaohongshu (RedNote) carousel PNGs or self-contained ELI5 visual explainers, with local Playwright rendering and fail-closed QA.
- > Constraints keep the page safe. Interpretation makes it meaningful.
- 
- ## 它解决什么
- 画图 Skill 先理解论点、关系与情绪,再选择两种产品路径之一:小红书轮播输出可编辑 JSON、HTML 预览、1080×1350 PNG 与 QA;ELI5 Visual Explainer 输出一个自包含响应式 HTML 与浏览器验证证据。**轮播的最终产品是 PNG;解释器的最终产品是 HTML。`--check-only` 对两者都只是预检**。
- - 将长文章、研究笔记或已有草稿改写成 6–10 页轮播叙事
- - 用可检查的 `designManifest` 记录视觉命题、隐喻、节奏与构图意图
- - 支持 editorial、mixed、image-led、photo-diary、object-study、poetic-poster 六种视觉模式
- - 知识型内容默认走 image-led / mixed 图文交替路径,并可复用 6 种 diagram SVG 模板表达流程、步骤、层级、时间、象限与对比关系
- - 支持本地 PNG、JPEG、WebP、SVG,并赋予 hero、evidence、atmosphere 等语义角色
- - 检查溢出、低对比度、重复构图、弱图像节奏与近期设计相似度
- - 生成本地 HTML 预览和逐页 PNG,并用 fail-closed delivery checker 阻止缺图、陈旧渲染或 BLOCKED QA 被当成成品
- - 生成 3–7 幕、低文案、大视觉的 ELI5 HTML 解释器,明确来源与简化边界
- - 在真实 Chromium 的 390×844 与 1365×768 视口检查外部请求、横向溢出、小字和浏览器错误
- - 把最终审美判断、手机验收与发布权留给人
- ## 适用场景与区别
- | | 说明 |
- |---|---|
- | 适合 | 知识型、研究型、机制型的小红书图文;把一篇文章拆成 6–10 页的叙事;需要一页式、手机和桌面都能看的解释页 |
- | 不适合 | 自动发帖或排期(本项目不做);纯照片修图;需要 JavaScript 交互的网页 |
- 和其他做法的区别:
- - 对比「直接让 AI 生图」:文字由 HTML/CSS 排版,产出可编辑的 JSON 源文件,再确定性渲染,所以中文排版可以修改、可以复现。
- - 对比「手工套模板」:先写叙事和设计意图(`designManifest`),再按内容选择构图。
- - 对比「普通 HTML 转图片工具」:多了溢出 / 对比度检查,以及 fail-closed 的交付门槛。
- ## 设计原则
- 1. 先写每页的叙事任务,再开始排版。
- 2. 图像必须承担意义,而不是给文字加一层装饰。
- 3. 规则是护栏,不是模板;内容变化应该带来构图变化。
- 4. 自动检查只能证明页面没有坏,不能证明它好看。
- 5. `--check-only` 不是交付;最后一次修改后必须重新渲染并逐页检查。
- 6. 不复制其他创作者的文字、水印、头像或标志性身份元素。
- ## 快速开始
- 1. 克隆到 skills 目录并安装渲染依赖:
- ```bash
- git clone https://github.com/ythx-101/huatu-skill.git ~/.codex/skills/huatu-skill
- cd ~/.codex/skills/huatu-skill
- python3 -m pip install -r requirements.txt
- python3 -m playwright install chromium
- ```
- 已经装了 Chrome/Chromium 的,可以用 `--browser <路径>` 或环境变量 `CHROME_BIN` 指定浏览器。其他支持 `SKILL.md` 的 Agent(例如 Claude Code 的 `~/.claude/skills/`)按各自的 skills 目录放置即可。
- 2. 在 Agent 里说一句话。轮播:
- ```text
- 使用 $huatu-skill,把这篇文章做成 8 页小红书图文。
- 先提出三种真正不同的视觉方向,选择后再渲染;加入有语义作用的图像,最后检查每一页和整组节奏。
- ```
- ELI5 解释器:
- ```text
- 使用 $huatu-skill,用 ELI5 HTML 模式把这篇文章做成 5 幕的一页式视觉解释器。
- ```
- 3. Skill 会先选择产品模式。轮播路径完成:内容契约 → 分页叙事 → JSON spec → 本地渲染 → 逐页视觉 QA → fail-closed 交付检查。解释器路径完成:3–7 幕叙事 → 单幕单概念 → 自包含 HTML → 双视口 Chromium QA → 人工检查。
- ## ELI5 Visual Explainer
- 从安全起始文件开始:
- ```bash
- cp assets/eli5-explainer-starter.html explainer.html
- python3 scripts/check_explainer.py explainer.html --check-only
- python3 scripts/check_explainer.py explainer.html --output-dir explainer-qa
- ```
- 真实浏览器命令生成 `qa.json`、`preview-mobile.png` 和 `preview-desktop.png`。HTML 只允许内联 CSS/SVG;不允许 JavaScript、远程字体/CDN、分析代码、网络资源、凭据、私有标识或二维码。参见 `references/eli5-html-mode.md`,以及可复现示例 `examples/eli5-moshi-hook.html` 和 `examples/eli5-moshi-browser-preview.html`。
- ## 轮播本地渲染
- 先检查结构:
- ```bash
- python3 scripts/render_carousel.py examples/mixed-carousel.json \
- --output-dir rendered --check-only
- ```
- 再生成 HTML 和 PNG:
- ```bash
- python3 scripts/render_carousel.py examples/mixed-carousel.json \
- --output-dir rendered --no-history
- ```
- 输出包括:
- - `carousel.html`:可编辑的本地预览
- - `slide-01.png` 等:1080×1350 图片
- - `qa.json`:尺寸、溢出与诊断结果
- - `design-manifest.json`:可检查的设计意图
- 渲染 PNG 需要 Playwright 与本地 Chromium(见「快速开始」);仅做 JSON 结构检查不需要浏览器,但结构检查不能替代成品验收。
- 最终逐页检查后,写入 `qa-summary.md`,再运行:
- ```bash
- python3 scripts/check_delivery.py examples/mixed-carousel.json \
- --output-dir rendered \
- --qa-summary qa-summary.md
- ```
- 只有输出 `release_ready: true` 才满足机械交付门槛;它仍不授权自动发布。
- ## 目录
- ```text
- SKILL.md Skill 工作流
- agents/openai.yaml Codex 展示信息
- assets/ 轮播与 ELI5 HTML 起始模板
- references/ 叙事、构图、图像、交付与 QA 规范
- scripts/render_carousel.py 轮播校验与渲染器
- scripts/check_delivery.py 轮播成品包 fail-closed 交付检查
- scripts/check_explainer.py ELI5 HTML 静态与双视口浏览器检查
- scripts/compare_directions.py 候选方向差异检查
- tests/ 单元测试
- examples/ 可复现示例
- ```
- ## 测试
- ```bash
- python3 -m unittest discover -s tests -v
- ```
- CI 中不运行浏览器测试(未安装 Playwright 时这些测试会自动跳过)。
- ## FAQ
- **能直接发布到小红书吗?**
- 不能。Skill 不登录、不上传、不自动发布,发布需要人工操作。
- **需要 API Key 或联网吗?**
- Skill 自身的脚本在本地渲染,不需要额外的 API Key;除首次安装 Playwright 与 Chromium 需要下载外,渲染和检查不依赖网络。图片只接受本地文件,远程 URL 会被拒绝。Agent 本身所用模型如何计费,不在本项目范围内。
- **没装 Playwright / Chromium 能用吗?**
- 只能跑 `--check-only` 结构预检,这不算交付;要渲染 PNG 或做浏览器 QA,必须装上。
- **支持哪些尺寸?**
- 默认 1080×1350(4:5)。单张 3:4 封面可以设 `canvas: {"width":1080,"height":1440}`;宽高允许范围 720–2160。
- **能改配色吗?**
- 默认是 Kami 主题,可以在 spec 里用 `theme` 覆盖(六位 hex 色值),见 `references/kami-design.md` 与 `references/spec-format.md`。
- **支持哪些视觉模式?**
- editorial、mixed、image-led、photo-diary、object-study、poetic-poster。
- **能在 Claude Code 或其他 Agent 里用吗?**
- 它是标准的 `SKILL.md` 结构,可以放进对应 Agent 的 skills 目录;本文示例按 Codex 编写。
- **ELI5 HTML 里能放 JavaScript 或外链字体吗?**
- 不能,只允许内联 CSS/SVG。
- **`release_ready: true` 是不是就代表图好看?**
- 不是。它只证明机械门槛通过,审美判断和发布权在人手里。
- **可以用别人的图吗?**
- 只使用原创、已授权或公有领域的素材。
- ## 隐私与版权
- - 图片只接受本地文件路径,远程 URL 会被拒绝。
- - Skill 不登录、上传或自动发布小红书;发布是独立的人工动作。
- - 请只使用原创、已授权或公有领域素材,并自行核对事实与来源。
- ## License
- MIT © 2026 QingYue
Ratings and comments
Sign in to rate this skill.
Sign inFree to use. If it’s helped, pass it on.