企业官网建设流程全解析

• AI 技能
• 人工智能

导读：本文以 codex-ppt-skill 内置风格参考 教学课件风.md 为主体，系统讲解该风格面向高校课程、专题讲座与技术培训场景的视觉体系——从适用场景、画布与配色、版式蓝图到渲染约束，并串联仓库内的风格确认流程、样张机制、Slide Job 结构与image_gen.py命令行参数，帮助读者在 Codex / OpenClaw 等 Skill 兼容 Agent 中直接复用或改造这一风格，生成"像专业学术课件而非营销 Pitch Deck"的全图型 PPT。

教学课件风（teaching courseware）是 codex-ppt-skill 内置的 12 套视觉风格参考之一（其余见 outline-style-and-sample.md 中的内置风格列表）。它服务的核心场景是：用整页生成图像的方式制作高校课程、专题讲座、技术培训与知识科普 PPT，要求页面同时承载文字、图解、图片和数据，并且视觉上"清晰、可信、有学术气质"。

上图即该风格的示例预览页：以深蓝/浅蓝学术色调为主，采用「三栏递进式」逻辑版式组织"输入与规划 → 图文生成 → 教学成果"的流程，区块内按"编号 + 标题 + 内容模块"分层，并容纳标题、正文、流程示意、图表、素材图标与课件缩略预览等多种教学元素——这正是本风格希望稳定输出的页面形态。

适用场景与风格定位

原文档明确列出教学课件风的适用场景：

• 高校课程、专题讲座与课堂教学；
• 技术培训、知识科普与专业能力建设；
• 概念讲解、体系梳理、案例分析与研究进展介绍；
• 需要同时呈现文字、图解、图片和数据的教学型演示。

在仓库的流水线语境中（见 SKILL.md 的默认工作流），这套风格通常在Step 3「确认统一的视觉风格」阶段被选用：当用户没有给出明确风格方向时，主 Agent 会给出 2～3 个候选风格并推荐其一，教学课件风就是面向教学/培训/学术汇报类内容的推荐候选之一。风格确认后，它会以style_name的形式写进每个 Slide Job，贯穿样张与全片生成。

GPT-Image-2 风格 Brief 全字段解析

教学课件风的核心资产是一份可直接投喂给 GPT Image 模型的 JSON Brief。它的设计原则是："由课程内容塑造的专业课堂语气，而非固定技术模板"（visual_direction原文："a professional classroom tone shaped by the lesson rather than a fixed technical template"）。下面按字段逐一拆解。

type 与 visual_direction

{ "type": "16:9 full-slide PowerPoint image", "style_name": "教学课件风", "best_for": "高校课程、专题讲座、技术培训、知识科普、概念讲解、体系梳理、案例分析和研究进展介绍", "visual_direction": "clear and credible academic courseware with structured knowledge communication, evidence-supported explanation, discipline-appropriate visuals, and a professional classroom tone shaped by the lesson rather than a fixed technical template" }

• type固定为16:9 full-slide PowerPoint image，与仓库的整页图片制图模式一致——每个最终origin_image/slide_XX.png都是一张完整的 16:9 页面图像（见 slide-generation-and-subagents.md）；
• visual_direction是全风格的一句话纲领：学术课件感 + 结构化知识传达 + 证据支撑的讲解 + 随学科/课程内容变化的专业课堂语气。

canvas：画布、背景与密度

"canvas": { "aspect_ratio": "16:9", "background": "white or very light cool gray with restrained pale-blue structural accents", "composition": "structured teaching slide with a clear title hierarchy and a content-driven combination of text, images, diagrams, charts, formulas, source material, annotations, or comparisons selected according to the lesson objective", "density": "balanced teaching density: substantial enough to support explanation, but never sparse, paragraph-heavy, or crowded; use strong grouping, alignment, and readable whitespace" }

• 背景为白色或极浅冷灰，仅以克制的淡蓝作为结构性强调；
• 构图由教学目标驱动，而非固定模板：文字、图解、图表、公式、素材、批注、对比按需组合；
• 密度要求"平衡的教学密度"：足以支撑讲解，但绝不稀疏、绝不整段堆文字、绝不拥挤，强调分组、对齐与可读留白。

color_palette：学术蓝系统

"color_palette": { "primary": "deep academic navy #0B2E6D and clear blue #1769AA", "secondary": "light blue #EAF3FB and cool gray #F3F6F9", "accent": "choose a small set of restrained auxiliary colors according to the subject matter, source material, and semantic categories", "neutral": "ink black #1F2937, body gray #4B5563, border gray #D7E0EA", "rule": "use the blue system to establish the teaching structure; select auxiliary colors only when the content needs semantic distinction, then apply them consistently rather than decoratively" }

配色是这套风格最可机器解析的部分：

rule是关键约束：蓝色系统负责建立教学结构；辅助色仅在内容需要语义区分时才启用，且一旦启用就全片一致地使用，而非当作装饰。这与 slide-generation-and-subagents.md 中"same palette, typography, icon language, texture, and mood across all slides"的 deck 一致性要求互相呼应。

typography：中文无衬线排印

"typography": { "title": "large bold Chinese sans-serif resembling Microsoft YaHei or Source Han Sans, usually dark navy, concise and immediately readable", "body": "compact but readable Chinese sans-serif with clear indentation and short explanatory phrases", "labels": "bold short labels with strong contrast, used when hierarchy or semantic categories need clarification rather than as mandatory card decoration", "text_quality": "all Chinese text, Latin terms, formulas, units, and data labels must be exact, readable, and non-garbled" }

• 标题：近似微软雅黑 / 思源黑体的大号粗体中文无衬线，通常深藏蓝、简明、一眼可读；
• 正文：紧凑但可读的中文无衬线，强调缩进清晰与短语化表达；
• 标签：仅用于澄清层级或语义类别，不是强制的卡片装饰；
• text_quality：所有中文、拉丁术语、公式、单位与数据标签必须精确、可读、不乱码。这也是仓库流水线的硬性要求——slide-generation-and-subagents.md 明确要求中文 deck 必须显式要求后端准确渲染中文，且 slide-worker.md 在子代理返回前必须检查"Chinese text is readable and not garbled"。

title_system：标题系统

"title_system": { "consistency_rule": "Keep title typeface, weight, color logic, alignment, and spacing consistent across slides of the same page type.", "cover": "May combine a large course title with one or more subject-relevant visuals and concise presenter or course information; choose the visual structure according to the discipline and topic.", "section_divider": "May use a concise section title with stronger whitespace and a restrained academic cue.", "content_slide": "Keep the page topic immediately recognizable, but let title alignment, supporting accents, and surrounding composition adapt to the teaching content.", "closing": "Use a concise acknowledgement or closing statement together with a subject-relevant visual or summary echo; keep the page informative and visually complete rather than leaving a nearly empty text-only slide.", "flexibility": "Treat the title system as a consistency guide rather than a fixed template. Do not force every slide into the same header, rule, alignment, or decorative treatment." }

标题系统不是"每页同一个页眉模板"，而是一套一致性指南：

• consistency_rule：同类型页面之间，标题字体、字重、颜色逻辑、对齐与间距保持一致；
• cover：大课程标题 + 学科相关的视觉素材 + 简明的讲者/课程信息，视觉结构随学科与主题选择；
• section_divider：章节页可用更克制的学术提示符 + 更强留白；
• content_slide：页面主题必须一眼可辨，但标题对齐、辅助强调与周边构图可随教学内容调整；
• closing：收尾页用简短的致谢/结语 + 学科相关视觉或总结呼应，不能是近乎空白的纯文字页；
• flexibility：只做一致性引导，禁止把每页都塞进相同的页眉、分隔线、对齐与装饰。

layout_patterns：八种教学页面模式

"layout_patterns": [ "course cover combining a clear title hierarchy with subject-relevant visual material and concise course information", "concept explanation using the most suitable combination of diagrams, images, definitions, formulas, source excerpts, or annotated examples", "sequence, process, development, or causal explanation with a clear viewing order", "comparison or relationship page whose structure follows the concepts being contrasted or connected", "case, text, artwork, experiment, event, or application analysis supported by relevant evidence and explanation", "overview or synthesis page organizing examples, themes, findings, or knowledge relationships", "knowledge summary using a concise framework, conclusion, or takeaway", "closing or acknowledgement page combining a short closing statement with a restrained subject-relevant visual" ]

八种模式对应：课程封面、概念讲解、过程/序列/因果、对比/关系、案例/材料/证据分析、总览/综合、知识总结、致谢收尾。这与仓库在 slide-generation-and-subagents.md 中推荐的页面角色清单（cover / section divider / context / process / comparison / data evidence / architecture / summary 等）高度同构——风格参考提供的页面模式，正是 Slide Job 中layout.role与layout.intent字段的可选值来源。

layout_usage_rule：模式即候选，不强制重复

"layout_usage_rule": "Choose the layout that best supports the teaching objective and viewing sequence. Every slide should combine meaningful visual explanation with readable text; use one strong visual or several complementary photographs, diagrams, charts, maps, formulas, documents, artworks, screenshots, or annotated examples according to the discipline and content. Keep the visual language coherent without forcing every page into cards, equal columns, or one repeated composition."

规则要点：每页必须"有意义的视觉解释 + 可读文本"并存；根据学科与内容选择一张强视觉或若干互补视觉（照片、图解、图表、地图、公式、文档、艺术作品、截图、批注示例）；保持视觉语言连贯，但禁止把每页都压进卡片、等宽分栏或同一套重复构图。仓库中 slide-generation-and-subagents.md 亦明确："Avoid generating every slide as the same three-card layout"——这与本风格规则同源。

layout_blueprints：三套可复用构图蓝图

"layout_blueprints": [ { "name": "概念 / 知识讲解", "sections": [ {"position": "title area", "count": 1, "labels": ["lesson question or core concept"]}, {"position": "primary teaching field", "count": 1, "labels": ["the most suitable visual and explanatory structure for the concept"]}, {"position": "supporting field", "count": 1, "labels": ["definitions, examples, evidence, annotations, or implications as needed"]} ] }, { "name": "过程 / 关系讲解", "sections": [ {"position": "title area", "count": 1, "labels": ["process, development, comparison, or relationship topic"]}, {"position": "primary relationship field", "count": 1, "labels": ["sequence, cause, contrast, hierarchy, interaction, or transformation"]}, {"position": "supporting field", "count": 1, "labels": ["conditions, examples, evidence, annotations, or summary as needed"]} ] }, { "name": "案例 / 材料 / 证据", "sections": [ {"position": "context field", "count": 1, "labels": ["case, text, event, artwork, experiment, or application context"]}, {"position": "evidence field", "count": 1, "labels": ["relevant visual material, source excerpt, data, observations, or comparison"]}, {"position": "teaching conclusion field", "count": 1, "labels": ["interpretation, lesson learned, or takeaway"]} ] } ]

三套蓝图覆盖教学最常见的信息组织方式：

1. 概念 / 知识讲解：标题区（课程问题或核心概念）+ 主教学区（最适合该概念的视觉与讲解结构）+ 支撑区（定义、示例、证据、批注或引申）；
2. 过程 / 关系讲解：标题区（过程/发展/对比/关系主题）+ 主关系区（顺序、因果、对比、层级、交互或转化）+ 支撑区（条件、示例、证据、批注或总结）；
3. 案例 / 材料 / 证据：情境区（案例、文本、事件、作品、实验或应用情境）+ 证据区（相关视觉材料、原始摘录、数据、观察或对比）+ 教学结论区（解读、经验或要点）。

重要提示：layout_blueprints是候选起点而非固定模板。仓库 outline-style-and-sample.md 与 slide-generation-and-subagents.md 反复强调：风格是"稳定的调色板/排版/图标语言/质感/氛围 + 随页面角色变化的版式"，不应把同一蓝图套到每一页。

visual_elements：允许与避免

"visual_elements": { "allowed": "discipline-relevant photographs, artworks, archival documents, source excerpts, maps, formulas, tables, charts, diagrams, screenshots, multi-image evidence groups, annotated images, timelines, relationship structures, restrained icons, and subtle academic background texture; cards and grids may be used when they genuinely clarify the material but are not the default", "avoid": "text-only pages, purely decorative illustration, repetitive card grids, default three-column layouts, generic AI-looking imagery, unsupported futuristic or technical styling, random 3D icons, playful stickers, excessive gradients, heavy shadows, glossy elements, inconsistent icon styles, dense ungrouped text, unrelated stock imagery, and ornamental layouts that weaken the teaching sequence" }

• 允许：学科相关的照片、艺术作品、档案文献、原始摘录、地图、公式、表格、图表、图解、截图、多图证据组、批注图、时间线、关系结构、克制的图标、微妙的学术背景纹理；卡片与网格仅在确实有助于澄清材料时使用，而非默认；
• 避免：纯文字页、纯装饰插图、重复的卡片网格、默认三栏布局、AI 感明显的图像（图内伪造文字、不合理的照片细节、通用发光科技特效、随机装饰物、重复模板式构图）、无依据的未来感/科技风、随机 3D 图标、俏皮贴纸、过度渐变/重阴影/高光、图标风格不统一、密集无分组的文字、无关的图库图片，以及削弱教学序列的装饰性版式。

image_treatment：各类素材的处理方式

"image_treatment": { "photos": "use relevant and credible course or case images as evidence, crop them consistently, and pair them with concise explanatory labels; one page may use a single main image or several complementary images when they explain different aspects of the topic", "screenshots": "place inside clean frames and preserve important interface details, annotations, and labels", "charts": "use the palette semantically, retain accurate axes and values, and emphasize the comparison or trend being taught", "illustrations": "choose diagrams, maps, explanatory drawings, documentary collage, symbolic graphics, or other illustration treatments appropriate to the discipline and lesson; avoid decorative scenes that do not teach anything", "discipline_materials": "treat formulas, artworks, historical documents, literary excerpts, medical images, scientific figures, and other subject-specific materials as valid visual evidence when relevant and accurately represented" }

• 照片：作为证据使用，统一裁切并配简明说明标签；一页可用单张主图，也可用多张互补图；
• 截图：放进干净的外框，保留界面关键细节、批注与标签；
• 图表：按调色板语义上色，保留准确的坐标轴与数值，突出要讲解的比较或趋势；
• 插画：选择与学科和课程适配的图解、地图、解释性绘图、纪实拼贴、象征性图形等；避免不教任何东西的装饰性场景；
• 学科材料：公式、艺术作品、历史文献、文学摘录、医学影像、科学图等，只要相关且被准确呈现，就视为有效视觉证据。

rendering_constraints：渲染约束清单

"rendering_constraints": [ "The slide must look like professional academic courseware, not a marketing pitch deck.", "Prioritize teaching sequence, conceptual clarity, and readable evidence over visual decoration.", "Every slide must contain both meaningful visual content and readable text; visuals should explain, demonstrate, compare, or provide evidence rather than merely decorate.", "Visual content may include photographs, diagrams, charts, maps, formulas, artworks, documents, source excerpts, screenshots, or other discipline-appropriate material; it does not always mean a decorative illustration.", "Avoid both underfilled slides and long blocks of prose. Convert dense explanations into diagrams, image groups, structured labels, or concise teaching points.", "Keep related information visibly grouped and maintain a clear viewing order.", "Avoid tiny text; split or simplify content when it cannot remain readable at presentation distance.", "Use semantic accent colors consistently across the deck.", "Do not force every slide into repeated cards, equal columns, a fixed module count, or an identical information grid.", "Avoid an obvious AI-generated look: no fabricated text inside images, implausible photo details, generic glowing technology effects, random decorative objects, or repetitive template-like compositions.", "Do not invent university, school, laboratory, company, or course logos; use only user-provided identity assets.", "Do not inherit topics, examples, imagery, terminology, or organizations from a style reference unless they are required by the source content.", "No watermark and no unrelated logo." ]

渲染约束是本风格的"验收红线"，共 13 条，核心可归纳为五组：

1. 身份正确：像专业学术课件，不是营销 Pitch Deck；教学序列、概念清晰、可读证据优先于视觉装饰；
2. 图文并存：每页必须同时有有意义的视觉内容与可读文本，视觉用于解释/演示/比较/提供证据，而非纯装饰；
3. 密度与可读性：避免空洞页与长段落，将密集解释转化为图解、图像组、结构化标签或简短教学要点；相关信息可见分组、保持清晰观看顺序；避免过小文字——在演示距离下不可读就拆分或简化内容；
4. 一致性：强调色全片一致使用；不强制每页重复卡片、等宽分栏、固定模块数或相同信息网格；
5. 反 AI 感与合规：图内不出现伪造文字、离谱照片细节、通用发光科技特效、随机装饰物、重复模板构图；不得编造大学/学校/实验室/公司/课程 Logo，只用用户提供的身份素材；不得从风格参考中继承主题、示例、图像、术语或机构（除非源内容要求）；无水印、无关 Logo。

在仓库流水线中落地这套风格

风格参考不是孤立的 JSON，它需要接入 codex-ppt-skill 的四段流程才能产出最终 PPT。

第一步：在风格确认阶段选用

在 outline-style-and-sample.md 定义的风格确认环节，主 Agent 会列出内置风格（含references/教学课件风.md），并给出 2～3 个候选（通常推荐其一）。选中教学课件风后，需提取其可复用视觉规则（调色板、排版方向、密度与留白、视觉元素处理）并保持全片统一。仓库同时支持用户自定义风格：存放到${CODEX_PPT_HOME:-~/.codex-ppt-skill}/references/，其优先级高于同名内置风格（详见 style-library.md）。

第二步：样张验证

按 outline-style-and-sample.md，风格确认后应只生成 1 页代表性样张（优先选内容页而非封面，以验证风格对真实内容的适配能力），存为{base_dir}/{deck_name}/origin_image/slide_XX.png，请用户确认"视觉风格、排版、版式密度与中文文字质量"。教学课件风特别值得检查的点：中文是否乱码、深蓝/浅蓝结构色是否稳定、辅助强调色是否全片一致、页面是否"看起来像课件而非宣传册"。样张通过后，需把sample_generation_method（含backend_used、tool_name、mode、prompt_source、approved_sample_path、handoff_rule等）写入deck_spec.json，再进入全片生产。

第三步：生成 Slide Job 并派发

全片生成前，用 prepare_slide_prompts.py 生成结构化的每页任务：

~/.codex-ppt-skill/.venv/bin/python {skill_root}/scripts/prepare_slide_prompts.py \ --spec {base_dir}/{deck_name}/deck_spec.json \ --out-dir {base_dir}/{deck_name} \ --selected-backend "<confirmed backend label>" \ --force

产出prompts/slide_XX.json、slide_jobs.json与slide_run_state.json。每个prompts/slide_XX.json都是自包含的 Slide Job，其 JSON 结构（见 slide-generation-and-subagents.md）与本风格 Brief 的字段一一对应：

{ "type": "16:9 full-slide PowerPoint image", "language": "Chinese", "canvas": { "aspect_ratio": "16:9", "use_full_canvas": true, "slide_number": "do not render a slide number" }, "style": { "name": "教学课件风", "visual_direction": "{与样张一致的最终风格描述}", "color_palette": "{主色与强调色}", "typography": "{字体性格、层级、字重、文本对齐}", "texture_and_finish": "{flat, paper, dashboard, editorial, whiteboard, etc.}", "deck_consistency": "same palette, typography, icon language, texture, and mood across all slides" }, "deck_context": { "source_summary": "{源材料全局摘要}", "core_claim": "{deck 的核心论点}", "canonical_terms": ["{术语1}", "{术语2}"] }, "layout": { "role": "concept | process | comparison | case study | ...", "intent": "{为什么本页使用该版式}", "composition": "{本页具体构图}", "content_zones": "{标题区、主体区、视觉区、页脚/标注区}", "variation_rule": "same style identity as the deck, but vary composition by slide role; do not repeat the same blueprint on adjacent slides unless the content is part of a deliberate repeated sequence", "relationship_to_previous_slide": "{新版式、延续版式、镜像版式或刻意重复序列}", "spacing": "clear hierarchy, coherent alignment, no overlapping elements" }, "text": { "title": "{本页标题}", "key_points": ["{要点1}", "{要点2}", "{要点3}"], "text_quality": "render all Chinese text exactly, clearly, and without garbled characters" }, "local_context": { "required_background": "{本页自包含所需的背景事实、列表、定义、比较或前页引用}" }, "visual_elements": { "main_visual": "{图标、图解、图表、插画或内容特定视觉方案}", "supporting_elements": "{箭头、卡片、标注、装饰元素、标签}" }, "constraints": [ "The final image itself must contain the title and key points.", "All text must be readable and correctly spelled.", "Keep the confirmed style consistent with the rest of the deck.", "No watermark, no unrelated logo, no extra slide number." ] }

派发阶段（slide-generation-and-subagents.md）使用slide_job_status.py查看派发槽位、record_slide_dispatch.py记录派发、record_slide_result.py记录结果、record_slide_blocker.py记录阻塞。子代理交接遵循 slide-worker.md 模板，其中强制要求：风格必须匹配已批准的样张、中文可读且不乱码、必需素材必须可见包含（不得用相似重绘替换）、无重叠或截断的重要内容；返回内容仅限backend_used、selected_source与一句qa_note。

第四步：CLI/API fallback 生成参数

若环境无内置图片工具而使用 image_gen.py，其默认参数与校验逻辑（从源码 image_gen.py 可确认）是：

• 默认模型gpt-image-2.5-flare，可通过环境变量CODEX_PPT_IMAGE_MODEL覆盖；
• 默认尺寸2560x1440（16:9，契合全页 PPT 图像），quality默认medium，输出格式默认png；
• GPT Image 2/2.5 系列尺寸校验：长边 ≤ 3840px、宽高均为 16px 的倍数、长边/短边 ≤ 3:1、总像素在 655,360 ～ 8,294,400 之间（见 image_gen.py）；
• quality可选low / medium / high / xhigh / max / auto，其中xhigh与max仅支持gpt-image-2.5-flare/gpt-image-2.5-sunburst（见 image_gen.py）；
• generate子命令支持--prompt / --prompt-file、--out、--n、--force、--dry-run，以及--augment（默认开启的结构化提示词增强，可把--style、--palette、--composition、--text、--constraints、--negative等字段拼入最终请求）；
• generate-batch子命令接收 JSONL 逐行任务，--concurrency默认 5（1～25）、--max-attempts默认 3（1～10）、--fail-fast可选；
• edit子命令支持--image（可多次）、--mask、--input-fidelity，用于样张或局部问题的精修。

后端选择的判定规则在 backend-selection.md 中：优先内置图片工具（Codex 通常为image_gen，OpenClaw 通常为image_generate），只有在内置不可用、缺少必需能力或用户明确要求 API/CLI 时才切换 fallback，且生成首图前必须向用户说明检查结果与所选后端。

风格文件的结构约定与二次复用

教学课件风作为内置风格，其文件结构本身就是仓库 style-library.md 中"保存可复用风格"的参考模板。若要基于它沉淀一套自定义课件风格，应按以下骨架组织风格文件（存放于${CODEX_PPT_HOME:-~/.codex-ppt-skill}/references/{style_name}.md，位于 skill 安装目录之外，可随 skill 更新与重装而保留）：

# {style_name} **适用场景:** - ... **GPT-Image-2 风格 Brief:** ```json { "type": "16:9 full-slide PowerPoint image", "style_name": "{style_name}", "best_for": "...", "visual_direction": "...", "canvas": { "aspect_ratio": "16:9", "background": "...", "composition": "...", "density": "..." }, "color_palette": { "primary": "...", "secondary": "...", "accent": "...", "neutral": "...", "rule": "..." }, "typography": { "title": "...", "body": "...", "labels": "...", "text_quality": "..." }, "layout_patterns": ["...", "..."], "layout_usage_rule": "...", "layout_blueprints": [ { "name": "...", "sections": [ {"position": "...", "count": 1, "labels": ["..."]} ] } ], "visual_elements": { "allowed": "...", "avoid": "..." }, "image_treatment": { "photos": "...", "screenshots": "...", "charts": "...", "illustrations": "..." }, "rendering_constraints": ["...", "..."] }

命名建议使用 2～8 个汉字的可复用风格名（如"深色数据科技风"），避免使用"我的风格1"这类模糊名称；风格文件必须自包含、不得依赖外部文件，且不得把用户私有内容（原文、业务数据、客户名、论文结果、精确引文）写入风格。 ## 常用 QA 检查清单 结合 [slide-generation-and-subagents.md](https://link.gitcode.com/i/5bc22b5f3ffa389e6c9a7579faf3303f) 的验收要求与本风格的 `rendering_constraints`，使用教学课件风生成后建议逐页检查： 1. **中文质量**：标题、正文、术语、公式、单位与数据标签是否精确、无乱码； 2. **风格一致性**：深蓝/浅蓝结构色是否稳定，强调色是否全片语义一致，图标语言与质感是否统一； 3. **素材保真**：必需源素材（实验图、架构图、数据图等）是否可见且内容未被重绘篡改（数据、坐标轴、标签、图例、数值需保留）； 4. **版式多样性**：是否每页都是三栏卡片或同一网格，是否按页面角色（概念/过程/案例/总结）选择了适配构图； 5. **图文并存与可读性**：每页是否既有有意义的视觉又有可读文本，是否有过小文字、重叠、截断； 6. **合规**：无水印、无无关 Logo、无编造的机构 Logo、无图内伪造文字。 ## 小结 教学课件风在仓库中的定位是"面向教学与培训场景的内置视觉系统"：它通过 `visual_direction`、画布、学术蓝配色、中文排印、标题系统、八种页面模式、三套构图蓝图与 13 条渲染约束，把"专业学术课件"这一抽象目标翻译成可被 GPT Image 模型稳定执行的 JSON Brief。接入 codex-ppt-skill 的标准流水线后，它贯穿"风格确认 → 样张审批 → Slide Job 生成 → 子代理派发 → 结果记录与组装"全流程，并可与 [style-library.md](https://link.gitcode.com/i/b11b494629f50cd9166f42d375fb6d59) 配合沉淀为用户自定义风格。如需查看其余内置风格或整套工作流，可继续阅读仓库的 [references/](https://link.gitcode.com/i/bd559dfa8b2f12ea8fccc5ab6175a429) 目录与 [docs/](https://link.gitcode.com/i/f05e4c8430c95aea3f9f1ae52a615c26) 下的各阶段文档。

• AI 技能
• 人工智能