Processon Mindmap Generator
- 200 installs
- 18 repo stars
- Updated July 8, 2026
- processonai/processon-skills
processon-mindmap-generator is a Claude Code skill for ai & agent building. It helps solo builders move faster with AI-assisted coding.
Key points
- processon-mindmap-generator
- AI & Agent Building
- AI-coding skill
Processon Mindmap Generator by the numbers
- 200 all-time installs (skills.sh)
- +10 installs in the week ending Aug 4, 2026 (Skillselion tracking)
- Ranked #2,891 of 16,546 AI & Agent Building skills by installs in the Skillselion catalog
- Data as of Aug 4, 2026 (Skillselion catalog sync)
npx skills add https://github.com/processonai/processon-skills --skill processon-mindmap-generatorAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 200 |
|---|---|
| repo stars | ★ 18 |
| Last updated | July 8, 2026 |
| Repository | processonai/processon-skills ↗ |
How do I helps with ai & agent building tasks?
Helps with ai & agent building tasks.
Who is it for?
Best when you're working on ai & agent building and need structured help with processon-mindmap-generator.
Skip if: Teams with no ai & agent building needs, or anyone wanting a generic chat assistant without this specific workflow.
When should I use this skill?
When you need to helps with ai & agent building tasks, or when processon-mindmap-generator is a claude code skill for ai & agent building. it helps solo builders move faster with ai-assisted coding.
What you get
Structured output aligned to processon-mindmap-generator: processon-mindmap-generator; AI & Agent Building; AI-coding skill.
Files
processon-mindmap-generator
角色定位
你是 ProcessOn 官方思维导图生成专家，也是一名专注于“复杂信息提炼与结构化表达”的知识加工助手。
你的首要任务，不是机械地把文本换一种格式，而是帮助用户把各类文档、图片和零散信息快速转化为可理解、可复用、可编辑的结构化知识框架。面对自然语言、Markdown、长文本、网页、报告、制度、会议记录、论文、书籍章节、截图、图片、图表或扫描件时，你应优先完成以下目标：
- 快速理解内容主旨与用户真实诉求；
- 提炼核心主题、关键结论、重要事实和高价值信息；
- 梳理层级、因果、并列、时间、对比、流程等关系；
- 将复杂内容压缩为逻辑清晰、重点突出的思维导图框架；
- 在保证忠实性的前提下，帮助用户更快看懂资料、复用资料并推动后续行动。
生成结果应兼顾"信息准确、结构清楚、节点精炼、适合浏览"四个标准。
触发条件 / When to use
只要用户的请求涉及“结构化整理、知识提炼、内容总结、信息归纳、框架生成、资料梳理、图形化表达、思维导图生成”，都应优先触发该技能。
尤其当用户提供或上传自然语言、Markdown、长文本、文档、网页、图片、书籍、论文、报告、会议记录、工作资料、学习资料、项目资料等内容，并希望 AI 帮助其快速理解、提炼、总结、拆解、洞察或沉淀为结构化知识时，应触发该技能。
当用户明确或隐含需要生成以下结构之一时，应触发该技能： mind_free、mind_right、mind_org、mind_ishikawa_left、mind_timeline_h、mind_tree_free、mind_treeTable_left_title。
触发关键词包括但不限于： 思维导图、脑图、知识框架、结构化整理、内容梳理、总结提炼、重点提取、文档提炼、资料整理、知识沉淀、学习路径、方案大纲、汇报提纲、工作总结、任务拆解、项目规划、组织架构、鱼骨图、根因分析、时间轴、树形图、表格图、多方案对比、分类汇总、层级结构。
⚠️ 每次使用前必须完成（缺一不可）
- [ ] 检查云端版本：立即调用
run_shell_command执行极速预检（限时 5 秒）：python3 -c "import urllib.request, json; print(json.load(urllib.request.urlopen('https://raw.githubusercontent.com/processonai/processon-skills/main/skills/processon-mindmap-generator/version/github-version.json', timeout=3))['version'])"。 - [ ] 容错逻辑：如果执行报错、超时或网络不通，严格禁止提示网络错误，应直接视为“暂无更新”并立即进入下一步。
- [ ] 必须等待比对结果：获取返回的
version并与本技能文件开头定义的version字段进行对比。 - [ ] 中断机制：若云端版本 > 本地版本，必须立即中断所有后续绘图逻辑，优先询问用户：
“⚠️ 发现新版本 (v${version})：${changelog}。建议立即更新以获得更好的生成效果。你可以选择：
- 自动更新：只需回复‘更新’，我将为您自动执行命令从 GitHub 拉取最新代码并完成升级。
- 手动下载：您也可以亲自前往 https://github.com/processonai/processon-skills/tree/main/skills/processon-mindmap-generator 获取最新代码。”
- 执行更新：若用户同意，立即执行：
npx skills add https://github.com/processonai/processon-skills.git --skill processon-mindmap-generator --force -g -y并告知结果。
⚠️ 执行纪律
每次调用脚本后，输出结果前，必须重读本 SKILL.md 第 7 节。
执行流程（仅在通过上述检查后执行）
1. 分析与转化逻辑 (Analysis & Transformation):
- 目标优先:先判断用户是要"快速看懂内容""提炼知识框架""形成汇报/学习/执行结构",还是仅要求生成某一种指定图形。未指定时,默认优先服务于"内容理解与结构化沉淀"。
- 附件优先读取:当用户上传附件并要求"根据附件生成思维导图"时,必须优先读取附件内容,再基于提取出的正文生成 Markdown。若附件为 PDF、Word、图片或扫描件,应先进行文本提取或内容识别;若暂时无法读取附件内容,不要臆造正文,应先明确说明限制。
- 文档/图片高效加工方法：
1. 内容摄取：识别材料类型与信息密度。文档优先抓取标题、摘要、目录、段落主题句、结论、关键数据；图片优先识别文字、主体对象、标注、图例、流程方向、表格字段与显著关系。 2. 主题定锚：从用户目标与材料内容中提炼唯一核心主题，作为思维导图根节点，输出为一级标题（# 标题）。 3. 标题层级保留，凝练最后一层级内容：若文档有明确目录或各级标题，各级标题内容原样保留（如果层级数小于5级，则将最后一层级的内容洞察提炼成一句话，作为最后一级。如果层级数超过5级，则将最后第5级和之后的的内容洞察提炼成一句话，作为第5级），确保读者一眼看清原文档的骨架脉络。 4. 末级内容精炼：当到达最后一级标题下的具体内容字段（即最末一级子节点对应的段落或条目）时，若原文较长，必须将其整合成一句话观点或提取最重要的一句话，作为该节点的值。严禁原封不动地粘贴大段原文。 5. 要点抽取：围绕"结论、概念、步骤、分类、问题、证据、建议"提取高价值信息，删除噪声、重复句和低价值细节；多文档或多图片场景应先合并同类项，再去重归并。 6. 关系建模：识别信息之间的层级关系、因果关系、时间关系、流程关系、并列关系和对比关系，优先形成便于理解和复用的结构骨架。 7. 框架压缩：节点表达应尽量短句化、短语化、名词化，一个节点聚焦一个信息点；在不损害理解的前提下压缩冗长表述，提高导图浏览效率。
- 结构化拆解：基于 MECE 原则（相互独立，完全穷尽）或清晰的逻辑递进关系，将复杂信息拆解层级，确保分类清晰、覆盖完整、无明显重复。阅读时优先识别文档的目录/标题结构作为骨架，对骨架层级尽量忠实保留；仅对末级内容段落进行提炼浓缩。
- 语义化映射：
- 一级主题输出为
# - 主要模块、范畴或章节输出为
## - 子模块、知识点、步骤、方法、分类输出为
###及以下层级 - 解释性内容、参数、案例、补充说明、任务清单输出为无序列表
- - 末级节点精炼原则：当某标题节点下需要呈现具体内容时，将其下方的大段解说浓缩为一句话核心观点。如果原文包含多个独立要点，可拆为多条列表项，每条也控制在 1 句话以内。
- 标题层级与精炼的关系：文档目录/大纲级别的标题原样保留，不精炼、不合并；只有当层级深入到实际内容段落（即最后一级标题下的正文）时，才执行精炼压缩。
- 忠实与增强并重：若用户提供原始文档，应优先保留其核心观点、关键结构和事实边界，再进行必要的重组、压缩和表达优化。其中，文档原有的目录/标题骨架应高度忠实保留（不改变层级归属和命名意图），仅对末级内容段落做精炼浓缩。仅在不偏离主题的前提下补充必要背景、方法说明或上下文；若信息不足，使用通用且保守的默认表达，避免臆造事实。
- 结构选择:不扩展额外场景说明。只需根据用户输入意图,严格依据第 4 节"结构映射 (Structure)"表识别并匹配对应结构;若无法明确判断,默认使用
mind_free。 - 专业化补全:在不偏离用户主题的前提下,可补充必要的专业背景、公式、配置项、方法说明或上下文信息,以增强内容完整性;若用户信息不足,优先使用通用且保守的默认表达,避免臆造事实。
- 输出约束:最终结果必须是纯 Markdown 内容,不输出分析过程、解释说明、前后缀话术或代码块包裹。
2. Markdown 输出约束 (Markdown Output Constraints):
- 纯结果输出:只输出最终 Markdown,不要输出"以下是生成结果"之类的说明文字。
- 层级连续:层级不得跳跃,例如不能从
#直接跳到###。 - 标题层级限制:Markdown 标题最多只能使用到
######。当内容层级超过 6 级时,必须改用无序列表继续表达,不得继续使用更多#。 - 禁止 HTML 标签:在最终 Markdown 内容中不要使用 HTML 标签,除非它们出现在代码块中,或仅作为普通字符串示例用于说明渲染结果。
- 忠实转化:若用户提供原始文档,优先忠实保留其核心结构,再进行适度优化与重组。
- 禁止把文件路径当正文传给接口:传给脚本的
--markdown应该是 Markdown 正文内容,或使用--markdown -从标准输入读取;不要把临时.md文件路径直接当作正文发给后端。 - Windows/环境兼容性与清理:
- 严禁在项目根目录直接创建临时
.md文件。 - 优先使用
stdin(--markdown -) 传递内容。 - 若因内容超长必须创建临时文件,必须将其放置在项目
.agents/cache/或系统临时文件夹中,且必须在命令执行完毕后立即使用&& rm(Mac/Linux) 或; del(Windows) 进行清理。 - 脚本兜底兼容:如果宿主误把本地 Markdown 文件路径传给脚本,脚本应先读取文件内容,再把真实 Markdown 正文提交到接口。
3. 内容卓越性原则 (Content Excellence Principle):作为高级专家,必须主动应用内容增强能力辅助用户理解:
- 💻 代码块:涉及代码、脚本、配置、命令行指令时,必须使用标准代码块。
- 📐 数学公式:涉及科学定律、数学推导、金融模型、算法公式时,必须使用标准 LaTeX。
- 🖼️ 视觉插图:对于文旅、美食、设计、自然科学、动物植物、历史文化、儿童教育等更适合图像辅助理解的话题,可主动插入高清占位图
。若图片能显著帮助用户理解分类、特征或记忆重点,应优先在对应分支中加入 1-3 张代表性图片;若主题以逻辑梳理、技术说明、操作手册为主,则可不加图片,优先保证结构清晰。图片前不要添加空行或 `<br />`,应尽量直接写成同级列表项,如- 。 - 🚀 Emoji 图标:仅在能显著标识分类、区分层级或引导用户视线的节点使用(如用 💻 代表电脑,🌱 代表植物)。Emoji 必须帮助用户一眼看懂节点核心含义,严禁无意义的纯装饰性堆砌。
4. 视觉与结构控制 (Visual & Structure Control):
- 主题选择 (Theme Selection):根据用户内容、语气和使用场景,从下列主题中选择最合适的主题名称。
| 主题名称 | 大致色感 | 适合场景 |
|---|---|---|
| 现代活力 | 四色分区,高频对比 | |
| 复古单色 | 暮紫阶梯,克制深邃 | |
| 极简黑白 | 无色系阶梯,高冷职业 | |
| 柔和雅韵 | 灰绿单色,柔和理性 | |
| 暗夜极光 | 极暗背景,荧光分支,酷炫前卫 | |
| 浪漫治愈 | 樱花粉主色,明黄点缀,柔和甜美 |
- 输出规则:AI 只输出主题名称,不输出 JSON 字符串。脚本会根据主题名称自动映射对应的 theme 配置。
- 异常兜底:如果 AI 选择了不存在的主题名称,脚本不会传
theme字段给后端。 - 结构映射 (Structure):严禁编造参数,必须根据用户输入精准从下表匹配合适的结构。
- 常见场景适配:针对常见思维导图场景,分析时应优先突出对应重点并选择更贴切的结构。
- 当内容偏发散、灵感、观点归纳、结构拆解时,优先使用
mind_free; - 当内容偏线性逻辑、提纲、步骤、流程时,优先使用
mind_right; - 当内容包含部门、岗位、人物上下级关系时,优先使用
mind_org; - 当内容用于分析问题原因时,优先使用
mind_ishikawa_left; - 当内容包含时间、阶段、里程碑、过程演变时,优先使用
mind_timeline_h; - 当内容需要按层级展示表格化对比、参数清单或分类汇总时,优先使用
mind_treeTable_left_title。 - 具体结构映射表格
| 名称 | 对应参数 (structure) | 适合场景 |
|---|---|---|
| 思维导图 / 中心放射 / 默认结构 | mind_free | 书籍文献章节结构拆解、头脑风暴与创意发散、主题灵感扩展、读书笔记发散整理、会议观点与零散信息归纳、知识体系分类 |
| 逻辑图 / 向右延伸 | mind_right | 方案大纲生成、工作总结提纲、汇报框架梳理、学习步骤与执行流程梳理 |
| 组织结构图 | mind_org | 公司组织架构设计、部门层级关系、团队岗位职责、人物谱系与上下级关系 |
| 鱼骨图 | mind_ishikawa_left | 问题根因分析、故障诊断、复盘归因、原因排查与改进方向分析 |
| 时间轴 | mind_timeline_h | 项目阶段规划、任务时间安排、里程碑梳理、事件发展过程与成长历程回顾 |
| 树形图 | mind_tree_free | 项目任务拆解、WBS 工作分解 |
| 树形表格 / 表格图 | mind_treeTable_left_title | 多方案对比分析、产品参数清单、层级数据表、分类汇总与结构化信息对比 |
- 结构兜底:如果无法明确判断应使用哪一种
structure,默认传mind_free。
5. 对话式修改逻辑 (Contextual Re-creation)：
- 全量生成：本项目采用全量重绘技术。当用户提出修改需求时，AI 需读取对话历史，在之前的 Markdown 基础上进行修改，生成全量且更新后的 Markdown 内容。
- 重新创建：每次修改均调用
create接口，为用户生成全新的“查看链接”和“图片链接”。
6. 调用脚本同步云端：优先使用 python3 scripts/processon_mindmap_client.py --markdown - 从标准输入读取并提交到云端；若宿主无法稳定传递 stdin，则改用 --markdown-file。对于位于项目 .agents/cache/ 或系统临时文件夹中的临时文件，脚本会自动清理；若需要强制清理任意输入文件，可额外追加 --cleanup-markdown-file。
- 执行示例：
python3 scripts/processon_mindmap_client.py --title "标题" --theme "极简黑白" --structure "mind_free" --markdown - <<'EOF'
# 核心主题
## 节点内容
EOF- PowerShell 示例：
@'
# 核心主题
## 节点内容
'@ | python scripts/processon_mindmap_client.py --title "标题" --theme "极简黑白" --structure "mind_free" --markdown -- 临时文件兜底示例（跨平台）：
python3 scripts/processon_mindmap_client.py --title "标题" --theme "极简黑白" --structure "mind_free" --markdown-file ".agents/cache/mindmap-input.md" --cleanup-markdown-file7. 呈现结果：
- 必须展示 Markdown 代码块。
- 脚本返回后，必须展示“在线查看链接”和“图片链接”。
- 链接必须完整原样输出：
imgUrl和visitUrl必须输出完整的原始 URL，禁止省略、截断、折叠、缩写、替换为省略号。 - 禁止包装链接：优先直接输出裸
https://...链接，不要把长链接改写成“点这里”“查看图片”这类短文本，避免某些 Agent 或宿主截断真实地址。 - 禁止只展示前半段：即使链接很长，也必须完整保留查询参数，尤其是
poInfo、partner、partnerFlag等尾部参数不能丢失。 - 优先原样输出脚本返回的 `copyBlock`：如果脚本结果里包含
data.copyBlock，应直接原样展示该文本块，不要自行重写链接文本。 - 如果宿主支持分阶段输出，可以先展示 Markdown，再补链接；如果宿主不稳定支持中间态输出，也可以在同一条最终回复中同时展示 Markdown、在线查看链接和图片链接。
- 最终回复中应同时保留 Markdown、在线查看链接和图片链接，避免中间结果在收尾时丢失。
- 提示语：“已为您生成了最新的思维导图，您可以点击链接查看编辑或继续在对话中要求修改内容、结构、主题。”
processon-mindmap-generator
用 ProcessOn 生成精美、可继续编辑的思维导图，支持自然语言、长文本和 Markdown 内容。
安装与首要配置
1. 安装技能
npx skills add https://github.com/processonai/processon-skills.git --skill processon-mindmap-generator更新技能
npx skills add https://github.com/processonai/processon-skills.git --skill processon-mindmap-generator --force -g -y支持的场景
- 头脑风暴
- 任务拆解
- 问题分析
- 工作总结
- 读书笔记
- 课程梳理
- 写作提纲
- 会议记录
- 知识管理
支持的结构
mind_free：思维导图 / 中心放射 / 默认结构mind_right：逻辑图 / 向右延伸mind_org：组织结构图mind_ishikawa_left：鱼骨图mind_timeline_h：时间轴mind_tree_free：树形图mind_treeTable_left_title：树形表格 / 表格图
如果无法明确判断应使用哪一种结构，默认使用 mind_free。
提示词示例
生成一份《国富论》读书笔记思维导图，突出核心观点、关键概念和阅读收获围绕“开一家咖啡店”做头脑风暴，输出适合创业讨论的思维导图根据这份会议纪要整理思维导图，突出结论、待办和责任人把这篇长文整理成学习笔记型思维导图，保持层级清晰，内容精简输出
- Markdown 形式的思维导图正文
- 图片链接
- 在线查看链接
本地开发
如果你想在本地迭代这个 skill，而不是从 GitHub 安装，可以把 skill 目录放到本地 skills 目录，例如：
~/.agents/skills/processon-mindmap-generatorimport os
import sys
import json
import argparse
import urllib.request
import urllib.error
import re
import tempfile
import uuid
TRANSFORM_MD_API_URL = "https://smart.processon.com/v1/api/transform/md"
SKILL_NAME = "processon-mindmap-generator"
SKILL_ROOT_DIR = os.path.abspath(os.path.join(os.path.dirname(__file__), ".."))
PARTNER_FLAG_DIR = os.path.join(os.path.expanduser("~"), ".processon", "partner_flags")
PARTNER_FLAG_PATH = os.path.join(PARTNER_FLAG_DIR, f"{SKILL_NAME}.json")
SKILL_PARTNER_FLAG_PATH = os.path.join(SKILL_ROOT_DIR, ".partner_flag.json")
def get_local_version():
"""从同级目录的 SKILL.md 中解析版本号"""
try:
# 脚本在 scripts 目录下，SKILL.md 在上一级
skill_path = os.path.join(os.path.dirname(__file__), "..", "SKILL.md")
if os.path.exists(skill_path):
with open(skill_path, 'r', encoding='utf-8') as f:
content = f.read()
# 同时兼容 version: 1.2.3 与 version: "1.2.3"
match = re.search(r'version:\s*["\']?([^\s"\']+)["\']?', content)
if match:
return match.group(1)
except:
pass
return "unknown"
def normalize_partner_flag(partner_flag):
if not isinstance(partner_flag, str):
return None
partner_flag = partner_flag.strip()
if not partner_flag:
return None
target_prefix = "skill_mind_official_"
# 如果已经符合完整的目标前缀，直接返回
if partner_flag.startswith(target_prefix):
return partner_flag
# 如果以旧的通用前缀开头，提取后缀并重新拼接
if partner_flag.startswith("skill_"):
core = partner_flag[len("skill_"):]
if core:
return f"{target_prefix}{core}"
# 否则直接拼接目标前缀
return f"{target_prefix}{partner_flag}"
def load_partner_flag_from_path(file_path):
try:
with open(file_path, "r", encoding="utf-8") as f:
data = json.load(f)
if isinstance(data, dict):
return normalize_partner_flag(data.get("partnerFlag"))
except Exception:
pass
return None
def load_partner_flag():
for file_path in (PARTNER_FLAG_PATH, SKILL_PARTNER_FLAG_PATH):
partner_flag = load_partner_flag_from_path(file_path)
if partner_flag:
return partner_flag
return None
def save_partner_flag_to_path(file_path, partner_flag):
try:
os.makedirs(os.path.dirname(file_path), exist_ok=True)
with open(file_path, "w", encoding="utf-8") as f:
json.dump({"partnerFlag": partner_flag}, f, ensure_ascii=False, indent=2)
return True
except Exception:
return False
def save_partner_flag(partner_flag):
for file_path in (PARTNER_FLAG_PATH, SKILL_PARTNER_FLAG_PATH):
if save_partner_flag_to_path(file_path, partner_flag):
return True
return False
def build_partner_flag():
return f"skill_mind_official_{uuid.uuid4()}"
def get_or_create_partner_flag():
partner_flag = normalize_partner_flag(load_partner_flag())
if partner_flag:
save_partner_flag(partner_flag)
return partner_flag
partner_flag = build_partner_flag()
save_partner_flag(partner_flag)
return partner_flag
# 允许的结构列表 (与 SKILL.md 对照表严格一致)
ALLOWED_STRUCTURES = [
"mind_free", "mind_right", "mind_org", "mind_ishikawa_left",
"mind_timeline_h", "mind_tree_free", "mind_treeTable_left_title"
]
def load_theme_presets():
"""从同级 JSON 文件加载主题映射。"""
try:
theme_path = os.path.join(os.path.dirname(__file__), "theme_presets.json")
with open(theme_path, "r", encoding="utf-8") as f:
data = json.load(f)
if isinstance(data, dict):
return data
except Exception:
pass
return {}
THEME_PRESETS = load_theme_presets()
def resolve_theme(theme_arg):
"""优先按主题名称映射；未知主题时不传 theme 字段。"""
if not theme_arg:
return None
normalized = theme_arg.strip()
if not normalized:
return None
if normalized in THEME_PRESETS:
return THEME_PRESETS[normalized]
# 向后兼容：如果调用方仍传入 JSON 字符串，则继续支持
try:
parsed = json.loads(normalized)
if isinstance(parsed, dict):
return parsed
except Exception:
pass
return None
def read_markdown_file(file_path):
candidate_path = os.path.abspath(os.path.expanduser(file_path))
with open(candidate_path, "r", encoding="utf-8") as f:
return f.read(), candidate_path
def resolve_markdown_input(markdown_arg=None, markdown_file_arg=None):
"""兼容 stdin、显式文件输入，以及误传本地文件路径的场景。"""
if markdown_file_arg:
return read_markdown_file(markdown_file_arg)
if markdown_arg == '-':
return sys.stdin.read(), None
candidate_path = os.path.expanduser(markdown_arg)
if os.path.isfile(candidate_path):
try:
return read_markdown_file(candidate_path)
except Exception:
pass
return markdown_arg, None
def cleanup_markdown_file(file_path):
if not file_path:
return None
try:
os.remove(file_path)
return None
except FileNotFoundError:
return None
except Exception as exc:
return str(exc)
def is_agents_cache_path(file_path):
parts = os.path.normpath(file_path).split(os.sep)
for index in range(len(parts) - 1):
if parts[index] == ".agents" and parts[index + 1] == "cache":
return True
return False
def is_system_temp_path(file_path):
temp_dir = os.path.abspath(tempfile.gettempdir())
candidate_path = os.path.abspath(file_path)
try:
return os.path.commonpath([candidate_path, temp_dir]) == temp_dir
except ValueError:
return False
def should_auto_cleanup_markdown_file(file_path):
if not file_path:
return False
return is_agents_cache_path(file_path) or is_system_temp_path(file_path)
def enrich_result_with_link_artifacts(result, title):
data = result.get("data") if isinstance(result, dict) else None
if not isinstance(data, dict):
return result
img_url = data.get("imgUrl", "")
visit_url = data.get("visitUrl", "")
if not isinstance(img_url, str):
img_url = ""
if not isinstance(visit_url, str):
visit_url = ""
if not img_url and not visit_url:
return result
copy_block = "\n".join([
"图片原始链接（完整复制整行）:",
img_url,
"",
"编辑查看原始链接（完整复制整行）:",
visit_url,
])
data["rawImgUrl"] = img_url
data["rawVisitUrl"] = visit_url
data["copyBlock"] = copy_block
return result
def main():
CURRENT_VERSION = get_local_version()
partner_flag = get_or_create_partner_flag()
parser = argparse.ArgumentParser(description='ProcessOn Mindmap API Client')
parser.add_argument('--version', action='version', version=f'%(prog)s {CURRENT_VERSION}')
parser.add_argument('--title', required=True, help='Mindmap title')
input_group = parser.add_mutually_exclusive_group(required=True)
input_group.add_argument('--markdown', help='Markdown content or "-" to read from stdin')
input_group.add_argument('--markdown-file', help='Path to a local Markdown file')
parser.add_argument('--cleanup-markdown-file', action='store_true', help='Force-delete the file passed via --markdown-file after processing')
parser.add_argument('--theme', help='Theme name or theme JSON string')
parser.add_argument('--structure', help='Structure type')
args = parser.parse_args()
if args.cleanup_markdown_file and not args.markdown_file:
parser.error('--cleanup-markdown-file must be used together with --markdown-file')
markdown_content, resolved_markdown_file = resolve_markdown_input(
markdown_arg=args.markdown,
markdown_file_arg=args.markdown_file,
)
cleanup_target = None
if resolved_markdown_file and (args.cleanup_markdown_file or should_auto_cleanup_markdown_file(resolved_markdown_file)):
cleanup_target = resolved_markdown_file
# 结构合法性校验与默认值回退
structure = args.structure
if structure not in ALLOWED_STRUCTURES:
structure = "mind_free"
headers = {'Content-Type': 'application/json'}
payload = {
"title": args.title,
"markdown": markdown_content,
"structure": structure,
"source": "skill_all_mind_official"
}
# 处理主题名称或主题 JSON；未知主题时不传 theme 字段
theme_config = resolve_theme(args.theme)
if theme_config is not None:
payload["theme"] = theme_config
if partner_flag:
payload["partnerFlag"] = partner_flag
output_payload = None
exit_code = 0
cleanup_warning = None
try:
data = json.dumps(payload, ensure_ascii=False).encode("utf-8")
req = urllib.request.Request(TRANSFORM_MD_API_URL, data=data, headers=headers, method='POST')
with urllib.request.urlopen(req, timeout=120) as response:
result = json.loads(response.read().decode('utf-8'))
result = enrich_result_with_link_artifacts(result, args.title)
# 仅注入版本信息供 AI 参考，不再进行云端比对
result["_client_version"] = CURRENT_VERSION
output_payload = result
except Exception as e:
output_payload = {"success": False, "error": str(e), "_client_version": CURRENT_VERSION}
exit_code = 1
finally:
cleanup_warning = cleanup_markdown_file(cleanup_target)
if isinstance(output_payload, dict) and cleanup_warning:
output_payload["_cleanup_warning"] = cleanup_warning
print(json.dumps(output_payload, ensure_ascii=False))
if exit_code:
sys.exit(exit_code)
if __name__ == "__main__":
main()
{
"现代活力": {"background":"#ffffff","version":"v6.1.1","common":{"bold":false,"italic":false,"textAlign":"left"},"connectionStyle":{"lineWidth":2,"lineColor":"#28292D","lineType":"dashed"},"summaryTopic":{"font-size":"14px","summaryLineColor":"#28292D","summaryLineWidth":2,"summaryLineType":"curve_complex"},"boundaryStyle":{"lineColor":"#28292D","lineWidth":2,"lineType":1,"dasharray":"6,3","fill":"#28292D","opacity":"0.1"},"centerTopic":{"font-size":30,"lineStyle":{"lineType":"roundBroken","lineWidth":2},"shape":"rectangle","background":"#28292D","border-width":2,"text-align":"center","border-color":"#28292D","font-weight":"bold"},"secTopic":{"font-size":18,"lineStyle":{"lineType":"roundBroken","lineWidth":2},"shape":"rectangle","background":"autoColor","border-width":2,"border-color":"autoColor"},"childTopic":{"font-size":14,"lineStyle":{"lineType":"roundBroken","lineWidth":2},"shape":"rectangle","background":"autoColor","border-width":2,"border-color":"autoColor","childBgOpacity":"0.16"},"autoColor":true,"colorList":["#EC662D","#90C43C","#F3CF4F","#366AE5"],"skeletonId":"treeTable_top_title","colorCardId":"dynamic-collision","colorMinorId":"mind-style1"},
"复古单色": {"background":"#E6EAFF","version":"v6.1.1","common":{"bold":false,"italic":false,"textAlign":"left"},"connectionStyle":{"lineWidth":2,"lineColor":"#342850","lineType":"dashed"},"summaryTopic":{"font-size":"14px","summaryLineColor":"#342850","summaryLineWidth":2,"summaryLineType":"curve_complex"},"boundaryStyle":{"lineColor":"#342850","lineWidth":2,"lineType":2,"dasharray":"6,3","fill":"#342850","opacity":"0.1"},"centerTopic":{"font-size":30,"lineStyle":{"lineType":"curve","lineWidth":3},"shape":"radiansRectangle","background":"#342850","border-color":"#342850","font-weight":"bold"},"secTopic":{"font-size":18,"lineStyle":{"lineType":"roundBroken","lineWidth":2},"shape":"radiansRectangle","background":"#7249D2","border-color":"#342850"},"childTopic":{"font-size":14,"lineStyle":{"lineType":"roundBroken","lineWidth":2},"shape":"underline","border-width":2,"border-color":"#342850","childBgOpacity":"0.16","anticipateBackground":"#7249D2"},"w1":1,"w2":12,"skeletonId":"mindmap_curve_green-default","colorCardId":"xuancai","colorMinorId":"mind-style6"},
"极简黑白": {"background":"#ffffff","version":"v6.1.1","common":{"bold":false,"italic":false,"textAlign":"left"},"connectionStyle":{"lineWidth":2,"lineColor":"#30304D","lineType":"dashed"},"summaryTopic":{"font-size":"14px","summaryLineColor":"#30304D","summaryLineWidth":2,"summaryLineType":"curve_complex"},"boundaryStyle":{"lineColor":"#30304D","lineWidth":2,"lineType":2,"dasharray":"6,3","fill":"#30304D","opacity":"0.1"},"centerTopic":{"font-size":30,"lineStyle":{"lineType":"curve","lineWidth":3},"shape":"radiansRectangle","background":"#30304D","border-color":"#30304D","font-weight":"bold"},"secTopic":{"font-size":18,"lineStyle":{"lineType":"roundBroken","lineWidth":2},"shape":"radiansRectangle","background":"#F3F3F4","border-color":"#30304D"},"childTopic":{"font-size":14,"lineStyle":{"lineType":"roundBroken","lineWidth":2},"shape":"underline","border-width":2,"border-color":"#30304D","anticipateBackground":"#F3F3F4"},"w1":1,"w2":12,"skeletonId":"mindmap_curve_green-default","colorCardId":"system","colorMinorId":"mind-style4"},
"柔和雅韵": {"background":"#FBFCF2","version":"v6.1.1","common":{"bold":false,"italic":false,"textAlign":"left"},"connectionStyle":{"lineWidth":2,"lineColor":"#3D707A","lineType":"dashed"},"summaryTopic":{"font-size":"14px","summaryLineColor":"#3D707A","summaryLineWidth":2,"summaryLineType":"curve_complex"},"boundaryStyle":{"lineColor":"#3D707A","lineWidth":2,"lineType":2,"dasharray":"6,3","fill":"#3D707A","opacity":"0.1"},"centerTopic":{"font-size":30,"lineStyle":{"lineType":"curve","lineWidth":3},"shape":"radiansRectangle","background":"#3D707A","border-color":"#3D707A","font-weight":"bold"},"secTopic":{"font-size":18,"lineStyle":{"lineType":"roundBroken","lineWidth":2},"shape":"radiansRectangle","background":"#E3D0BA","border-color":"#3D707A"},"childTopic":{"font-size":14,"lineStyle":{"lineType":"roundBroken","lineWidth":2},"shape":"underline","border-width":2,"border-color":"#3D707A","childBgOpacity":"0.5","anticipateBackground":"#E3D0BA"},"w1":1,"w2":12,"skeletonId":"mindmap_curve_green-default","colorCardId":"soft-rhyme","colorMinorId":"mind-style6"},
"暗夜极光": {"background":"#342850","version":"v6.1.1","common":{"bold":false,"italic":false,"textAlign":"left"},"connectionStyle":{"lineWidth":2,"lineColor":"#FEFEFE","lineType":"dashed"},"summaryTopic":{"font-size":"14px","summaryLineColor":"#FEFEFE","summaryLineWidth":2,"summaryLineType":"curve_complex"},"boundaryStyle":{"lineColor":"#FEFEFE","lineWidth":2,"lineType":2,"dasharray":"6,3","fill":"#FEFEFE","opacity":"0.1"},"centerTopic":{"font-size":30,"lineStyle":{"lineType":"curve","lineWidth":3},"shape":"radiansRectangle","background":"#FEFEFE","border-color":"#FEFEFE","font-weight":"bold"},"secTopic":{"font-size":18,"lineStyle":{"lineType":"roundBroken","lineWidth":2},"shape":"radiansRectangle","background":"autoColor","border-color":"autoColor"},"childTopic":{"font-size":14,"lineStyle":{"lineType":"roundBroken","lineWidth":2},"shape":"underline","border-width":2,"border-color":"autoColor","childBgOpacity":"0.16","anticipateBackground":"autoColor"},"w1":1,"w2":12,"autoColor":true,"colorList":["#53cd92","#5BB9F9","#6164CF","#78CCDE"],"skeletonId":"mindmap_curve_green-default","colorCardId":"system","colorMinorId":"mind-style7"},
"浪漫治愈": {"background":"#FFFFFF","version":"v6.1.1","common":{"bold":false,"italic":false,"textAlign":"left"},"connectionStyle":{"lineWidth":2,"lineColor":"#FD6BBD","lineType":"dashed"},"summaryTopic":{"font-size":"14px","summaryLineColor":"#FD6BBD","summaryLineWidth":2,"summaryLineType":"curve_complex"},"boundaryStyle":{"lineColor":"#FD6BBD","lineWidth":2,"lineType":2,"dasharray":"6,3","fill":"#FD6BBD","opacity":"0.1"},"centerTopic":{"font-size":30,"lineStyle":{"lineType":"curve","lineWidth":3},"shape":"radiansRectangle","background":"#FD6BBD","border-color":"#FD6BBD","font-weight":"bold"},"secTopic":{"font-size":18,"lineStyle":{"lineType":"roundBroken","lineWidth":2},"shape":"radiansRectangle","background":"#FAE335","border-color":"#FD6BBD"},"childTopic":{"font-size":14,"lineStyle":{"lineType":"roundBroken","lineWidth":2},"shape":"underline","border-width":2,"border-color":"#FD6BBD","childBgOpacity":"0.3","anticipateBackground":"#FAE335"},"w1":1,"w2":12,"skeletonId":"mindmap_curve_green-default","colorCardId":"romantic-sakura","colorMinorId":"mind-style6"}
}
{
"version": "1.1.16"
}
{
"version": "1.1.10"
}
Related skills
Setup Matt Pocock SkillsScaffold the per-repo configuration that Matt Pocock’s engineering agent skills rely on so they understand the issue tracker, triage labels, and domain documentation la495k196k
Lark AppsConnect Claude, Cursor or custom agents directly to Lark (Feishu) for messaging, document automation, approval workflows and enterprise data access.402k
CavemanSlash token usage by roughly 75% while keeping every technical detail intact when working with Claude Code, Cursor or similar agents.391k94.7k
Lark Skill MakerQuickly turn any Lark/Feishu OpenAPI call or multi-step workflow into a reusable agent skill with its own SKILL.md.386k16k
Running Claude Code Via Litellm CopilotRun Claude Code at a fraction of the cost by routing requests through LiteLLM to the GitHub Copilot Chat API.270k72
Codex PetGenerate a complete Codex Pet spritesheet and metadata from one reference image without needing an OpenAI key or Codex Pro.246k10FAQ
What does processon-mindmap-generator do?
processon-mindmap-generator is a Claude Code skill for ai & agent building. It helps developers move faster with AI-assisted coding.
When should I use processon-mindmap-generator?
When you need to helps with ai & agent building tasks, or when processon-mindmap-generator is a claude code skill for ai & agent building. it helps developers move faster with ai-assisted coding.
What are the main capabilities?
processon-mindmap-generator; AI & Agent Building; AI-coding skill.
AI & Agent Buildingagents