Submit Producti Directories Merged logo

Submit Producti Directories Merged

Organization
flaqai
submit-producti-directories-merged

外链自动提交合并版:在当前授权范围内处理目录投递和一对一官方 Contact 邮件申请,包含去重、验证、结果取证与可恢复审计。

Overview

Publisherflaqai
Repositorybacklink_skills
Skill namesubmit-producti-directories-merged
Stars
760
Forks
237
Bundled files
7
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 7 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by flaqai on GitHub. Read the source before you install it.

Installation

Install the Submit Producti Directories Merged AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/flaqai/backlink_skills/tree/main/submit-producti-directories-merged
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/flaqai/backlink_skills.git /tmp/backlink_skills
mkdir -p .claude/skills
cp -r /tmp/backlink_skills/submit-producti-directories-merged .claude/skills/submit-producti-directories-merged
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Submit Producti Directories Merged in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Submit Producti Directories Merged on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Submit Producti Directories Merged is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

外链自动提交合并版

适用范围

本技能用于受控批量处理产品目录、资料页、项目展示页和一对一官方 Contact 邮件申请。目标是高效完成简单、可验证的动作,并把需要人工处理的页面完整交接。

不适用于付费链接、强制互链、虚构资料、群发、自动跟进、绕过验证码、请求对方发布文章,或任何超出当前授权的动作。

本公开版不得携带或示例化任何任务专属的品牌、域名、账号、联系人、凭据、本机路径、历史站点或执行结果。

每批次开始前

每个批次都必须重新确认以下事项;不得继承其他任务的资料、登录状态或长期授权。

  1. 已核实的产品资料:公开名称、规范网址、可用文案、图片、类别和联系方式别名。
  2. 可执行范围:站点清单、允许的入口类型、是否允许登录、无费用营销订阅、官方 Contact 邮件,以及授权有效期。
  3. 自动化边界:选用 CDP(浏览器调试协议直连)还是 CU(Computer Use,桌面操控);确认可用浏览器、已授权账号和必要权限。
  4. 记录与证据:读取已有记录,确认本批次的授权引用和保存位置。

只有当前批次明确授权时,才可登录、注册、勾选无费用营销订阅或发送官方 Contact 邮件。付费、自动续费、捐赠、强制互链、账号归属异常、强反自动化绕过、群发和自动跟进始终需要单独授权。

读取资源

执行前阅读以下文件:

没有记录时,从模板复制一份。读取文件不等于执行:每站最终动作前和结果判断后,都必须通过检查单并记录 checklist PASS/FAIL。

建队列与基础边界

  1. 规范化站点域名和投递路由,删除记录中的跟踪参数;必须保留的路由参数放入受控证据。
  2. 以“平台域名 + 产品标识 + 账号别名 + 路由”生成幂等键。已有 submitted、awaiting approval、published 或结果不明的同一幂等键不得重新执行。
  3. 先做可达性、相关性、真实性、免费路径和条款预检。付费链接、强制互链、无关分类、不可达或禁止自动化的路由直接分流。
  4. 可选互链字段保持为空;不得因为一个付费或合作入口就停止,应回到首页继续寻找正常的免费入口。
  5. 记录状态必须使用正式状态模型:already_listed 映射为 duplicate — no action;captcha_wait 映射为 blocked — manual verification。

不得虚构产品、公司、价格、地址、联系人、资质、数据、奖项、合作或法律事实。未知的可选字段留空;未知的必填字段应阻塞该站。

发现入口和内容面分类

每个站从规范首页开始,通过导航、页脚、登录后区域、站内搜索和真实链接/按钮发现当前入口。保存的深链只能作线索,不能直接当成有效投递路由。

优先识别可公开展示规范网址的非内容编辑器入口,例如商家通道、资料页、目录收录、项目展示、免费广告、新闻稿、账号资料链接位,以及当前批次已授权的官方 Contact 邮件入口。

短贴、长文和无法可靠分类的内容编辑器一律不执行:分别记录 short note — no action、long post — no action 或 unknown — no action,不得填写内容、预填、保存草稿、交人工、提交或发布。界面写着 Post 不构成例外。只有内容编辑器的站点记为 ineligible。

只有常规手段找不到任何可验证入口时,才进行视觉兜底:按页面首、中、尾逐段查找,并记录每段结论。视觉发现后仍须核验真实控件、链接或最终路由;视觉判断不能替代路由、免费性、身份和条款预检。

站内去重是硬门槛

在填写任何字段前,用站点真实的搜索控件完成固定查询集:

  1. 规范网址,包括带和不带尾部斜杠的变体;
  2. 裸域名;
  3. 官方品牌或产品拼写;
  4. 从标题或候选结果发现的词序、空格、连字符和大小写变体。

每次查询都要记录输入词、触发方式、结果网址、结果数量和可见候选标题。还要检查账户后台、近期列表和分类列表。每个候选必须打开或读取其实际出站网址,再与规范网址和域名归一化比对;标题相同或不同都不能单独作为结论。

命中规范网址或域名时,记录 duplicate — no action 并停止。站内去重能力不存在时,记录 Duplicate check: not available — user-authorized direct attempt;能力存在但无法完整核验时,记录 Duplicate check: inconclusive — user-authorized direct attempt。两种例外都必须有具体缺口、已完成检查、证据和当前批次的明确直接尝试授权,且只允许一次最终提交尝试。提交时出现“网址已存在”或同等回执,即判为重复并停止;不得重试。

验证、预填与人工交接

先做只读预检,识别登录、邮箱验证、验证码、上传和其他阻塞点。普通原生验证只可在当前授权范围内按有限次数尝试;不得绕过强反自动化验证。

若验证无法自动完成,先填写所有已核实且适用的字段,上传合规素材,并只在当前授权允许时选择无费用营销订阅。未知或不适用字段才可留空,且必须在记录中说明原因。保留原标签页、当前网址、目标标识和待办动作,绝不留下空表单或关闭交接页。

完成验证后,先重新读取页面和短时效令牌状态,再继续已授权的下一步。不得通过修改浏览器管理客户端、账号设置或指纹配置来解决页面问题;这类改动需要单独的当前授权。

自动化、重试与标签页纪律

CDP 报错、超时、空响应或找不到元素不等于可以重跑。每次受控重试前都要留下:

  1. 证据:精确错误、失败命令、当前目标、网址和页面状态;
  2. 假设:至少两个可区分的原因;
  3. 判别:能区分这些原因的最小只读检查。

只有产生新证据、且下一次操作与上次实质不同,才允许一次受控重试。相同脚本、目标、参数和等待条件不得重复执行。最终 Submit、Publish 和 Gmail Send 零次重试。没有新假设、受控重试失败,或可能已经发生最终动作时,停止该站该动作并按事实记录。

若当前授权允许,可对 CDP 无法得出明确结论的站点使用一次 CU 复核;CU 不能绕开一次最终动作、去重或验证码规则。打开新批次前关闭无关旧标签页,但必须保留人工交接页和结果不明页。

表单、官方 Contact 邮件与最终动作

表单填写后要回读受控字段值,确认名称、描述、网址和必填项没有因页面刷新而丢失。上传完成前不得继续下一步。第一个明确页面错误立即停止该站,不做脚本盲重试。

官方 Contact 邮件仅在当前批次明确授权、已核验 Gmail 发件别名、且收件人来自目标站官方 Contact/投稿/资源推荐/合作页面时可用。发送前在 Gmail Sent、Drafts、All Mail 和现有记录中按品牌、规范网址、目标域名和联系路由去重。每个目标域名和官方联系路由最多发送一封初始邮件;不得 CC/BCC、群发、重发、自动跟进或伪造身份。邮件只可请求对方自愿考虑收录规范网址,不得索要 dofollow、排名承诺、互链或内容发布。

最终 Submit、Publish 或 Gmail Send 只点击一次。提交前启动结果捕获:立即采样网址、页面状态和原生文本,并在可用时读取网络响应。确认成功需要三类互相一致的信号:状态或路由变化、与当前动作相关的原生正向回执、以及后台/邮箱/公开页等独立确认。点击、跳转、清空表单、草稿或泛化感谢页都不算成功。

最终动作后没有明确回执时,进行两到三轮只读核验。表单可查当前页、后台、邮箱和公开页;邮件只查撰写页或线程、Sent/All Mail、Drafts/Outbox。仍无回执时记录结果不明,保留页面供人工核验,绝不重投或重发。

记录、审计与交付

公开记录只能保存别名和受控证据标识,不得保存密码、一次性验证码、Cookie、会话标识、原始邮箱、电话号码、令牌化网址或其他敏感数据。记录必须以 shareable 范围通过审计。

在技能根目录运行:

bash
python3 scripts/audit_submission_record.py path/to/batch-record.md
python3 scripts/audit_submission_record.py path/to/batch-record.md --json

交付时逐站说明入口类型、去重证据、最终状态、阻塞原因、保留页面和下一步。目录已提交、待审、已发布、邮件已发送和邮件结果不明必须分别统计;邮件发送不代表送达、回复、收录、外链或发布。

资源

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Submit Producti Directories Merged AI skill do?

外链自动提交合并版:在当前授权范围内处理目录投递和一对一官方 Contact 邮件申请,包含去重、验证、结果取证与可恢复审计。

Why use Submit Producti Directories Merged on TypingMind?

Because you install it once and use it with any model. Submit Producti Directories Merged is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Submit Producti Directories Merged in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/flaqai/backlink_skills/tree/main/submit-producti-directories-merged. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Submit Producti Directories Merged?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Submit Producti Directories Merged?

As many as you like. As long as a model supports skills, you can use Submit Producti Directories Merged with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Submit Producti Directories Merged AI skill free?

Yes. It is published on GitHub by flaqai under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇