backlink-discovery SKILL.md skillA

backlink-discovery from kennyzir/7deer_skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add kennyzir/7deer_skills/backlink-discovery@git:20260403.858f36d

Pins git:20260403.858f36d in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
kennyzir/7deer_skills
Path
backlink-discovery/SKILL.md
Versions recorded
1
Latest version
git:20260403.858f36d, committed Apr 3, 2026
Size
4,343 bytes
Repository stars
336
License
MIT

外链机会发现引擎。用户输入目标网址,立即用 web_search 开始多轮关键词派生搜索, 目标发现 300 个相关平台后自动停止,结果存入该网址专属数据库。 不限外链方式(论坛/GitHub/Wiki/目录等),只发现不执行。 触发:用户提供网址,说"发现外链"、"找外链机会"、"发现外链机会"。.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Backlink Discovery — 外链机会发现引擎

## 核心逻辑

**每个 URL = 独立发现任务,目标 300 个平台。**

```
用户输入 https://xxx.com
  → 立即用 web_search 开始前台搜索
  → 多轮关键词派生,持续发现
  → 达到 300 个平台后停止
  → 结果存入数据库

下次输入 https://yyy.com
  → 新的独立发现任务
  → 各自数据库,互不干扰
```

## 触发方式

```
发现 https://xxx.com 的外链机会(目标300个)
```

## 执行流程(前台 web_search)

### Step 1:接收任务,提取种子关键词

解析目标 URL,实时提取种子关键词(不写死):

```
https://robloxcalc.com
  ↓
种子关键词:roblox, calculator, math, lua, game, game calculator, gaming, education, tool
```

### Step 2:多轮 web_search(前台执行)

每轮用 `web_search` 搜索 8-12 个查询,从结果提取平台域名 → 分类 → 判断相关度。

**搜索词思路要宽**,不要只搜"xxx alternatives":
- 竞品 + "free tools list"
- 竞品 + "directory submit"
- 竞品 + "community"
- 竞品 + "tutorial resources"
- 竞品 + "wiki"
- 竞品 + "github awesome list"
- 竞品 + "for kids/math/education"
- 竞品 + "game dev"
- 竞品 + "fan sites blogs"
- 竞品 + "similar games"
- 竞品 + "submit free"

每轮结束后从发现结果中派生新关键词 → 进入下一轮。

停止条件:
- 达到 300 个平台 → 停止
- 连续 2 轮无新发现 → 停止

### Step 3:结果写入数据库

每个 URL 独立数据库目录:

```
memory/backlink-discovery/{提取的域名}/
├── platforms.json      # 所有发现平台(含相关度、方式分类)
└── summary.md         # 汇总报告
```

### Step 4:返回结果

发现完成后返回:
- 总平台数 + P0/P1/P2 分布
- 外链方式分布
- Top 10 高相关平台
- 数据存放路径

用户查询时读数据库返回最新状态。

## 数据库读取

```
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add kennyzir/7deer_skills/backlink-discovery@sha256:4b6423a495f460b0

The line at the top of this page pins the label git:20260403.858f36d, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_gqgwaq7a7fpauddm.svg)](https://markdownregistry.com/a/art_gqgwaq7a7fpauddm)

4 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 1 version of this file, committed on Apr 3, 2026.

versioncommittedcommitsizeaudit
git:20260403.858f36d latest2026-04-03 858f36d 4,343 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (4343 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

kennyzir/7deer_skills · 336 stars · license MIT · pushed 2026-09-29 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_gqgwaq7a7fpauddm
GET https://markdownregistry.com/api/v1/resolve?ref=kennyzir/7deer_skills/backlink-discovery
GET https://markdownregistry.com/api/v1/blob/4b6423a495f460b0d5a55fda1fc2c28789ff123c099ceeffc0d002d609274d48

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from kennyzir/7deer_skills

auto-page-sync SKILL.md skill
kennyzir/7deer_skills · auto-page-sync/SKILL.md · 仓库 Markdown/JSON 内容自动同步到前端页面,配置 GitHub Actions 定时拉取 + 部署,保持 Google SEO 内容新鲜度。支持日报、博客、Changelog、Landing Page 等多种页面模式。
v1.0 · audit A · 336 stars
backlink-intelligence SKILL.md skill
kennyzir/7deer_skills · backlink-intelligence/SKILL.md · AI/Tools目录外链情报收集与评估。当需要为项目寻找外链机会时使用,包括: (1) 搜索免费AI工具目录、SaaS目录、创业目录 (2) 批量评估目标站点的收费/登录/审核要求 (3) 记录外链提交结果到memory文件 (4)…
git:20260404.f48d6fc · audit A · 336 stars
data-scraper-intent SKILL.md skill
kennyzir/7deer_skills · data-scraper-intent/SKILL.md · A toolkit for web data extraction and search intent analysis. Includes patterns for handling lazy-loaded content and…
git:20260116.d3a8dc0 · audit A · 336 stars
favicon-icon-generator SKILL.md skill
kennyzir/7deer_skills · favicon-icon-generator/SKILL.md · Generate and validate favicon and application icon systems for web projects. Use when creating SVG icons, web…
git:20260907.9e3cb28 · audit A · 336 stars
gemini-thinking-protocol SKILL.md skill
kennyzir/7deer_skills · gemini-thinking-protocol/SKILL.md · 核心认知引擎 - 强制执行 First Principles, Dialectics, Systems Thinking 与 Communication Protocol
v1.0 · audit A · 336 stars
google-trends-to-pages SKILL.md skill
kennyzir/7deer_skills · google-trends-to-pages/SKILL.md · 将 Google Trends 关键词分类为搜索意图并生成 SEO 页面结构建议。适用于根据搜索量和增长率确定内容优先级、标题层级、内链与 Schema 类型。
git:20260907.12dc2ff · audit A · 336 stars
html5-game-radar SKILL.md skill
kennyzir/7deer_skills · html5-game-radar/SKILL.md · HTML5 游戏发现雷达 - 多源监测又新又热的 HTML5 游戏,识别 SEO 套利窗口。 触发条件: - 用户说「跑 HTML5 雷达」、「启动 HTML5 监控」、「HTML5 游戏扫描」 - 每天 cron 自动触发(建议…
git:20260907.7c1814f · audit A · 336 stars
itchio-new-game-hunt SKILL.md skill
kennyzir/7deer_skills · itchio-new-game-hunt/SKILL.md · Hunt for fresh browser-playable games on itch.io /newest that are worth building SEO arbitrage sites for. Crawls new…
git:20260907.0dc8461 · audit A · 336 stars
keyword-competition-analysis SKILL.md skill
kennyzir/7deer_skills · keyword-competition-analysis/SKILL.md · 谷歌关键词竞争度分析。当用户要求分析某个关键词的搜索竞争度、SEO难度、关键词排名机会、市场调研,或要求"分析下XXX关键词"时触发。使用浏览器抓取Google搜索结果页作为主要数据源,输出结构化竞争度报告。
git:20260403.a8603e0 · audit A · 336 stars
multi-game-codes-hub SKILL.md skill
kennyzir/7deer_skills · multi-game-codes-hub/SKILL.md · Generate a Next.js Roblox codes page from validated JSON using a reusable TSX template. Use when creating or…
git:20260907.251ccd0 · audit A · 336 stars
nextjs-seo-booster SKILL.md skill
kennyzir/7deer_skills · nextjs-seo-booster/SKILL.md · A complete SEO toolkit for Next.js applications, including structured data (Schema.org), dynamic sitemap generation…
v1.1 · audit A · 336 stars
nextjs-seo-foundations SKILL.md skill
kennyzir/7deer_skills · nextjs-seo-foundations/SKILL.md · Next.js 14 应用的生产级 SEO 工程化规范 (Metadata, Schema, Performance)
v1.0 · audit A · 336 stars

Every file in kennyzir/7deer_skills

Browse by kind, by grade A, or by owner.