backlink-source-prep SKILL.md skillA
backlink-source-prep from flaqai/backlink_skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add flaqai/backlink_skills/backlink-source-prep@git:20260923.c025b7dPins git:20260923.c025b7d in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- flaqai/backlink_skills
- Path
双线外链挖掘矩阵/skills/backlink-source-prep/SKILL.md- Versions recorded
- 2
- Latest version
- git:20260923.c025b7d, committed Sep 23, 2026
- First version recorded
- Sep 23, 2026
- Size
- 2,445 bytes
- Repository stars
- 791
- License
- MIT
Prepare traceable backlink source data from Semrush organic competitors, Backlink Gap, referring-domain exports, local workbooks, and public lists. Use for source acquisition, inventory, normalization, consolidation, exclusion, and priority compression; stop before final site screening or submission.
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
# 外链源表整理 把分散的竞品和外链导出整理成可追溯、可压缩、可继续筛选的标准源表。原始文件永不覆盖；所有派生文件另存。 ## 三种模式 - **文件导入**：用户已提供 CSV/XLSX，只做登记、读取和整理。 - **浏览器导出**：只有得到明确授权才操作 Semrush；不使用爬虫替代产品导出。 - **离线整理**：读取已有导出，生成合并候选、排除表、优先候选和统计报告。 需要浏览器导出时，先读 [references/semrush-export.md](references/semrush-export.md)。处理字段和压缩规则时，读 [references/source-schema.md](references/source-schema.md)。 ## 工作流程 1. 为每个源文件登记目标域名、报告类型、数据库、报告日期、导出日期和文件名。 2. 从自然搜索竞品中综合相关度、共同关键词、自然流量和主题适配选择参考竞品。指标决定优先顺序，不设单一严格淘汰线。 3. 按工具允许的比较数量分批导出反向链接差异或引荐域名；记录批次号和竞品槽位。 4. 运行 `scripts/audit_semrush_exports.py` 检查文件数、行数、空表、表头差异和读取错误。 5. 标准化目标域名、来源竞品和引荐域名；保留原始值与来源文件。 6. 先排除自有域、竞品自身域、明显短链、赌博、恶意、镜像和没有研究价值的噪声，再生成优先候选。 7. 输出总量、唯一域名数、目标覆盖数和各排除原因，不能只给压缩后的数字。 ## 优先候选 优先级可以参考目标覆盖数、竞品覆盖数、链接实力、自然流量和主题信号，但不得把单个第三方分数当作最终质量结论。高权重通用站不自动成为可投递平台；低权重垂直目录也不自动淘汰。 ## 交接 至少交付：原始文件登记、合并候选、排除表、优先候选、统计报告。文件名后缀应带数据量，例如 `合并去重候选-<行数>条.csv`。此阶段不得把结果写成“已找到外链平台”或“已核验可投递”。
Read the whole file at its exact version.
How to install
mdr add flaqai/backlink_skills/backlink-source-prep@sha256:b68a69d9e39afe8eThe line at the top of this page pins the label git:20260923.c025b7d, 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.
[](https://markdownregistry.com/a/art_ckisx26ci3xhvohj)
1 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 2 versions of this file, all committed on Sep 23, 2026.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260923.c025b7d latest | 2026-09-23 | c025b7d | 2,445 B | A | view · diff |
| git:20260923.7837170 | 2026-09-23 | 7837170 | 2,443 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (2445 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
flaqai/backlink_skills · 791 stars · license MIT · pushed 2026-10-20 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_ckisx26ci3xhvohj GET https://markdownregistry.com/api/v1/resolve?ref=flaqai/backlink_skills/backlink-source-prep GET https://markdownregistry.com/api/v1/blob/b68a69d9e39afe8ead5de264beee3e8d0b7baa834e82b874a26ca44ee2cbf7e5
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.