Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add sherotree/seo-agent-skills --skill competitor-backlink-gap-extractorgit clone --depth 1 https://github.com/sherotree/seo-agent-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/sherotree/seo-agent-skills/competitor-backlink-gap-extractor)<a href="https://agentmods.dev/skills/sherotree/seo-agent-skills/competitor-backlink-gap-extractor"><img src="https://agentmods.dev/badge/skills/sherotree/seo-agent-skills/competitor-backlink-gap-extractor/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/sherotree/seo-agent-skills/competitor-backlink-gap-extractor"><img src="https://agentmods.dev/badge/skills/sherotree/seo-agent-skills/competitor-backlink-gap-extractor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00098 | $0.01205 |
| Opus 5 | $0.00049 | $0.00602 |
| Sonnet 5 | $0.00020 | $0.00241 |
| Haiku 4.5 | $0.00010 | $0.00120 |
Grade A, and why
competitor-backlink-gap-extractor scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Competitor Backlink Gap Extractor
独立 skill：只负责从竞品域名/页面提取高质量外链，并可选做 Intersection / Gap。不依赖、不调用其他 SEO/GEO skill。
Prerequisites
Prefer .env.local in the project (or git root). Shell export still works and wins.
# .env.local
DATAFORSEO_LOGIN=your_login
DATAFORSEO_PASSWORD=your_password
Do not commit it. Confirm the consuming repo gitignores .env / .env.*. Do not store credentials in the skill directory or paste the file into chat.
Lookup order: existing env → .env.local then .env (cwd up to git root, then the skill dir) → ~/.env.local / ~/.env / ~/.dataforseo.env. Only DATAFORSEO_* keys are read. No extra packages.
Quick Start
python3 scripts/extract_backlink_gap.py "https://www.uwarp.design/"
python3 scripts/extract_backlink_gap.py https://www.uwarp.design/ --limit 300
python3 scripts/extract_backlink_gap.py https://www.uwarp.design/ --own uwarp.design
Inputs
| 参数 | 类型 | 必填 | 默认 | 说明 |
|---|---|---|---|---|
target |
String… | 是 | — | 一个或多个竞品域名或页面 URL |
own |
String | 否 | — | 己方域名；提供后计算 Gap（竞品有、己方无） |
limit |
Integer | 否 | 300 |
每个 target 最多返回条数（API max 1000） |
min_rank |
Integer | 否 | 30 |
源站 domain_from_rank 下限（0–100 标尺） |
min_etv |
Integer | 否 | 300 |
源站月自然流量下限（美国 location_code: 2840） |
mode |
String | 否 | one_per_domain |
one_per_domain 适合 Outreach；as_is 返回全部链接 |
允许 nofollow；排除 UGC（API attributes has_not ugc，本地再丢一次）。rel="sponsored" 不在排除范围内。
Mandatory filters
PRD 意图必须满足。Backlinks API 没有 domain_stat.* 字段，映射如下：
| PRD | 实际请求 |
|---|---|
is_lost = false |
["is_lost", "=", false] + backlinks_status_type: "live" |
is_broken = false |
["is_broken", "=", false] |
| nofollow allowed | 不设 dofollow 过滤 |
| 不要 UGC | ["attributes", "has_not", "ugc"] + 本地 attributes 含 ugc 则丢弃 |
domain_stat.ranks.dataforseo > 30 |
["domain_from_rank", ">", 30] + rank_scale: "one_hundred" |
domain_stat.organic.etv > 300（美国） |
二次请求 Labs bulk_traffic_estimation/live（location_code: 2840），本地过滤 |
orderBy etv desc |
API 用 order_by: ["domain_from_rank,desc"]，拿到 etv 后再按流量降序 |
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 10d ago First seen · 98 lines · 98 tokens per session scan A 38fe939c9848
competitor-backlink-gap-extractor is a skill published in the GitHub repository sherotree/seo-agent-skills (2 stars, last pushed 23d ago), licensed MIT. It adds 98 tokens to every session and 1,205 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
gingiris-seo-geo-agent
SEO/GEO Agent Operations SOP v2 — Rebuilt from real-world operations (analook.com 0→launch, GSC incident, DataForSEO monitoring, gingiris.tools post-migration recovery). What's new in v2: • Step-by-step onboarding (Q1→Q6), multiple choice wherever possible — no big forms • Mandatory daily SEO log — first item is…
seo-audit
Use when the user wants to audit, crawl, or diagnose SEO issues on their website. Triggers on: 'audit my site', 'crawl', 'SEO issues', 'broken links', 'missing meta', 'thin content', 'site health', 'technical SEO'.
seo-keywords
Use when the user wants keyword research, keyword suggestions, rank tracking, or position monitoring. Triggers on: 'keyword research', 'keyword ideas', 'track rankings', 'rank tracking', 'position tracking', 'SERP', 'search volume', 'keyword difficulty'.
seo-strategy
Use when the user wants an SEO strategy, action plan, or recommendations. Triggers on: 'SEO strategy', 'SEO plan', 'SEO recommendations', 'improve SEO', 'what should I fix', 'SEO roadmap', 'quick wins'.
data-charts-tako
Search and visualize the world's data - get charts, insights, and embeddable knowledge cards for finance, economics, demographics, sports, and more.
apollo-lead-finder
Two-phase Apollo.io prospecting: free People Search to discover ICP-matching leads, then selective enrichment to reveal emails/phones (credits per contact). Creates Apollo lists. Deduplicates against existing contacts by LinkedIn URL.