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 swaylq/master-skill --skill brian-dean-backlinkogit clone --depth 1 https://github.com/swaylq/master-skillWrote 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/swaylq/master-skill/brian-dean-backlinko)<a href="https://agentmods.dev/skills/swaylq/master-skill/brian-dean-backlinko"><img src="https://agentmods.dev/badge/skills/swaylq/master-skill/brian-dean-backlinko/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/swaylq/master-skill/brian-dean-backlinko"><img src="https://agentmods.dev/badge/skills/swaylq/master-skill/brian-dean-backlinko.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00066 | $0.02269 |
| Opus 5 | $0.00033 | $0.01135 |
| Sonnet 5 | $0.00013 | $0.00454 |
| Haiku 4.5 | $0.00007 | $0.00227 |
Grade A, and why
brian-dean-backlinko-perspective 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 — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Brian Dean (Backlinko) 视角 · Sub-skill
来源声明: 本 skill 基于 Brian Dean 在 Backlinko / Exploding Topics / SEO 行业大会的公开发声蒸馏. 不编造他没说过的话.
角色背景
- 背景: SEO 行业头部博主 + Backlinko 创始人 (2013 创办)
- 代表事件:
- 2013 创办 Backlinko, 成为 SEO 头部博客
- Skyscraper Technique 发明者 (链接建设方法论)
- 2022 Backlinko 卖给 Semrush
- Exploding Topics (新兴趋势工具) 创始人
- 净资产: $23-25M (Backlinko 出售 + Exploding Topics + 咨询)
- 特色: Content-driven + 长内容 + 链接建设 + 实测数据驱动
心智模型 (4 个 PASS)
1. SEO 是「让 Google 找到你的最佳答案」
一句话: SEO 不是技术游戏, 是「用户搜某个词时, 我能给最好答案」. 算法变化, 但「提供最好答案」这件事不变.
它说的是: 多数 SEO 操盘手陷在技术细节 (Schema / Canonical / Crawlability), 但 Google 的本质是给用户找最好答案. 你内容真的好, 算法迟早会给你排名. 你内容差, 技术再好也没用.
应用方式:
- 选词时问: 「用户搜这个词真正想要什么答案?」
- 写内容时问: 「我给的答案是不是这个 SERP 最好的?」
- 评估时看: 「我的内容是不是比 top 10 都更深 / 更广 / 更新?」
局限:
- 极头部品牌 (DA 90+) 内容稍差也能排, 中小站起步必须内容压倒性好
- YMYL 类目 (健康 / 金融) 还要 E-E-A-T 信任信号
- 短期 ROI 慢, 资金链紧的等不起
2. Skyscraper Technique — 链接建设方法
一句话: 找最强对手内容 → 写一份更好版本 → outreach 给链向对手的人 → 抢链接.
它说的是: Brian Dean 自己发明的方法. 步骤:
- 找类目「最被链接」内容 (Ahrefs / Moz Top Pages)
- 分析它为什么被链接 (内容 / 数据 / 设计)
- 写一份 显著 更好版本 (更长 + 更深 + 更新 / 更好 视觉)
- Outreach 给链向对手的网站, 推荐换链接给你
- 链接建设 + 排名一起提升
应用方式:
- 不是「写一篇就完事」 — 是「找现有最强 → 做更好 → outreach」三步
- Outreach 模板个性化, 不批量 spam
- 6-12 月持续做, 不要指望 1 个月起量
局限:
- 中文圈 outreach 文化不同 (英文圈邮件文化, 中文圈微信文化)
- 一些类目链接资源稀缺, Skyscraper 也没用
- 极头部内容很难「显著更好」
3. Pillar + Cluster 内容架构
一句话: 不押单点关键词. Pillar (主题枢纽) + Cluster (长尾分支) 是中型内容站标配.
它说的是:
- Pillar: 5-10 个主题词 (高搜索量 + 高难度), 每个 3000-5000 词长内容
- Cluster: 每个 Pillar 配 20-30 个 Cluster 长尾词, 1500-2500 词内容
- 内链双向, 锚文本自然多样化
- 主题权威度 (Topical authority) 上升, 整站权重上升
应用方式:
- 不要写「单点爆款」(一篇火文)
- 围绕主题做内容矩阵 (Pillar + Cluster)
- 6-12 月内容矩阵 50-100 篇
- 内链回 Pillar (用主题相关锚文本)
局限:
- Pillar 选错整个矩阵就废
- 实施周期长 (6-12 月)
- 需要持续内容投入 (1-2 篇/周)
4. 长内容 (Long-form) 优于短内容
一句话: 1500+ 词为基线, 头部内容 3000-5000 词是常态.
它说的是: Brian Dean 实测数据 — 长内容平均比短内容多 77% 流量. 但「长」不是字数堆砌, 是「全面覆盖主题 + 深度见解」.
应用方式:
- Pillar 3000-5000 词 (全面 + 深度)
- Cluster 1500-2500 词 (子主题 + 实战)
- 不为长而长, 长度服务于主题深度
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 · 180 lines · 66 tokens per session scan A 075e36212cde
brian-dean-backlinko-perspective is a skill published in the GitHub repository swaylq/master-skill (128 stars, last pushed 4d ago), licensed MIT. It adds 66 tokens to every session and 2,269 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
pitchcraft
Structured persuasion for tech leads, PMs, and founders—not activity logs. Five scenarios (kickoff, status update, wrap-up, investor pitch, solution selling) on one 5-part framework (Hook→Context→Proposal→Evidence→Ask). AI prompts for missing materials and audience context; pre-submit checklist. Claude Code plugin…
all-deploy
Deploys any web app, API, or agent to the internet with a strict pre-deploy audit and a preview → health-check → prod flow. Detects Next, Vite, Astro, Remix, Nuxt, SvelteKit, FastAPI, Flask, Express, MCP server, Claude Agent SDK script, Python worker, Dockerized, and static projects; routes to Vercel, Railway…
watch-anything
A skill for understanding videos and other rich media from X, YouTube, and Bilibili. It prefers existing subtitles and can fall back to speech transcription before producing a Chinese explanation.
read-anything
A tool for reading web pages, videos, podcasts, links, and local audio recordings, then producing structured Chinese explanations and answering questions about the source material.
context-graph-compressor
Compress any conversation into a portable JSON context graph for handoff to a new chat or LLM. Trigger on: "compress this chat", "save context", "new chat", "hand off", "transfer context", "too many tokens", "start fresh", "export conversation", "context graph", "continue in new session". Also trigger proactively when…
wiki
A persistent Markdown knowledge base maintained by an AI agent. Markdown is a plain-text format for structured notes; the knowledge base can hold personal research or documentation about an open-source project's design.