# law-ahrefs-content-engineering-claude-code-2026-04-28

## Veille

Post from the **Ahrefs blog** published on **April 28, 2026** by **Ryan Law** (Director of Content Marketing, Ahrefs) describing an in-house **content engineering** system built around **Claude Code**: an editorial pipeline that produces **publish-ready drafts in 6 to 12 minutes**. **Pivot thesis**: ***« AI content is not, by default, good. This process works well because it mirrors our existing human editorial process »*** — quality doesn't come from the model but from the **faithful reproduction of a human editorial process** proven over decades. Architecture: **~23 skill files**, each corresponding to an editorial step (keyword research, topic gap analysis, structural outlining, research compilation, draft generation, formatting), **orchestrated by a master skill `blog-pipeline`** that chains them to produce a complete article. **Seven design principles**: (1) **mimic human workflows** by chaining skills adapted from existing Ahrefs editorial documentation; (2) **output each step separately** for troubleshooting (*« if you get an article at the end of a ten minute run, and it's bad, it's hard to diagnose precisely where and why the process went wrong »* → save intermediate outputs); (3) **create test cases** via Anthropic's `skill-creator` skill to evaluate and improve guidance; (4) **plug in quality data sources** — the **Ahrefs MCP** (keyword metrics, parent topic, long-tail themes, SERP overviews, competitive analysis), competitive analysis and product docs; (5) **front-load human direction** via context parameters enabling editorial guidance; (6) **build interactive previews** in HTML format for review before publication; (7) **allow customization** (each team member can fork and modify the system). **Volume**: ~**15 articles published** and ~**30 articles updated** via this workflow; development started in **February 2026** (the prior process from **August 2025** took several days and manual intervention). **Explicit caveats** (anti-oversell): *« experience matters »* — the process reflects decades of editorial expertise; topic selection focuses on **informational SEO content** the author knows well; Ahrefs **has no plan to "scale" content massively** but maintains an **evergreen library**. Philosophy: automate *« the formulaic parts of work »* to eliminate drudgery and free up time for research, thought leadership, webinars, and system optimization — **not** replace human effort. Canonical reference cited by Pasquale Pillitteri (*Opus 4.8 SEO workflow*) as field proof of the « 6-12 min/draft » gain. Direct convergence with the **skills-over-prompts** doctrine (Lattice, PROJ-AI), **systems around the model** (Dropbox/Okumura), and the use of **HTML as a review artifact** (Shihipar).

## Titre Article

How I Do Content Engineering With Claude Code

## Date

2026-04-28

## URL

https://ahrefs.com/blog/how-i-do-content-engineering-with-claude-code/

## Keywords

content engineering, content engineering, Claude Code, skill files, blog-pipeline, skill orchestration, keyword research, topic gap analysis, structural outlining, research compilation, draft generation, formatting, ready-to-publish draft in 6-12 minutes, 23 skill files, Ahrefs MCP, Model Context Protocol, parent topic, long-tail, SERP overview, competitive analysis, skill-creator, test cases, saving intermediate outputs, pipeline troubleshooting, front-loading human direction, HTML preview, fork and customization, AI content is not by default good, mirror existing human editorial process, formulaic parts of work, evergreen library, no massive scale, informational SEO, content marketing, editorial workflow, editorial automation, Ryan Law, Ahrefs, systems around the model, skills over prompts

## Authors

**Ryan Law** — Director of Content Marketing chez **Ahrefs**. Praticien senior du content marketing SEO ; le billet est un retour d'expérience personnel (*« How I do… »*) publié sur le **blog Ahrefs** (ahrefs.com/blog) le **28 avril 2026**.

## Ton

**Profile**: Practitioner post (*how-I-do* / experience report), first-person singular (*« I »*), aimed at content marketers, SEO managers, and editors curious about industrializing their production with AI. **Pragmatic-pedagogical** register, **medium** technical level (assumes familiarity with SEO, MCP, Claude Code, skills, but explains each step).

**Style**: Demonstration prose structured by numbered principles and workflow steps. **Editor-engineer** logic: a counter-intuitive thesis is stated (AI does not produce good content by default), illustrated with a concrete architecture (23 skills + `blog-pipeline`), quantified with a result (6-12 min/draft, 15 published / 30 updated), then expectations of scale are explicitly defused (caveats). Strong honesty: repeated insistence that the system **reproduces** human expertise rather than replacing it.

**Key aphorisms**:
- ***« AI content is not, by default, good. This process works well because it mirrors our existing human editorial process. »*** (central thesis).
- ***« If you get an article at the end of a ten minute run, and it's bad, it's hard to diagnose precisely where and why the process went wrong. »*** (justification for save-intermediate-outputs).
- *« Experience matters. »* (anti-oversell caveat).

**Worked metaphors / frames**:
- ***Content engineering*** — editorial content treated as a manufacturing chain broken into tooled, testable steps, rather than a monolithic creative act.
- ***Mirror the human editorial process*** — the AI pipeline as a mirror of an existing human workflow: quality is carried by the process, not the model.
- ***Save every step*** — pipeline observability (intermediate outputs) as a condition for debugging, by analogy with software system logs.

**Epistemic position**: an operator's experience report (Ahrefs, a reference SEO publisher) backed by modest, verifiable numbers (15 + 30 articles), with **explicit caveats** that reinforce credibility (no promise of massive scale, acknowledgment that human experience remains the foundation). Promotional source (Ahrefs sells the MCP used) but a cautious, reproducible framing.

**Authority**: (a) Ahrefs **brand** (a reference SEO tool, hence business legitimacy); (b) Ryan Law's **role** (Director of Content Marketing); (c) **honesty** about limits (experience required, no scale); (d) **reproducibility** (forkable system, documented steps) — becomes the **field reference** cited by 2026 SEO workflows (Pillitteri).

## Pense-betes

- **Date / source**: **April 28, 2026**, **Ahrefs blog** (ahrefs.com/blog). Author: **Ryan Law** (Director of Content Marketing, Ahrefs).
- **Central thesis (to remember verbatim)**: ***« AI content is not, by default, good. This process works well because it mirrors our existing human editorial process. »*** ### Pipeline architecture
- **~23 skill files**, one per editorial step: keyword research, topic gap analysis, structural outlining, research compilation, draft generation, formatting.
- Orchestration by a master skill **`blog-pipeline`** that sequences the others → complete article.
- **Ahrefs MCP** = live SEO source of truth (keyword metrics, parent topic, long-tail, SERP overview, intent, competitive analysis) instead of hallucinations. ### The 7 design principles 1. **Mimic human workflows** (skills adapted from existing Ahrefs editorial documentation). 2. **Output each step separately** → troubleshooting (save intermediate outputs). 3. **Create test cases** via Anthropic's `skill-creator`. 4. **Plug in quality sources** (Ahrefs MCP, competitors, product docs). 5. **Front-load human direction** (context parameters). 6. **Interactive HTML previews** for review before publication. 7. **Forkable / customizable** by each team member. ### Numbers & caveats
- **6 to 12 minutes** for a publish-ready draft (canonical figure quoted everywhere).
- **~15 articles published**, **~30 updated**. Development started **February 2026**; the prior process (**August 2025**) meant several days plus manual intervention.
- **Explicit caveats**: *« experience matters »*; topics = well-mastered **informational SEO**; **no massive-scale plan** → **evergreen** library.
- Philosophy: automate *« the formulaic parts of work »* (drudgery) → free up time for research / thought leadership / webinars / system optimization. ### To leverage in engagements / presentations
- **Field proof-point** for the editorial-cycle gain: 6-12 min/draft, anchored on live data (MCP), with a human safeguard.
- Direct illustration of the **skills-over-prompts** + **systems around the model** doctrine (the edge = the orchestrated pipeline, not the raw model) — overlaps with Lattice, PROJ-AI, Dropbox/Okumura.
- The **save-every-step** idea = reusable agentic-pipeline observability as a pattern (cf. decision traces / agent debugging).

## RésuméDe400mots

Ryan Law, Director of Content Marketing at Ahrefs, describes in this **April 28, 2026** blog post the **content engineering** system he built around **Claude Code** to produce publish-ready article drafts in **6 to 12 minutes**. His founding thesis defuses the hype from the outset: *« AI content is not, by default, good. This process works well because it mirrors our existing human editorial process »*. In other words, quality doesn't come from the model but from the **faithful reproduction of a human editorial process** already proven.

The system rests on **about 23 skill files**, each corresponding to a specific editorial step: keyword research, topic gap analysis, structural outlining, research compilation, draft generation, formatting. A master skill, **`blog-pipeline`**, chains them together to produce a complete article. At the core of the setup, the **Ahrefs MCP** lets Claude pull **real SEO data** (keyword metrics, parent topic, long-tail themes, SERP overviews, search intent, competitive analysis) rather than inventing figures.

Law lays out seven design principles: mimicking existing human workflows; outputting each step separately for troubleshooting (*« if you get an article at the end of a ten minute run, and it's bad, it's hard to diagnose precisely where and why the process went wrong »*); creating test cases via Anthropic's `skill-creator`; plugging in quality data sources; front-loading human direction via context parameters; building interactive HTML previews for review; and making the system forkable and customizable by each team member.

The numbers remain deliberately modest: **~15 articles published** and **~30 updated**, with development starting in **February 2026** (the prior process, from August 2025, took several days plus manual intervention). Law pairs all this with **explicit caveats** that reinforce his credibility: *« experience matters »* (the process reflects decades of expertise), topic selection is limited to well-mastered **informational SEO content**, and Ahrefs **has no plan to scale massively** — it maintains an **evergreen** library.

The overall philosophy is to automate only *« the formulaic parts of work »* — the formulaic drudgery — to free up time for research, thought leadership, webinars and system optimization, without replacing human effort. This post has become the **field reference** cited by 2026 SEO workflows (notably Pasquale Pillitteri), a concrete illustration of the *skills-over-prompts* and *systems around the model* doctrine: the advantage comes from the orchestrated pipeline, not the raw model.

## GrapheDeConnaissance

- Ryan Law —travaille_chez→ Ahrefs (ORGANISATION, 0.97)
- Ryan Law —a_créé→ content engineering (METHODOLOGIE, 0.96)
- content engineering —est_basé_sur→ Claude Code (TECHNOLOGIE, 0.96)
- content engineering —utilise→ skill files (TECHNOLOGIE, 0.95)
- blog-pipeline —utilise→ skill files (TECHNOLOGIE, 0.94)
- content engineering —permet→ draft prêt à publier (CONCEPT, 0.94)
- content engineering —utilise→ Ahrefs MCP (TECHNOLOGIE, 0.93)
- Ahrefs MCP —permet→ keyword data / parent topic / SERP overview (CONCEPT, 0.92)
- Ryan Law —affirme_que→ l'IA ne produit pas du bon contenu par défaut (AFFIRMATION, 0.95)
- qualité du contenu IA —est_basé_sur→ la reproduction du processus éditorial humain (CONCEPT, 0.93)
- sauvegarde des outputs intermédiaires —permet→ le troubleshooting du pipeline (CONCEPT, 0.9)
- skill-creator d'Anthropic —permet→ la création de cas de test pour les skills (CONCEPT, 0.88)
- Ryan Law —mesure→ ~15 articles publiés + ~30 mis à jour via le pipeline (MESURE, 0.92)
- Ahrefs —s_oppose_à→ scale massif du contenu (CONCEPT, 0.9)
- previews HTML —permet→ la revue humaine avant publication (CONCEPT, 0.88)

---
Canonical: https://www.thekb.eu/en/fiches/law-ahrefs-content-engineering-claude-code-2026-04-28/