blog-creator
Create an SEO blog post from a keyword, a topic idea, content requirements, or an existing outline.
Full write flow
- Interpret a keyword that matches what users want to write (subagent) — Ref:
references/keyword.md. Result is saved into{PROJECT_ROOT}/blogs/<topic>/keyword.md'. This file is required input for all later steps — do not skip. - Find information gain (subagent) — Run /content-researcher with step 1 output so it skips its own search. Result is saved into
{PROJECT_ROOT}/blogs/<topic>/knowledge-base.md,{PROJECT_ROOT}/blogs/<topic>/under-discussed.md.- If user clearly states what to write, continue creating the outline.
- Otherwise, suggest users to find an under-discussed angle from
{PROJECT_ROOT}/blogs/<topic>/under-discussed.md. Stop here and wait for response.
- Select conversion hooks (subagent) — Ref:
references/conversion.md. Result:{PROJECT_ROOT}/blogs/<topic>/conversion-hooks.md. - Create outline (subagent) — Pass step 1 output and
conversion-hooks.mdto the subagent. Ref:references/outline.md. Result:{PROJECT_ROOT}/blogs/<topic>/outline.md. Stop. Present outline and wait for feedback. - Write blog (subagent) — Ref:
references/write.md. After writing, run the audit-polish loop fromreferences/audit-blog.md. Returns:{PROJECT_ROOT}/blogs/<topic>/blog.md - Create illustration images (subagent) — Ref:
references/image.md
For steps labelled with (subagent), run them as subagents.
Router
Interpret the user's intent, flexibly route to different steps. We don't have to write from scratch every time.
- Full write/rewrite for a new subject -> step 1
- Only need keyword/SERP research for a blog topic -> step 1 only (
references/keyword.md) - Collect more information / draft is thin -> step 2
- Create or revise an outline -> step 4 (
references/outline.md) - Write a blog post from an outline -> step 5
- Polish an existing blog without changing the outline -> step 5
- Audit an outline for quality/completeness ->
references/audit-outline.md - Audit a blog draft for quality/completeness ->
references/audit-blog.md - Humanize a blog article (remove AI voice, make it sound natural) ->
references/humanizer.md - Generate illustration images for a finished blog -> step 6 (
references/image.md) - Add or review conversion hooks ->
references/conversion.md
This is not an exhaustive list. Decide which step to go based on the actual intent.
Intermediate research files
{PROJECT_ROOT}/blogs/<topic>/
keyword.md— competitive SERP gap analysisknowledge-base.md— knowledge baseunder-discussed.md— questions competitors don't answer wellconversion-hooks.md— selected product mentions and where they fitoutline.md— content outlineblog.md— final blog post
Ensure all files exist at the end of research.
More from rankearly/rankearly-skills
blog-title-generator
Generate SEO blog titles, title tags, and H1 variations for an SEO blog. Use when the user wants blog title ideas, headline options, title tag suggestions, H1 variants, or SEO/CTR title optimization for a planned or drafted blog post.
12blog-image
Generate a Nanobanana Pro prompt for blog images - either a scroll-stopping cover or an explanatory in-post illustration. Use when the user asks for a "blog cover", "blog image", "post thumbnail", "illustration for my blog", "header image", or wants to create a visual for a blog post or article section.
11seo-memory
Maintain a project knowledge file for SEO content creation. Use when the user shares critical context about their project — product renames, new/removed features, service changes, subproduct launches, pricing updates, audience shifts, or any factual change that SEO content should reflect. Also triggers on "update seo memory", "remember this for content", "initialize seo memory from domain", or when the user corrects a factual detail about their product/service. Even small updates matter — stale project facts in published content erode trust.
10topic-research
Expand topics into keywords or cluster a keyword library into topics and keyword clusters using RankEarly. Use when the user asks for keyword expansion, topic clustering, content clusters, topic maps, keyword research, or content planning tied to a keyword library.
10serp-gap-analysis
Analyze a live Google SERP for keyword winnability and competitor gaps. Use when the user asks for SERP analysis, real-result keyword difficulty, SEO competitor analysis, content gap analysis, or a brief or content plan for a specific keyword or query.
10content-researcher
Collect what high-ranking content covers about a topic, surface under-discussed subjects, and discover information gains (unique takes). Use when the user wants to research before writing — "research X for me", "find information gains for X", "find content gaps about X", "what are competitors missing about X", or any request to analyze what's already ranking.
7