seo-outline
Skill0 starsChanged 7 months agoMITView on GitHub
Use to turn a target keyword (or keyword cluster) into an article outline that can rank. Produces target keyword, intent, top-ranking patterns, recommended outline with H2/H3, internal-link targets, and word-count target. Hands the outline to content-agent to write.
In this repository8 other files it gives its agents.
- code-reviewSkill
- cold-email-sequenceSkill
- content-calendarSkill
- funnel-analysisSkill
- market-researchSkill
- qualify-leadSkill
- release-notesSkill
- write-linkedin-postSkill
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 20
Look at the top 5 ranking pages.
- Distinctive: line 69
Don't pad to hit a word count.
- Distinctive: line 70
Don't keyword-stuff. Use the keyword in H1, intro, and one H2.
- Distinctive: line 71
Never recommend an outline you couldn't write a credible draft of.
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
seo-outline
A ranking article does three things at once: matches the search intent, covers the topic at least as completely as the top results, and gives a reader something the top results don't.
Inputs to gather
- Target keyword (or cluster of related keywords).
- Existing pages on the site that could be linked internally.
- Domain authority — high (can target competitive head terms) vs new (target long-tail first).
- Brand voice doc — link if one exists.
Method
- Identify search intent: informational, navigational, transactional, or commercial-investigation.
- Look at the top 5 ranking pages. Note: their angle, their headers, their word count, their content format (listicle, how-to, ultimate guide, comparison).
- Find the content gap — a sub-topic, framing, or proof they all miss.
- Build an outline that covers the same ground plus the gap.
- Plan internal links to existing site pages.
Output format
## Target keyword
<keyword> | intent: <type> | competition: <low/med/high> | suggested word count: <range>
## SERP analysis
| Rank | URL | Angle | Word count | Format |
|---|---|---|---|---|
| 1 | ... | ... | ... | ... |
| 2 | ... | ... | ... | ... |
| ... |
## Gap we'll exploit
<one paragraph: what we'll cover that the top results don't>
## Outline
# <H1: working title>
## <H2: section 1>
- key sentence
- key sentence
### <H3: subsection>
- key sentence
## <H2: section 2>
- key sentence
[continue for full outline — typically 5-8 H2 sections]
## Internal links to wire in
- [<anchor text>](<url-on-our-site>) — placement: section X
- [<anchor text>](<url-on-our-site>) — placement: section Y
## CTA for the article
<single specific CTA — newsletter, demo, asset download>
## Hand-off to content-agent
"Write a <word count> <format> targeting <keyword>, following the outline above. Voice: <preset>. Lead with <hook idea>."Hard rules
- Don't pad to hit a word count. The top result is the floor, not the ceiling.
- Don't keyword-stuff. Use the keyword in H1, intro, and one H2. Variants elsewhere.
- Never recommend an outline you couldn't write a credible draft of.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

