content-plan
Skill0 starsChanged 30 days agoMITView on GitHub
Plan the pages and articles a site needs to be found: who searches, for what, which page answers each question, and in what order to write them. Covers search intent, topic clusters, internal linking, refreshing old pages and thin content. Use when the user asks for a "content plan", "content strategy", "keywords", "what should we write", "blog ideas", or a findable content.thin or links.orphan finding.
9 other projects use a version of this.
Adopted by
Most recently taken up by
- RightBlogger/bloggingskillstheir own version, first seen Nov 1, 2026
- fliqrlabs/instagram-creator-skillstheir own version, first seen Nov 1, 2026
- codebywater/WB-OZON-AI-TEAMtheir own version, first seen Oct 25, 2026
- cuevaio/skillstheir own version, first seen Oct 3, 2026
- DRAZY/claude-skillstheir own version, first seen Sep 14, 2026
- marcus-at-localhost/market-context-kittheir own version, first seen Aug 21, 2026
Other versions9 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 9
- fliqrlabs/instagram-creator-skills★ 5same name
- RightBlogger/bloggingskills★ 4same name
- codebywater/WB-OZON-AI-TEAM★ 2same name
- cuevaio/skills★ 2same name
- donatassimkus/claude-ai-skills★ 1same name
- DRAZY/claude-skills★ 1same name
- lumizone/social-content-os-claude-skill★ 0same name
- marcus-at-localhost/market-context-kit★ 0same name
- phoenixvn/claude-code-agency★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
The file
We split this skill into the rules it gives an agent
4 rules. 0 are common, 3 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 7 edited versions we read keep these.
3
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 12
Ask the owner for the audiences and what each one is trying to do.
- Very specific: line 14
Search Console queries the site already shows for (the measure skill).
- Distinctive: line 19
Do not invent search volumes.
- Distinctive: line 40
Write first what is closest to revenue and where the site has the best chance: service and location pages, then the guides that support …
“Common” is measured: kept by at least 6 in 10 of the 7 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Content plan
1. Who searches, for what
Ask the owner for the audiences and what each one is trying to do. For each audience list the questions they type, in their words and their languages. Sources, best first:
- Search Console queries the site already shows for (the
measureskill). - The questions sales and support answer every week.
- Google's "People also ask" and autocomplete, and the questions people ask AI assistants.
- Competitors' pages that rank.
Do not invent search volumes. Without data, rank by how close a query is to a sale.
2. One page per intent
Group the questions by intent and give each group one page:
| Intent | Page |
| "who does X in Y" | a service or location page |
| "how much / how long / what do I need" | a guide with the answer first |
| "X vs Y" | a comparison with a table |
| a specific job, product, event | its own page with its structured data |
Two pages for one intent compete with each other: merge them, redirect the weaker one.
3. Clusters and links
A hub page per topic links to every page in the cluster, and each links back and to its neighbours. findable's links.orphan lists pages nothing links to.
4. Order
Write first what is closest to revenue and where the site has the best chance: service and location pages, then the guides that support them, then news. Refresh pages that lost clicks before writing new ones.
5. Each page
The answer first, then the detail. Facts with sources. Who wrote it. A clear next step (the cro skill). A title and description that say what the page offers (findable checks them). No AI-generated filler: Google's scaled content abuse policy targets pages made to rank rather than to help.
Hand the plan to the owner as a table: page, audience, question, intent, priority, status.
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.