pages-to-win
Skill0 starsChanged 29 days agoMITView on GitHub
Use for choosing what to write or improve, for example "what pages should I create", "what should we write about", "which keywords can we win", "plan my content", "build a content calendar", "turn these keywords into a plan", "where are my content gaps", or "plan three months of posts". Reads the business profile, stored keywords and the existing plan, then proposes at most 10 pages to win, each with a gap type and the metric it should move, and saves the approved ones to the plan.
In this repository10 other files it gives its agents.
- ai-readiness-checkSkill
- analytics-ga4Skill
- approve-and-measure-changeSkill
- connect-and-importSkill
- core-web-vitalsSkill
- leadsSkill
- search-consoleSkill
- site-auditSkill
- start-hereSkill
- tag-manager-trackingSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
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
- Very specific: line 31
After the user approves, gravity_add_strategies(site_id, items=[...]).
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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
Pages to win
Why: a short list of pages tied to a gap and a metric gets built and measured. A long calendar of guesses does not.
Rules that come first
- Propose at most 10 items. Each item has a gap type and the one metric it should move.
- Gap types, use exactly one per item:
missing page(nothing targets the query),weak page(a page exists but does not answer the query),not crawlable(an AI or search bot cannot read it),not citable(hard to quote: no clear answer, no facts, no source),wrong intent(the page type does not match what the searcher wants). - The metric is something AdvisorSEO or the user can measure later: organic clicks or impressions for the target query, leads from the page, or a crawler and citability check moving from fail to pass. Never an AI rank position.
- Saving items to the plan is a write. Show the preview, wait for the user's yes in a new turn, then call with
confirm=true. - Keyword volumes and difficulty are recorded values. Say where they came from and do not present them as fresh.
- Any rate you report comes with its n plus an interval, or the words "insufficient data".
Steps
- Get the site from start-here.
gravity_get_profile(site_id): what the business sells, where and to whom. Ifconfiguredis false, ask for the missing parts and save them withgravity_set_profile(preview, then confirm).gravity_list_keywords(site_id): the stored keywords. If there are none, research them from the profile, then store them withgravity_add_keywords(site_id, keywords=[...])(preview, then confirm). Each keyword takeskeywordand, when known,search_volume,difficulty,intentandpage_type.gravity_list_strategies(site_id): what is already planned. Do not propose a page that is already there.gravity_list_content(site_id): what already exists, to tell amissing pagefrom aweak page.- Optional: run ai-readiness-check or read
gravity_audit_findingswhen the gap may benot crawlableornot citable. - Propose the list as a table: page title, target query, gap type, metric to move, why this one.
- After the user approves,
gravity_add_strategies(site_id, items=[...]). Each item takestitle,target_keyword,content_type(blog_post,service_page,landing_pageorfaq_page),search_intent,priority(1 is highest),notes(put the gap type and metric here) anddays_from_now. Preview, then confirm. - Writing and publishing a page is the job of approve-and-measure-change.
Check
The lead's eval proves this skill when the reply calls gravity_list_keywords and gravity_list_strategies, proposes no more than 10 items, every item carries one of the five gap types and a named metric, no item states an AI rank position, and gravity_add_strategies is only called with confirm=true after a user approval turn.
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.

