powerczukpowerczuk/seo-machine/skills/entity-coverage/SKILL.md

entity-coverage

Skill0 starsChanged 2 months agoMITView on GitHub

Entity coverage matrix from the top-10 SERP with MUST-COVER / OPPORTUNITY / INFORMATION GAIN classes, 5–8 information-gain points, and an entity salience brief.

1 other project uses a version of this.

Adopted by

Most recently taken up by

howseen-ai/howseen-geo-skillstheir own version, first seen Sep 20, 2026

Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
howseen-ai/howseen-geo-skills★ 1same 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.
In this repository15 other files it gives its agents.
- alignment-auditSkill
- auditSkill
- citable-passageSkill
- content-briefSkill
- humanizerSkill
- internal-linksSkill
- meta-tagsSkill
- navboost-auditSkill
- optimizeSkill
- researchSkill
- schema-genSkill
- scoreSkill
- seo-fundamentalsSkill
- topic-clustersSkill
- write-seoSkill

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:
If a draft was supplied: mark which MUST-COVER entities it lacks and which gain points it already has — this is the input for G2/G3 in …
line 26

≈ “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.

Keep what fits and drop the rest. Your version, ready for your agents.

Files

SKILL.md

/entity-coverage — Entity coverage matrix & information gain

Target query: $ARGUMENTS

Evidence: G2 entity-IDF (US9679018B1) and G3 information gain (US20200349181A1) — see ${CLAUDE_PLUGIN_ROOT}/skills/seo-fundamentals/references/patent-signals.md. Knowing what the top 10 cover and what they miss is the primary input to content that ranks differently from them.

Process

Inputs — query (required); locale (infer from the query language unless given); optional existing article to compare.
Fetch the top 10 for the query (WebSearch, then WebFetch each result). Note any result that cannot be crawled (paywall, JS-only, blocked) and proceed with what is available.
Extract entities per result — people, organizations, products, tools, standards, places; versioned references and dates; numeric attributes (prices, percentages, counts); domain concepts (methods, regulations, algorithms). Use a structured extraction pass; do not pad with generic terms (the topic word itself, "Google", "users").
Coverage matrix — rows = entities/attributes, columns = C1…C10, cell ✓/✗, coverage %. Sort by coverage descending.
Classify — MUST-COVER ≥70% · OPPORTUNITY 30–70% · INFORMATION GAIN <30%.
Information-gain points (5–8) — prioritize by originality potential (can the author add own data, a real case, a screenshot?), relevance to intent, author capability. For each: coverage % (n of 10), why it is an opportunity, suggested H2/H3, treatment, research or data needed. Do not invent the data; name what is needed.
Entity salience brief — primary entity (singular), 5–8 secondary specialized entities, required placements (title, H1, first 50 words as sentence subject, subject of ≥3 sentences).
If a draft was supplied: mark which MUST-COVER entities it lacks and which gain points it already has — this is the input for G2/G3 in /score.

Output

Coverage matrix table.
Classification summary (counts + lists).

Information-gain points as structured entries:

GAIN POINT #n: <name>
  Coverage in top 10: X% (Y of 10)
  Why: <reason>
  Suggested heading: "<H2/H3>"
  Treatment: <what to include>
  Data needed from the author: <list>

Entity salience brief.
Uncrawlable results and caveats (entity extraction is approximate; IDF is proxied by "absent from the top 10").

Next: /content-brief (uses these points as outline sections), /write-seo, or /score for an existing draft.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

Reviews can't be read right now.

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.

Check your setup, free