Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add lhitches/claude-seo-skills --skill topical-authority-mapgit clone --depth 1 https://github.com/lhitches/claude-seo-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/lhitches/claude-seo-skills/topical-authority-map)<a href="https://agentmods.dev/skills/lhitches/claude-seo-skills/topical-authority-map"><img src="https://agentmods.dev/badge/skills/lhitches/claude-seo-skills/topical-authority-map/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/lhitches/claude-seo-skills/topical-authority-map"><img src="https://agentmods.dev/badge/skills/lhitches/claude-seo-skills/topical-authority-map.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00110 | $0.01377 |
| Opus 5.5 | $0.00044 | $0.00551 |
| Sonnet 5.5 | $0.00022 | $0.00275 |
| Haiku 4.5 | $0.00011 | $0.00138 |
Grade A, and why
topical-authority-map scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are building a Topical Authority Map. This is a structured site architecture built around how we think Google and AI search engines decide which sites are the specialist on a topic. It is NOT a keyword list. It is NOT a list of topics. It is the blueprint for an entire website's content strategy, built around a single central entity and routed through four connected clusters.
The four clusters:
- Core Pages (the money pages users buy from)
- AOR Pages (Areas of Relevance, the supporting authority articles)
- Linking Map (which page links to which page, with what anchor text)
- Buyer Journey (every page tagged TOFU, MOFU, or BOFU)
Plus a fifth output: a 12-week Publishing Order with content briefs that turns the map into a content plan.
Output: Two deliverables.
.xlsxspreadsheet with five tabs: Core Pages, AOR Pages, Linking Map, Buyer Journey, Publishing Order..mdstrategy document covering central entity, source context, persona, folder structure, linking rules, an optional NLP category check, and quality standards.
Mode: Interactive. Pause at the five checkpoints (marked Checkpoint 1 to Checkpoint 5 in the reference files) to confirm decisions with the user before proceeding. Do not skip checkpoints.
Data honesty. This skill leans on search volumes, SERPs, People Also Ask and autocomplete. Use them only when you can actually see them: through a web search tool, a keyword tool, or data the user pastes (Semrush, Ahrefs, Google Keyword Planner). Search Console impressions are not search volume: they count how often this one site appeared in results, not how many people searched. If the user gives you impressions, keep them in their own column headed "GSC impressions" with the date range, never in the Search Volume column, and never use them for the merge and split thresholds. When you cannot see real volumes, say so, ask the user to paste what they have, and write "no data" in the Search Volume column. Never estimate a search volume or invent a PAA question and present it as researched. Where volume is missing, make merge and split calls on competitor coverage and on whether it is a service the business sells, and say that is what you did.
No file tools? If you cannot create files in this environment, output each spreadsheet tab as its own CSV code block and the strategy document as markdown, and tell the user to paste each CSV into a separate sheet.
Why we think topical maps work
Here is how we think about why topical maps work. These five points are our working theory from running this method on client sites, not confirmed Google mechanisms, and none of them is E-E-A-T marketing:
- Historical user data accumulation. Our working theory: every visitor adds to Google's picture of your site, so a topical map concentrates that picture on one topic and gives Google more evidence that you satisfy users on it. Spread it across four unrelated topics and we think you lose on all four.
- Knowledge Graph alignment. Google has entities with attributes and relationships. We think a site built to MATCH what Google already knows about your entity is easier for Google to understand and match to searches.
- Lower cost of retrieval. Every title, heading, paragraph, and image should map to a real query. Our working theory: pages that answer a clear query in a clear structure are easier for Google to understand and rank.
- Satisfaction signal transfer. We think that when an AOR page satisfies a reader and links to a core page, it helps that core page too. More good AOR pages, stronger core pages.
- Index construction efficiency. Our reasoning: it is simpler for a search engine to serve one site for many related queries than many different sites for one query each, so deep, well-organised coverage gives Google a reason to serve more of the topic from your domain.
Critical warning: A topical map filled with low-quality content hurts the whole site. Bad pages drag every other page down. Do not publish to fill the map. Every article must be quality work. If you cannot write a good article on a topic, leave it out.
What ships with it
7 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- today Changed · +4 lines 353d7cc51ce8
- 1mo ago First seen · 69 lines · 110 tokens per session scan A dec53b7c07d1
topical-authority-map is a skill published in the GitHub repository lhitches/claude-seo-skills (21 stars, last pushed yesterday), licensed MIT. It adds 110 tokens to every session and 1,377 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
comparator
Generic Comparison Matrix Builder: creates, populates, and maintains weighted XLSX comparison matrices for ANY domain and ANY pair (or set) of solutions. Evidence comes from whatever is available — CIRs produced by MultAI's solution-researcher, documents in the working folder, LLM knowledge, or user description. A CIR…
board-deck-builder
Assembles comprehensive board and investor update decks by pulling perspectives from all C-suite roles. Use when preparing board meetings, investor updates, quarterly business reviews, or fundraising narratives. Covers structure, narrative framework, bad news delivery, and common mistakes.
excel-cli
Discover and launch the Excel CLI for ordinary Excel workbook requests on Windows, including reads, writes, formulas, data refreshes, and workbook automation. Use the installed excel-cli plugin's npx launcher and native help to find commands; report presentation conventions are a separate optional skill.
google-apps-script
Build Google Apps Script automation for Sheets and Workspace. Custom menus, triggers (onEdit / time-driven / form submit), dialogs, sidebars, email batches, PDF export, external API. Use whenever the user wants to automate a Google Sheet, build a Sheets menu / sidebar / dialog, hit a Sheets row from email or a…
dgn-to-excel
Convert DGN files (v7-v8) to Excel databases. Extract elements, levels, and properties from infrastructure CAD files.
dwg-to-excel
Convert AutoCAD DWG files (1983-2026) to Excel databases using DwgExporter CLI. Extract layers, blocks, attributes, and geometry data without Autodesk licenses.