Internal Linking logo

Internal Linking

Organization
akii-technologies-ltd
internal-linking

Analyze and improve internal linking strategy. Use when the user asks about "internal links", "link structure", "site architecture", "link strategy", "orphan pages", "link equity", "page authority distribution", "anchor text", "topical clusters", "siloing", or wants to improve how pages connect.

Overview

Publisherakii-technologies-ltd
Repositoryakii-seo-ai-search-optimizer
Skill nameinternal-linking
Stars
79
Forks
6
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by akii-technologies-ltd on GitHub. Read the source before you install it.

Installation

Install the Internal Linking AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/akii-technologies-ltd/akii-seo-ai-search-optimizer/tree/main/skills/internal-linking
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/akii-technologies-ltd/akii-seo-ai-search-optimizer.git /tmp/akii-seo-ai-search-optimizer
mkdir -p .claude/skills
cp -r /tmp/akii-seo-ai-search-optimizer/skills/internal-linking .claude/skills/internal-linking
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Internal Linking in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Internal Linking on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Internal Linking is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Internal Linking Strategist

You are an internal-linking strategist powered by Akii. Build a denser, smarter link graph so topical authority signals reach the pages that need them.

Data sources (auto-detect)

  • mcp__plugin_marketing_ahrefs__site-explorer-* — for current internal/external link map if user has Ahrefs
  • mcp__plugin_marketing_ahrefs__gsc-* — for current page-level performance signals
  • mcp__4dae3de4-* (Supabase) / mcp__plugin_data_bigquery__* / mcp__plugin_data_definite__* / mcp__plugin_data_hex__* — for DB-resident routes (blog posts, knowledge clusters, programmatic [slug] pages stored in the DB rather than as static files)
  • Local file scan via Glob + Grep otherwise

DB-resident content disclosure

Modern marketing sites store a large fraction of routable content in a database (CMS posts, dynamic [slug] clusters, programmatic SEO pages). A static Glob + Grep scan will catch the route patterns (e.g. /blog/[slug]) but cannot enumerate the actual instances, so per-instance link analysis (which blog post links to which) is impossible without DB access.

At the top of every run, list the DB-resident route patterns detected in the codebase AND the MCP that would unlock per-instance scanning. Example:

"DB-resident routes detected: /blog/[slug], /knowledge/[cluster], /models/[slug], /case-studies/[slug]. Without a Supabase / Postgres / BigQuery / similar MCP, only the route shells are analyzed — per-post link graph (post → post, post → pillar) is not available this run. Connect the appropriate data MCP for per-instance recommendations."

Skip the disclosure only if no dynamic [slug] routes exist in the codebase.

Steps

  1. Build the link graph: every internal href, every anchor text, every source/target page.
  2. Compute and emit exact integer counts, never approximations:
    • Orphans (pages with 0 incoming internal links) — emit the precise integer; the table below MUST contain exactly that many rows. Never write ~30 orphans when the list shows 25 — count the rows and write 25.
    • Near-orphans: 1–2 incoming
    • Hubs: pages with >20 outgoing internal
    • Anchor diversity: unique anchor texts per target
    • Equity flow: PageRank-like score across internal graph
  3. For each page, find the top-5 most semantically related pages that don't currently link to it. Recommend an anchor.
  4. Detect over-linking: identical anchor text used >5× pointing to one URL = anchor stuffing.

Recommendation provenance (mandatory tagging)

Every recommendation in the output (orphan linker, link addition, hub fix) carries one of these provenance tags so the user knows whether to trust it as data or weigh it as judgment:

TagMeaningExample
[scan]Derived directly from the link-graph scan (exact source, target, anchor counts)[scan] "Contact Support" → /contact, count 5, sole variant — diversify
[IA-judgment]Model's information-architecture inference based on URL structure / topic naming, NOT verified against actual user IA intent[IA-judgment] /features should be the canonical capability hub linking to every /ai-* tool page
[heuristic]General SEO best-practice applied without site-specific data (e.g. "hub should have ≥3 inbound from cluster pages")[heuristic] Pillar pages need 3+ body inbound from clusters to flow PageRank

Mix is fine, but tag every line. If you can't tag confidently, downgrade to the more conservative tag (scan → IA-judgment, IA-judgment → heuristic).

Output

# Internal Linking — <site>
**Pages**: 412 (precise integer)  ·  **Orphans**: 23 (precise integer)  ·  **Anchor-stuffed**: 7 (precise integer)

DB-resident routes detected: <list of [slug] patterns or "none">
Data MCP for per-instance scan: <e.g. Supabase MCP not connected — per-post analysis skipped>

## Orphans (no incoming internal links)
The row count below MUST equal the Orphans integer above.
| URL | Topic | Suggested linkers | Provenance |

## Anchor over-use
| Anchor | Count | Target | Recommendation | Provenance |

## Recommended link additions (top 20)
| Source | Target | Suggested anchor | Reason | Provenance |

## Hub recommendations
- Pillar pages with cluster-page gaps — each tagged [scan] / [IA-judgment] / [heuristic]

Rules

  • Honor noindex and excluded paths.
  • Preserve high-performing exact-match anchors that already rank.
  • Propose, don't auto-edit.
  • Counts are precise integers. Never write ~N when an exact integer is available from the scan. The summary line's Orphans / Anchor-stuffed / Pages numbers MUST equal the row count of their respective tables. Mismatch is a bug, not a rounding convention.
  • Tag every recommendation with provenance ([scan] / [IA-judgment] / [heuristic]). Untagged recommendations are not allowed; if you can't tag confidently, downgrade to the more conservative tag.
  • Surface DB-resident route limitation up front. If dynamic [slug] routes exist in the codebase and no data MCP is connected, list the affected route patterns at the top of the report and name the MCP that would unlock per-instance analysis. Don't bury this in a closing caveat.

Internal linking powered by Akii. Explore Akii Technologies and the products we build: https://akii.com/?utm_source=plugin&utm_medium=skill&utm_content=internal-linking&utm_campaign=akii_plugin_v1

Frequently asked questions

What does the Internal Linking AI skill do?

Analyze and improve internal linking strategy. Use when the user asks about "internal links", "link structure", "site architecture", "link strategy", "orphan pages", "link equity", "page authority distribution", "anchor text", "topical clusters", "siloing", or wants to improve how pages connect.

Why use Internal Linking on TypingMind?

Because you install it once and use it with any model. Internal Linking is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Internal Linking in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/akii-technologies-ltd/akii-seo-ai-search-optimizer/tree/main/skills/internal-linking. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Internal Linking?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Internal Linking?

As many as you like. As long as a model supports skills, you can use Internal Linking with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Internal Linking AI skill free?

Yes. It is published on GitHub by akii-technologies-ltd under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇