Add internal links to every article without DB edits

    1

    a method and reference implementation for internal linking at scale.

    Free

    Security scanned

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    Add internal links to every article without DB edits

    Example session with this skill installed

    A 5-line article snippet with a heading, an existing link, an image alt, a code block and plain text, plus a 5-entry link map where 'guides' is a substring of another target's URL. Run with --self-url /ergonomics.
    Command: python3 scripts/link_injector.py --map links.json --html article.html --self-url /ergonomics

    • Read your context and instructions
    • Compiled the add internal links
    • Generated the UI component

    Standing desk setup

    A standing desk works best with a monitor arm. See our desk reviews.

    Good ergonomics beats expensive desks.

    desk.height = elbow_height

    More guides on ergonomics are coming.

    --audit result: {"anchors": 4, "auto_links": 3, "nested_anchor_depth": 1, "href_contains_anchor": false} **Note:** Real run of the injector on a short illustrative article.

    setup.jpg

    TSX · React component

    Generated

    Example file from a real run - the skill writes it into your workspace.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    What it does: a method and reference implementation for internal linking at scale. Instead of bulk-updating the content table, the agent injects links in the server-side render step, so every article gains links immediately and a bad map is a code revert. Before building the map it probes each target URL (only 200 counts; a redirect to login is excluded) and freezes that as a test. The injector follows ten safety rules, including whole-word Unicode matching, longest keyword first, one link per keyword with a page cap, self-link skipping, idempotency and re-segmenting after each insert so a later keyword never lands inside a fresh href. It tests on exported real articles and verifies the live page. Who it is for: site owners, content teams and developers with blogs or docs too large to link by hand. What is inside: SKILL.md workflow, small-archive strategy, generator rules, live verification; scripts/link_injector.py (inject + audit, self-test). Limits: internal links help crawling and context; they do not make weak pages rank. Port the logic to your stack for production rendering.

    Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Marketing & SEO.

    • Regex-based HTML segmentation assumes reasonably well-formed article HTML; always run the audit on real exports.
    • Keyword matching is literal; synonyms need their own map entries.
    • Target reachability checks need network access to your own site.
    • Does not decide your site structure; it links to pages you already have.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before buying a skill.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Free to use

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed today

    • Free with an Agensi account

    Permissions

    Terminal / Shell
    Network Access
    Read Files

    Allowed Hosts

    your-site$u
    your-site
    Listedtoday

    What's inside

    Frequently Asked Questions

    Render-time injection gives the same HTML to crawlers with zero production writes; undoing a bad map is a code revert instead of a data restore.

    It skips headings, existing links, code, scripts, captions and attributes, and the audit mode checks for nested anchors and links inside hrefs.

    Yes. Word boundaries are Unicode-aware, so 'café' links while 'cafés' does not.

    Probably not. The skill adds a deterministic related-reading block so each target still receives inbound links.

    Any server-rendered stack or static build step. The Python file is a reference you can port; the tests define the behavior.

    New in Marketing & SEO

    Free