Recover slipping pages and refresh stale content, with your agent
Finds pages losing Search Console clicks or carrying stale facts, diagnoses whether the drop is snippet decay, a substance gap or internal overlap, updates the page in code, and checks live with clickd.
Add it, from the top of the site’s repositorynpx skills add subinternal/clickd --skill clickd-content-refresh
Then ask your agentFind the pages on example.com that lost the most Search Console clicks recently, diagnose why, refresh their facts and headings in code, and verify with clickd.
For teams with an existing library of guides, docs or landing pages that need upkeepCheck a page for AI tells
Four steps from decay diagnosis to verified refresh
Your agent diagnoses whether a page lost clicks from snippet fatigue, outdated facts or internal overlap before editing a line.
1Find pages losing clicks or carrying stale factsclickd_traffic
2Diagnose why the page slipped
3Refresh the substance, headings and links in codeclickd_tells
4Check the refreshed page live with clickdclickd_check
A decaying guide diagnosed and refreshed
Substance, headings, citations and schema updated in code while keeping the working URL intact.
example.com/guides/soc2-checklist
Clicks down 38% over 60 days; diagnosed as substance + snippet decay.
Sample
DiagnosisImpressions steady (4,900/mo), average place slipped 3.1 -> 6.8Rivals added continuous monitoring steps and current auditor timelines
Substance & headings2024 control names and a 180-word throat-clearing introUpdated control table, 45-word direct answer under H1, 2 new question H2s
Links & citations2 dead outbound links (404); only 1 incoming internal linkReplaced broken sources with AICPA docs; added 4 internal links from hub pages
dateModified disciplineStale 2024 date in Article JSON-LDUpdated visible date and Article dateModified after shipping real factual edits
How clickd proves the refresh
Never bump a date without updating substance. clickd checks the live HTML and tracks the change.
clickd_traffic & clickd_queriesSpots pages where clicks, CTR or average position slipped across recent Search Console windows.
clickd_pages & clickd_tellsChecks the page’s current rules, outbound links and AI writing tells before and after the rewrite.
clickd_rescan & clickd_changesVerifies the refreshed page passes every on-page, link and schema rule on the live site.
When to reach for it
Reach for it when
Guides or landing pages that used to bring steady search traffic have slipped in clicks or position.4
Pages reference old versions, retired features, outdated pricing or broken outbound citations.
Two pages on your site have started splitting impressions for the same search.
Leave it when
You only want to change the published date to today without updating the page’s substance.1,3
The page is brand new and has not been indexed long enough to measure.
More things to ask your agent
Everyday prompts that load the Content refresh skill in Claude Code, Codex or Cursor.
Recover slipping pagesUse clickd_traffic and clickd_queries to find the 3 pages that lost the most clicks over the last 60 days and refresh them in code.
Update outdated guidesAudit our /guides/ folder for stale 2024/2025 facts, dead outbound links and AI tells, update the substance, and verify with clickd.
Resolve keyword cannibalizationFind where two of our pages split impressions for the same query and merge or refocus them cleanly.
Content refresh skill vs the alternatives
Why pairing an open repository skill with a live crawler beats manual audits and prompt-only checklists.
How it reads your siteBy hand: Manual spot-checks in a browser · Prompt-only skill: Reads local source files only; misses live headers, redirects and JS shellsReads the live URL, HTTP headers, raw HTML and Search Console via clickd MCP
How changes are madeBy hand: Copy-pasting between docs, spreadsheets and editors · Prompt-only skill: Suggests generic copy in chat with no repo contextEdits your actual templates, routes and schema in the repository
How fixes are provedBy hand: Checking pages one by one after deploy · Prompt-only skill: Agent grades its own homework with no live checkRuns clickd_rescan and clickd_changes on the deployed site to prove rules passed
Skills to use alongside it
Included when you run npx skills add subinternal/clickd.
Keyword researchFinds striking-distance keywords (positions 4 to 20), CTR gaps, cannibalized queries and competitor topic gaps using Google Search Console data and clickd, then maps each query to one page and one action.See skill
On-page SEORewrites title tags, meta descriptions, single H1s, question headings, answer-first openings, image alt text and AI writing tells in your site’s templates and content files, checked live with clickd.See skill
Site architectureAudits and fixes your site’s internal link graph, orphan pages, topic hubs, crawl depth and BreadcrumbList schema in code, then verifies the updated structure on the live site with clickd.See skill
Questions about the Content refresh skill
Should my agent update `dateModified` on every build?
Never. Bumping dates without changing the substance of the page violates Google’s date guidelines. The skill only updates dateModified after making verifiable factual or structural improvements.
Should we change the URL slug when refreshing an old guide?
Keep existing working URLs intact whenever possible. Changing a URL forces a redirect and resets link signals; only redirect when consolidating two competing pages.
Install it by hand
The line at the top adds it for any agent. Or fetch its 1 files where your agent looks. Your agent also needs clickd connected over MCP: connecting an agent shows how.
Loads skills from .claude/skills/ in the repository, for everyone who works in it, or ~/.claude/skills/ for every project on your machine. Claude uses it when a request matches its description, or type /clickd-content-refresh.
Puts the files in .claude/skills/clickd-content-refresh/.
Loads skills from .agents/skills/ in the repository and its parent folders, or ~/.agents/skills/ for every project. Codex uses it when a task matches its description, or mention it as $clickd-content-refresh; /skills lists them.
Puts the files in .agents/skills/clickd-content-refresh/.
Loads skills from .cursor/skills/ or .agents/skills/ in the repository, or ~/.cursor/skills/ for every project. It also reads .claude/skills/, so one copy there serves both. The agent uses it when it is relevant, or type / in Agent chat and pick it.
Puts the files in .cursor/skills/clickd-content-refresh/.
An agent that does not load skills can still follow the file. Save the folder in the repository and point its standing instructions at it, with a line in AGENTS.md, which many agents read. The agent reads AGENTS.md when it starts, and follows the file when the task matches.
SKILL.md stays short and sends your agent to a reference when a step needs it.
SKILL.mdThe four steps from spotting slipping pages in Search Console to diagnosing the drop, refreshing facts, headings and links in code, and checking live with clickd.89 lines