Plan and build new pages from real topic gaps, with your agent
Turns competitor topic gaps and customer questions from clickd’s content brain into fact-backed briefs and finished pages in your repo, complete with question headings, internal links and JSON-LD schema.
Add it, from the top of the site’s repositorynpx skills add subinternal/clickd --skill clickd-content-brief
Then ask your agentPull the next topic gap for example.com with clickd, write a brief from our repo’s facts, build the page with schema and internal links, and check it live.
For founders, marketers and developers shipping new guides, tools or service pages
Four steps from topic gap to published, linked page
Your agent checks your sitemap first so you never build a duplicate page, writes a brief from real repo facts, builds the route, and wires internal links.
1Pick a gap no existing page on the site already coversclickd_content_next
2Assemble the brief from real site facts and rival gaps
3Build the page, schema and internal links in the repo
4Check the live page with clickd and mark the brief doneclickd_check
A topic gap turned into a finished page
From `clickd_content_next` to a deployed route on example.com with schema and internal links.
example.com/guides/cold-chain-monitoring
Built from content brief #14; 0 duplicate routes in sitemap.
Sample
Intent & format checkGap flagged by clickd_gaps; top results are technical guidesAssigned to /guides/cold-chain-monitoring with sensor range table and alert rules
Fact source in repoSensor specs in src/data/hardware.ts; compliance rules in docs/Every temperature range, battery life figure and alert threshold read from repo data
Internal links wiredNew pages previously launched as orphans with 0 incoming linksLinked from /guides, /industries/pharmacy, /sensors/temp-pro and /llms.txt
Live clickd checkChecked before marking brief donePasses clickd_check (agent view), 0 AI writing tells, valid Article JSON-LD
How clickd powers the content brief loop
Every brief comes from measured gaps and ends with a live check on the deployed URL.
clickd_content_brain & clickd_content_nextGenerates and prioritizes topic briefs from rival gaps, market questions and your existing pages.
clickd_links & clickd_schema_createFinds the existing hub pages that should link to the new route and builds its JSON-LD block.
clickd_check, clickd_tells & clickd_content_doneVerifies the live page renders cleanly with zero AI tells before marking the brief complete.
When to reach for it
Reach for it when
Rivals rank or get cited for buyer topics where your site has no page yet.
You want to turn clickd_content_next or clickd_gaps into a finished, well-linked page in your repo.
You want every new guide or landing page to ship with schema, sitemap entry and internal links on day one.4
Leave it when
An existing page on your site already targets the same search intent: use the content refresh skill instead.
You want to mass-generate dozens of unreviewed articles with no real product or business facts.2
More things to ask your agent
Everyday prompts that load the Content brief skill in Claude Code, Codex or Cursor.
Next brief from content brainCall clickd_content_next on example.com, assemble the brief using facts from our repo, build the page, and link it from 3 hubs.
Build a technical guideTurn our top competitor topic gap in clickd_gaps into a new guide with question H2s, Article schema and sitemap entry.
Brief only for reviewWrite a fact-backed content brief for our next service page from clickd_gaps and stop for my review before drafting code.
Content brief 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 brief skill
How does Content brief prevent duplicate or thin AI articles?
Step 1 checks your existing routes and sitemap first so you never build a second page for an existing intent, and Step 2 requires every section to cite real facts from your repository or ask you before writing.
Does the skill also wire internal links to the new page?
Yes. A new page published with zero incoming internal links sits as an orphan. Step 3 adds descriptive internal links from 3 to 5 existing hub or sibling pages in the same commit.
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-brief.
Puts the files in .claude/skills/clickd-content-brief/.
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-brief; /skills lists them.
Puts the files in .agents/skills/clickd-content-brief/.
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-brief/.
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.
Terminal, for Any other agent
mkdir -p docs/clickd-content-brief
curl -fsSL https://clickd.com/skills/content-brief/SKILL.md -o docs/clickd-content-brief/SKILL.md
echo "For planning and building new pages from topic gaps, follow docs/clickd-content-brief/SKILL.md." >> AGENTS.md
PowerShell, for Any other agent
New-Item -ItemType Directory -Force docs\clickd-content-brief | Out-Null
Invoke-WebRequest https://clickd.com/skills/content-brief/SKILL.md -OutFile docs\clickd-content-brief\SKILL.md -UseBasicParsing
Add-Content AGENTS.md "For planning and building new pages from topic gaps, follow docs/clickd-content-brief/SKILL.md."
Puts the files in docs/clickd-content-brief/.
What is inside
SKILL.md stays short and sends your agent to a reference when a step needs it.
SKILL.mdThe four steps from picking an uncovered topic gap to assembling a fact-backed brief, building the page with schema and internal links in the repo, and checking live with clickd.90 lines