agentleFS
khadinakbarlabskhadinakbarlabs/ai-visibility-tracker/skills/visibility-onboarding/SKILL.md

visibility-onboarding

Skill0 starsChanged 9 days agoMITView on GitHub

Get started with AI search visibility tracking for a brand or website — connect Apify once, ask for brand, website and must-track keywords, research the rest, ask how often to track (hourly, daily, weekly or on demand), then run the baseline, charts and recommendations automatically and save a per-project memory.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 0 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Resume first: Read the project index. If this brand/site already has a project, do not onboard again: route to seo-growth-agent and …

    line 10
  2. Very specific:

    Then do everything, no more questions: Run the baseline (ai-visibility-tracker), generate the dashboard with charts, produce the top …

    line 14

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Onboard once, then run on autopilot

Use on first use, "get started", "track my website/brand", or when adding a new project or site. Follow autopilot for when to ask and when to proceed, research-led intake, Apify access and projects and memory. The host LLM does the research, analysis and writing; the package supplies skills, not its own model, account or database.

  1. Resume first. Read the project index. If this brand/site already has a project, do not onboard again: route to seo-growth-agent and continue from its memory. Ask "which project?" only when several saved projects plausibly match.
  2. Ask once (turn 1). If Apify is not connected, start the browser sign-in yourself on the side (CLI apify login --method console, or the host's connector card) and mention it in one line. In the same short message ask only for brand, website and any keywords or questions that must be tracked — or "figure it out". Never ask for competitors, audience, market, device, panel size or report format; research and default them.
  3. Research without asking. Inspect the site and market (intake): offering, audience, competitors, topics, 5–8 literal buyer questions, target pages and market/device defaults. Put the user's must-track keywords/questions first. Keep verified facts, inferences and user-supplied items labelled. Verify Apify access silently and read live Actor pricing plus credit status.
  4. One plan card, one question (turn 2). Show the plan (brand/site, competitors, tracked questions × platforms, target pages, monthly growth scan, report location) with cost per run and per month for Weekly (recommended) / Daily / Hourly pulse / On demand, and ask "How often should I track this?". Flag any option that exceeds remaining credits. The answer is the standing approval for that plan and its caps; record it once against the plan revision.
  5. Then do everything, no more questions. Run the baseline (ai-visibility-tracker), generate the dashboard with charts, produce the top recommendations with implementation steps (visibility-action-plan), configure and verify the schedule for the chosen frequency (scheduled-visibility-tracking), and save the project memory (portfolio.json, context.md, handoff.md, report).
  6. Finish briefly: what was measured, the top 3 actions, next run with timezone, monthly cap, report location, and how to change frequency, pause, add a website or show the dashboard.

Validation stays on: give each project and site a stable safe ID; accept only public domains and same-domain HTTPS target URLs; exclude local/private addresses and credential-bearing URLs; budgets are finite nonnegative USD; a missing or zero cap permits no paid launch. If Apify is not connected yet, continue the research and show the plan with costs, and start the baseline as soon as access works — without re-asking the onboarding questions. If the host cannot schedule or store files, say so in one line and use on-demand tracking or a downloadable project export.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.