agentleFS
hikmahtechhikmahtech/drwhome/.claude/skills/marketing-analytics/SKILL.md

marketing-analytics

Skill0 starsChanged 45 days agoMITView on GitHub

Pull Search Console and GA4 for drwho.me via the sibling analytics-toolkit and write a dated markdown report to docs/internal/analytics/ (gitignored). Use when asked how drwho.me is doing in search, or to check traffic to the tools or the MCP server.

6 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions6 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 6

    1. okou-ai/okou-skills★ 81same name
    2. vm0-ai/vm0-skills★ 81same name
    3. minamagdyyyy/agentic-marketing★ 5same name
    4. m-binimran/marketing-pack★ 1same name
    5. paulopestanajunior/agents-config★ 1same name
    6. lengrufeng2008/dsh-skill-library★ 0same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 6 edited versions we read keep these.

  • 0

    Distinctive

    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:

    Read-only. Scope is ONLY drwho.me.

    line 8
  2. Very specific:

    Treat python-httpx and (no client name) as unclassified, not as people.

    line 44

“Common” is measured: kept by at least 6 in 10 of the 6 edited versions of this file we could read. “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

drwho.me analytics report

Read-only. Scope is ONLY drwho.me. Ignore every other property on the account (domainposture.com has its own skill in its own repo). Never invent a number.

Toolkit: ~/Workspace/hikmah/analytics-toolkit (sibling repo, shared with Domain Posture). Default window 28 days; override with DAYS=<n>.

Procedure

  1. Resolve node. Bare node may be an nvm lazy-load function that recurses. NODE="$(ls -d "$HOME"/.nvm/versions/node/*/bin/node | sort -V | tail -1)" and use "$NODE" for every command.
  2. Auth check. "$NODE" ~/Workspace/hikmah/analytics-toolkit/discover.mjs. If it fails with invalid_grant / invalid_rapt / ADC refresh failed, stop and ask the owner to run bash ~/Workspace/hikmah/analytics-toolkit/login.sh in an interactive terminal. From the output keep only sc-domain:drwho.me and the GA4 property for drwho.me (properties/533500563 as of 2026-09; it also holds the pre-split history of the old site, so compare only windows after 2026-09-17).
  3. Pull.
    • DAYS=<n> "$NODE" ~/Workspace/hikmah/analytics-toolkit/gsc.mjs sc-domain:drwho.me
    • DAYS=<n> "$NODE" ~/Workspace/hikmah/analytics-toolkit/ga.mjs properties/533500563
    • DAYS=<n> "$NODE" ~/Workspace/hikmah/analytics-toolkit/ga-mcp.mjs properties/556540241 (the separate "drwho.me MCP" property; MCP events never go to 533500563).
    • Bing: run traffic, pages and queries with https://drwho.me/ via "$NODE" ~/Workspace/hikmah/analytics-toolkit/bing.mjs. The site's own Cloudflare beacon is the primary page-view count; GA4 is secondary.
  4. Write docs/internal/analytics/YYYY-MM-DD.md (the directory is gitignored — the repo is public and these notes name private infrastructure). Sections: header and window; totals with deltas against the previous file; top tool pages; top queries; MCP usage; three concrete actions.

    MCP usage: report real use, never the raw total. Most MCP traffic is directories and registries probing the server (glama, mcpbeat, tendle, *-probe, *-health, …). On 2026-10-02 about 340 sessions came from ~57 clients and one was a real agent. Headline number = REAL USE from ga-mcp.mjs (tool calls from known agents + unclassified clients). Show the agent and unknown rows in full; give probes one summary line. If a new client name looks like a real agent or a probe, add it to the lists in ga-mcp.mjs. Treat python-httpx and (no client name) as unclassified, not as people.

  5. Show the owner a short summary and the file path. Do not commit.

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.