Meridian Result Visualization
google/meridian
Loads a saved Meridian MMM model and produces an HTML results summary, with optional health checks and approval checkpoints at each step.
Looker Studio (formerly Google Data Studio) expertise. An agent skill from thatrebeccarae/claude-marketing.
$ npx skills add thatrebeccarae/claude-marketing --skill looker-studio -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install thatrebeccarae/claude-marketing looker-studio --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/thatrebeccarae/claude-marketing.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/looker-studio .claude/skills/looker-studio && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "looker-studio" agent skill from https://github.com/thatrebeccarae/claude-marketing/tree/main/skills/looker-studio into .claude/skills/looker-studio/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "looker-studio", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/thatrebeccarae/claude-marketing/tree/main/skills/looker-studioType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add thatrebeccarae/claude-marketing --skill looker-studio -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install thatrebeccarae/claude-marketing looker-studio --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/thatrebeccarae/claude-marketing.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/looker-studio .agents/skills/looker-studio && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "looker-studio" agent skill from https://github.com/thatrebeccarae/claude-marketing/tree/main/skills/looker-studio into .agents/skills/looker-studio/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "looker-studio", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add thatrebeccarae/claude-marketing --skill looker-studio -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install thatrebeccarae/claude-marketing looker-studio --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/thatrebeccarae/claude-marketing.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/looker-studio .cursor/skills/looker-studio && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "looker-studio" agent skill from https://github.com/thatrebeccarae/claude-marketing/tree/main/skills/looker-studio into .cursor/skills/looker-studio/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "looker-studio", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/thatrebeccarae/claude-marketing.git --path skills/looker-studio--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add thatrebeccarae/claude-marketing --skill looker-studio -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install thatrebeccarae/claude-marketing looker-studio --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/thatrebeccarae/claude-marketing.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/looker-studio .gemini/skills/looker-studio && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "looker-studio" agent skill from https://github.com/thatrebeccarae/claude-marketing/tree/main/skills/looker-studio into .gemini/skills/looker-studio/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "looker-studio", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install thatrebeccarae/claude-marketing looker-studioInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add thatrebeccarae/claude-marketing --skill looker-studio -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/thatrebeccarae/claude-marketing.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/looker-studio .github/skills/looker-studio && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "looker-studio" agent skill from https://github.com/thatrebeccarae/claude-marketing/tree/main/skills/looker-studio into .github/skills/looker-studio/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "looker-studio", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add thatrebeccarae/claude-marketing --skill looker-studio -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install thatrebeccarae/claude-marketing looker-studio --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/thatrebeccarae/claude-marketing.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/looker-studio .opencode/skills/looker-studio && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "looker-studio" agent skill from https://github.com/thatrebeccarae/claude-marketing/tree/main/skills/looker-studio into .opencode/skills/looker-studio/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "looker-studio", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
looker-studioLooker Studio (formerly Google Data Studio) expertise. An agent skill from thatrebeccarae/claude-marketing.
Looker Studio is an agent skill from thatrebeccarae/claude-marketing. Looker Studio (formerly Google Data Studio) expertise. Build dashboards, design data visualizations, connect data sources, and create marketing reports. Use when the user asks about Looker Studio, Data Studio, marketing dashboards, data visualization, report building, or connecting analytics data sources.
Its SKILL.md is about 3.6k tokens, which your agent loads only when the skill is triggered. The skill folder holds 7 other files, including scripts (for example `EXAMPLES.md`, `REFERENCE.md` and `scripts/data_pipeline.py`).
It sits in Data & Analytics, covering Data visualization, Paid advertising and Marketing analytics. The repository describes itself as: A full marketing department for Claude Code. Skill packs for Klaviyo, Shopify, GA4, Looker Studio, paid media, and more. Audit, optimize, and report using natural language. The licence is MIT.
4 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit a8a63ec. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Ships 1 file in scripts/ (Python), which the agent can run.
Shell commands in SKILL.md call:
pythongitFrom the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Looker Studio loads about 3.6k tokens when it runs. Until then it costs about 80 tokens; SKILL.md has 1,046 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check noted patterns worth knowing about, such as sudo or a known installer.
code** API credentials in scripts — use `.env` files- Add `.env` and credential files to `.gitignore`Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.
The full file from thatrebeccarae/claude-marketing at commit a8a63ec, republished under its MIT licence (© thatrebeccarae). 1,046 words, ~3,595 tokens.
.claude/skills/looker-studio/SKILL.md (or your agent's skills folder). This skill also uses 6 other files; get the full folder from GitHub.Expert-level guidance for Looker Studio — building dashboards, connecting data sources, designing visualizations, and creating automated marketing reports.
git clone https://github.com/thatrebeccarae/claude-marketing.git && cp -r claude-marketing/skills/looker-studio ~/.claude/skills/--, //, or /* */ style comments. Never include comments in formulas. Add context in the field description instead.CONTAINS_TEXT(), LOWER(), or exact match over regex when possible(?i) for case-insensitive, but does NOT support lookaheads/lookbehinds\\ for literal backslash in regex patterns within string literals (e.g., "\\s" for whitespace, "\\|" for literal pipe)Page 1: Executive Summary
|- KPI scorecards (Revenue, ROAS, CPA, Spend, Conversions)
|- Period-over-period trend lines
|- Channel performance table (sortable)
|- Budget pacing gauge chart
Page 2: Paid Media Deep-Dive
|- Google Ads performance (campaign breakdown)
|- Meta Ads performance (campaign breakdown)
|- Microsoft Ads performance
|- Cross-channel spend allocation (pie/donut)
|- CPA trend by channel (combo chart)
Page 3: SEO & Organic
|- Google Search Console: impressions, clicks, CTR, position
|- Top queries table
|- Page-level performance
|- Organic landing page engagement (from GA4)
Page 4: Email & CRM
|- Email campaign metrics (opens, clicks, revenue)
|- List growth trend
|- Flow/automation revenue
|- Subscriber engagement tiers
Page 5: Conversion Funnel
|- Funnel visualization (awareness -> consideration -> conversion)
|- Landing page performance table
|- Device breakdown
|- Geographic heatmapPage 1: Revenue Overview
|- Revenue, Orders, AOV, Conversion Rate scorecards
|- Revenue trend (daily/weekly)
|- Revenue by channel
|- Top products table
Page 2: Customer Acquisition
|- New vs returning customer revenue
|- CAC by channel
|- LTV:CAC ratio
|- First-order source attributionPage 1: Organic Performance
|- Total clicks, impressions, CTR, avg position
|- Trend lines (90-day)
|- Top 20 queries (with position change)
|- Top landing pages
|- Device + country breakdown| Data Type | Best Chart | Avoid |
|---|---|---|
| KPI with comparison | Scorecard with delta | Pie chart |
| Trend over time | Line chart or area chart | Bar chart (if >7 periods) |
| Category comparison | Horizontal bar chart | 3D charts |
| Part of whole | Stacked bar or donut | Pie with >6 slices |
| Distribution | Histogram or heatmap | Scatter (if not correlation) |
| Geographic | Geo map or heatmap | Tables for location data |
| Funnel | Custom funnel (shapes) | Bar chart |
| Table data | Table with heatmap bars | Unsorted tables |
When asked to create a Looker Studio dashboard:
CASE
WHEN date_field >= DATE_DIFF(TODAY(), INTERVAL 30 DAY) THEN "Current Period"
WHEN date_field >= DATE_DIFF(TODAY(), INTERVAL 60 DAY) THEN "Previous Period"
ELSE "Older"
ENDCASE
WHEN REGEXP_MATCH(source_medium, "google.*cpc|google.*paid") THEN "Google Ads"
WHEN REGEXP_MATCH(source_medium, "facebook|fb|meta|instagram") THEN "Meta Ads"
WHEN REGEXP_MATCH(source_medium, "bing.*cpc|microsoft") THEN "Microsoft Ads"
WHEN REGEXP_MATCH(source_medium, "email|klaviyo|braze") THEN "Email"
WHEN source_medium = "organic" THEN "Organic Search"
WHEN REGEXP_MATCH(source_medium, "social") THEN "Organic Social"
ELSE "Other"
ENDSUM(revenue) / SUM(cost)Ask me questions like:
For detailed Looker Studio function reference, connector setup guides, and advanced techniques, see REFERENCE.md.
Dashboard templates designed for DTC e-commerce teams running Klaviyo + Shopify + GA4.
Track email and SMS marketing effectiveness with Klaviyo data.
Page 1: Email & SMS Overview
|- Scorecards: Total Revenue, Flow Revenue %, Campaign Revenue %, List Size
|- Revenue trend: flows vs campaigns over time (area chart)
|- Channel split: email vs SMS revenue (stacked bar)
|- Engagement tiers donut: Active / Warm / At-Risk / Lapsed
Page 2: Flow Performance
|- Flow revenue table (sortable by revenue, click rate)
|- Welcome Series funnel (sent -> opened -> clicked -> converted)
|- Abandoned Cart recovery rate trend
|- Flow-over-flow comparison (combo chart)
Page 3: Campaign Performance
|- Campaign table: send date, subject, open rate, click rate, revenue
|- A/B test results (winner highlighting)
|- Send time heatmap (day of week x hour)
|- Unsubscribe rate trendData source: Google Sheets (fed by data_pipeline.py --action sync-klaviyo)
Map flow performance across the customer journey.
Page 1: Journey Overview
|- Stage funnel: Prospect -> New Customer -> Active -> VIP -> At-Risk -> Lapsed
|- Revenue by stage (horizontal bar)
|- Stage transition rates
Page 2: Stage Deep-Dive
|- Filter control: select lifecycle stage
|- Flow performance for selected stage
|- Customer count trend per stage
|- Revenue per customer by stage (combo chart)Reconcile Klaviyo-attributed revenue with Shopify actuals.
Page 1: Attribution Overview
|- Scorecards: Shopify Revenue, Klaviyo Attributed, Attribution %, Gap
|- Daily revenue: Shopify total vs Klaviyo attributed (dual axis)
|- Channel breakdown: Email, SMS, Flows, Campaigns (stacked bar)
|- Attribution gap trend line
Page 2: Channel Detail
|- Channel performance table (Klaviyo revenue per channel)
|- Shopify source breakdown (UTM-based)
|- Overlap analysis notesData source: Blended — Shopify Orders sheet + Klaviyo Revenue sheet
Campaign-level ROI with A/B test insights.
Page 1: Campaign Scorecard
|- Filter: date range, campaign type, channel
|- Campaign table with conditional formatting (green/red on benchmarks)
|- Revenue per recipient trend
|- Best-performing subject lines (top 10)
Page 2: Send Optimization
|- Send time analysis (heatmap: day x hour)
|- Audience size vs performance scatter
|- Frequency analysis: sends per subscriber per monthCopy-paste formulas for common DTC metrics in Looker Studio.
SUM(total_revenue) / COUNT_DISTINCT(customer_email)SUM(ad_spend) / COUNT_DISTINCT(CASE WHEN order_number = 1 THEN customer_email ELSE NULL END)(SUM(total_revenue) / COUNT_DISTINCT(customer_email)) / (SUM(ad_spend) / COUNT_DISTINCT(new_customer_email))COUNT_DISTINCT(CASE WHEN order_count > 1 THEN customer_email ELSE NULL END) / COUNT_DISTINCT(customer_email) * 100SUM(CASE WHEN source_type = "flow" THEN revenue ELSE 0 END) / SUM(revenue) * 100CASE
WHEN days_since_last_open <= 30 THEN "Active (0-30d)"
WHEN days_since_last_open <= 90 THEN "Warm (31-90d)"
WHEN days_since_last_open <= 180 THEN "At-Risk (91-180d)"
ELSE "Lapsed (180d+)"
ENDSUM(revenue) / SUM(recipients)SUM(discount_amount) / SUM(gross_revenue) * 100Paid connectors (Supermetrics, $30-100/mo) work but aren't necessary. The free pattern:
python scripts/data_pipeline.py --action sync-klaviyo --sheet-id YOUR_SHEET_IDpython scripts/data_pipeline.py --action sync-shopify --sheet-id YOUR_SHEET_ID --days 30# Create a sheet with correct headers for a CRM dashboard
python scripts/data_pipeline.py --action create-sheet --template crm-dashboard
# See all available templates
python scripts/data_pipeline.py --action list-templatesFor complete dashboard build walkthroughs and use cases, see EXAMPLES.md.
The skill includes a data pipeline script for pushing data to Google Sheets:
python scripts/data_pipeline.py --action sync-klaviyo --sheet-id SPREADSHEET_IDpython scripts/data_pipeline.py --action sync-shopify --sheet-id SPREADSHEET_ID --days 30python scripts/data_pipeline.py --action create-sheet --template crm-dashboardData not refreshing: Google Sheets data in Looker Studio caches for ~15 minutes. Force refresh with the "Refresh data" button in Looker Studio, or set the data source cache to 1 minute in report settings.
Calculated field errors: Common causes:
--, //, or /* */ comments. Never include comments in calculated field formulas. Use the field description for documentation instead."\\s" for whitespace, "\\|" for literal pipe).Blending shows nulls: Left outer join means unmatched rows from the right source show null. Ensure join keys match exactly (case-sensitive, same date format).
Sheets row limit: Google Sheets has a 10M cell limit. For large datasets, aggregate before writing (daily summaries instead of per-event data), or use BigQuery instead.
Service account permission errors: The service account email must be shared on the target Google Sheet with Editor access. Check IAM permissions if Drive API calls fail.
.env files.env and credential files to .gitignore© thatrebeccarae, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 6 other files (scripts) in skills/looker-studio of thatrebeccarae/claude-marketing.
Open the folder on GitHubat commit a8a63ec
Looker Studio next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Looker Studio this skillthatrebeccarae/claude-marketing | 161 | — | ~3.6k | Automated safety check: Notes | MIT | |
| Meridian Result Visualizationgoogle/meridian | 1.6k | — | ~1.3k | Automated safety check: Pass | Apache-2.0 | |
| Meridian Budget Optimizationgoogle/meridian | 1.6k | — | ~1.1k | Automated safety check: Pass | Apache-2.0 | |
| Soku CLIAbout-Intelligence/soku-cli | 305 | — | ~2.4k | Automated safety check: Pass | MIT | |
| Analytics Trackingfreekmurze/dotfiles | 1k | 12 repos | ~2k | Automated safety check: Pass | None | |
| Google Adsarnabbagxd/Brand-building-skills | 729 | — | ~3.1k | Automated safety check: Pass | MIT |
google/meridian
Loads a saved Meridian MMM model and produces an HTML results summary, with optional health checks and approval checkpoints at each step.
google/meridian
Reopens a fitted Meridian MMM from a saved file and runs budget allocation scenarios, producing an HTML report and a Python script that repeats the run.
About-Intelligence/soku-cli
Guides an agent through the soku command line tool for ads, GA4 and PostHog data reads, ads writes, SEO hosting, automations, files and skill management.
freekmurze/dotfiles
When the user wants to set up, improve, or audit analytics tracking and measurement.
arnabbagxd/Brand-building-skills
Plan, build, and optimize Google Ads campaigns — Search, Shopping, Performance Max, Display, and YouTube — including keyword research, match types, bidding strategy, Quality Score, ad extensions…
kostja94/marketing-skills
When the user wants to set up, audit, or optimize analytics tracking (GA4, events, conversions).
thatrebeccarae/claude-marketing
Analyze Google Analytics data, review website performance metrics, identify traffic patterns, and suggest data-driven improvements.
thatrebeccarae/claude-marketing
Comprehensive content marketing toolkit with brand voice analysis, SEO optimization scripts, content frameworks, social media strategy, and content calendar planning.
thatrebeccarae/claude-marketing
Klaviyo marketing operations and analyst expertise. An agent skill from thatrebeccarae/claude-marketing.
thatrebeccarae/claude-marketing
Klaviyo API and developer integration expertise. An agent skill from thatrebeccarae/claude-marketing.
thatrebeccarae/claude-marketing
Shopify e-commerce platform marketing expertise. An agent skill from thatrebeccarae/claude-marketing.
thatrebeccarae/claude-marketing
A/B and multivariate testing methodology. An agent skill from thatrebeccarae/claude-marketing.
Categories
Looker Studio (formerly Google Data Studio) expertise. An agent skill from thatrebeccarae/claude-marketing. Looker Studio is an agent skill from thatrebeccarae/claude-marketing. Looker Studio (formerly Google Data Studio) expertise.
Looker Studio fits situations like: the user asks about Looker Studio; marketing dashboards; data visualization; report building.
Run `npx skills add thatrebeccarae/claude-marketing --skill looker-studio -a claude-code`. Or copy the skill folder (skills/looker-studio in thatrebeccarae/claude-marketing) into .claude/skills/looker-studio in your project. Claude Code loads it when a task matches its description.
Run `npx skills add thatrebeccarae/claude-marketing --skill looker-studio -a codex`. Or copy the skill folder (skills/looker-studio in thatrebeccarae/claude-marketing) into .agents/skills/looker-studio in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add thatrebeccarae/claude-marketing --skill looker-studio -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/looker-studio, .gemini/skills/looker-studio, .github/skills/looker-studio and .opencode/skills/looker-studio in your project.
Going by SKILL.md and its folder, Looker Studio needs Python for the scripts in its folder and the command-line tools its instructions call (python and git). Our summary lists: Python 3.
SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found notes only (mentions a .env file), nothing it rates as a warning. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
Looker Studio is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
About 3.6k tokens (SKILL.md is roughly 14k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Looker Studio: Meridian Result Visualization (google/meridian, 1.6k stars), Meridian Budget Optimization (google/meridian, 1.6k stars), Soku CLI (About-Intelligence/soku-cli, 305 stars) and Analytics Tracking (freekmurze/dotfiles, 1k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
thatrebeccarae (a GitHub user) maintains it in thatrebeccarae/claude-marketing, which has 161 GitHub stars. The repository holds 55 skills in this directory. The repository was last updated on May 14, 2026.
Source: thatrebeccarae/claude-marketing on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.