Analytics & metrics
1,706 rows from 429 repositories
Instrumenting a product and reading what comes back.
What Analytics & metrics skills agree on
352 skill files read, by 333 of the 342 authors on this shelf whose files we hold, 2026-09-06
The middle one of the 66 measured here is ~2.0k tokens long, counted with cl100k_base
Counted by distinct author, so one author publishing three of these counts once. Where a claim sits in fewer files than authors, that is said: a claim held by forty authors across three files is one file people copied, not forty people who agreed. Near-identical wordings are grouped and the other wordings are shown, so the grouping is yours to check.
What they tell the agent to do
- Read product marketing context before asking questions37 of 333 in 16 filesalso worded as Check for product context files before asking questions; Read the product marketing context file first
- Test one variable at a time26 of 333 in 11 filesalso worded as Test a single variable per test; Test one variable per test
- Pre-determine sample size before launch24 of 333 in 16 filesalso worded as Pre-determine sample size before launching; Calculate sample size before launching
- Verify tracking and QA variants before launch17 of 333 in 8 filesalso worded as Verify tracking and QA all variants before launch; Verify event tracking and variant attribution before launch
- Monitor for technical issues during the test14 of 333 in 6 files
- Match each save offer to the cancel reason14 of 333 in 5 filesalso worded as match save offers to cancel reasons
- Start every test with a specific hypothesis14 of 333 in 7 filesalso worded as Start with a specific hypothesis; Start each test with a specific hypothesis
- Keep the continue-cancelling option visible13 of 333 in 4 filesalso worded as Keep the continue-cancelling action visible and unobstructed
- Document every test with hypothesis, variants, results, and learnings13 of 333 in 6 filesalso worded as Document every test with hypothesis, variants, results, and learnings; Document every test with results and learnings
- Gather churn, billing, product, usage, and constraint context first12 of 333 in 3 filesalso worded as Gather churn, billing, usage, and constraint context; Gather churn, billing, usage, and constraint context first
- Build a health score from weighted signals12 of 333 in 3 filesalso worded as Build a health score from churn signals; Build a weighted 0-100 health score
- Retry soft declines 3-5 times over 7-10 days12 of 333 in 3 filesalso worded as Retry soft declines three to five times; Retry soft declines 3-5 times over 7-10 days
- Stop tests where guardrails turn significantly negative12 of 333 in 4 filesalso worded as Stop the test on significant guardrail failure; Stop the test if guardrail metrics significantly worsen
- Collect only what you need11 of 333 in 6 filesalso worded as only collect what you need; Only collect data you need
- Establish naming patterns before implementing10 of 333 in 5 filesalso worded as establish naming conventions before implementing
What they tell it not to do
- Do not change variants mid-test26 of 333 in 16 filesalso worded as Do not change variants mid-test; Don't change variants mid-test
- Do not peek at results and stop early26 of 333 in 16 filesalso worded as Don't peek at results and stop early; Do not stop early because results look good
- Do not add traffic from new sources mid-test21 of 333 in 11 filesalso worded as Adding traffic from new sources during a test; Don't add traffic from new sources
- Never put PII in event properties15 of 333 in 14 filesalso worded as Never put PII in event properties; Never include PII in event properties
- Do not retry hard declines14 of 333 in 5 filesalso worded as Don't retry hard declines; Never retry hard declines
- Do not track vanity metrics14 of 333 in 10 filesalso worded as Focusing on vanity metrics only; Do not track vanity metrics
- Avoid discounts of 50 percent or more13 of 333 in 4 filesalso worded as Don't discount deeper than 50 percent; offering discounts of 50% or more
- Do not hide the cancel option12 of 333 in 3 filesalso worded as Don't hide the cancel button; don't hide the cancel option
- Do not use spaces or special characters in event names11 of 333 in 6 filesalso worded as don't use spaces or special characters in event names; no spaces or special characters in event names
- Don't cherry-pick segments10 of 333 in 3 filesalso worded as Don't cherry-pick segments
What they expect to be installed
- PostHog47 of 333 in 30 files
- GA435 of 333 in 23 files
- Mixpanel30 of 333 in 19 files
- Segment22 of 333 in 11 files
- Google Tag Manager22 of 333 in 15 files
- Amplitude19 of 333 in 16 files
- LaunchDarkly16 of 333 in 8 files
- gtag.js15 of 333 in 10 files
- Optimizely15 of 333 in 7 files
- VWO15 of 333 in 7 files
What they ask it to produce
- Tracking plan document20 of 333 in 13 filesalso worded as Tracking plan; tracking plan document in markdown
- Documented test record with hypothesis, variants, results, decision18 of 333 in 9 filesalso worded as Test documentation with hypothesis, variants, results, and decision; test documentation with variants, results, and learnings
- Health score model16 of 333 in 7 filesalso worded as Customer health scoring model; weighted health score model
- Dunning email sequence12 of 333 in 3 filesalso worded as Four-email dunning sequence
- Cancel flow with survey and save offers9 of 333 in 3 filesalso worded as Cancel flow design with exit survey and offers; cancel flow design with survey and save offers
- Event taxonomy table9 of 333 in 8 filesalso worded as Event taxonomy document; An event taxonomy reference file
- Exit survey11 of 333 in 2 filesalso worded as Exit survey with reason options
- UTM parameter spreadsheet8 of 333 in 5 filesalso worded as UTM naming spreadsheet
When Analytics & metrics authors say to reach for one
The situations these authors wrote into their own files, counted out of the same 333 authors, with the skills that name each one
- User wants to plan, design, or implement an A/B test22 of 333 in 14 files
- User wants to reduce churn or improve retention14 of 333 in 5 files
- Churn prevention
- Marketing churn prevention
- and 17 more on this shelf
- User wants to build a cancellation flow12 of 333 in 3 files
- Churn prevention
- Marketing churn prevention
- and 17 more on this shelf
- User wants to recover failed payments12 of 333 in 3 files
- Churn prevention
- Marketing churn prevention
- and 17 more on this shelf
- User mentions Google Analytics or GA412 of 333
- Google analytics
- and 1 more on this shelf
- User asks about setting up analytics12 of 333
- Tracking plan
- Analytics profile setup
- Linkedin analytics interpreter
- Posthog
- and 1 more on this shelf
- User wants to set up, improve, or audit analytics tracking11 of 333 in 6 files
How Analytics & metrics skills are built
1,528 skill directories by 363 authors, read from their repositories’ own file trees 2026-08-05
The middle bundle among those shipping files is 3 files, 20.9 KB beside SKILL.md
Counted by distinct author, same as above, so one author publishing forty template copies counts once. SKILL.md itself is not counted as a file, so a single-file skill is one where that file is the whole skill.
The shape
- SKILL.md is the whole skill149 of 363 authors, 920 of 1,528 skills
- files ship beside it214 of 363 authors, 608 of 1,528 skills
- executable scripts ship inside76 of 363 authors, 201 of 1,528 skills
The folders they converge on
- references/138 of 363 authors, 405 of 1,528 skills
- scripts/60 of 363 authors, 169 of 1,528 skills
- agents/34 of 363 authors, 102 of 1,528 skills
- evals/29 of 363 authors, 64 of 1,528 skills
- assets/22 of 363 authors, 36 of 1,528 skills
- examples/15 of 363 authors, 27 of 1,528 skills
PostHog/posthog/io.github.PostHog/mcp MCP server
no license37,662★ repoOfficial PostHog MCP Server for product analytics, feature flags, experiments, and more.
Kaelio/ktx/packages/cli/src/skills/analytics Skill
1,540★ repoktx is an executable context layer for data and analytics agents 🐙 Allow Claude Code, Codex, or other AI agents to query analytical databases accurately and with full context of your company
indranilbanerjee/digital-marketing-pro/skills/ab-test-plan Skill
734★ repoOpen-source AI marketing plugin for agencies & in-house teams — 158 skills, 25 specialist agents, 12-Part Strategy Flow, Cowork team-persistent, EU AI Act Article 50 ready, 6-platform AEO/GEO incl. Google AI Mode. Installs on Claude Code, Cowork, Codex, Cursor, Copilot CLI, Antigravity. MIT-licensed.
heliocosta-dev/revenue-centric-design Skill
no license455★Product-design, conversion & behavioral-science principles for SaaS
yanhua1010/self-media-content-workflow/skills/self-media-content-analytics Skill
365★ repo通用、模块化的自媒体内容生产与经营 Skills / A modular, tool-agnostic self-media content skill suite
surendranb/google-analytics-mcp/io.github.surendranb/google-analytics-mcp MCP server
235★ repoGA4 MCP server for AI agents: schema discovery, server-side aggregation, analysis-ready defaults.
jtrackingai/analytics-tracking-automation Skill
133★AI-powered GA4 + GTM event tracking — automates site analysis, event schema, GTM sync, preview verification, and publishing. Works with Cursor, Codex, and any AI agent.
ralfbecher/orionbelt-analytics/io.github.ralfbecher/orionbelt-analytics MCP server
no license45★ repoOntology-based MCP server for database schema analysis and RDF/OWL ontology generation
Agronomic experiment design starter
ma-compbio-lab/SkillFoundry/skills/agriculture-food-and-plant-science/agronomic-experiment-design-starter Skill
36★ repoA framework for discovering, compiling, and validating reusable skills for scientific agents.
TabooHarmony/roblox-brain/skills/roblox-analytics Skill
31★ repoGive your AI coding agent a Roblox brain. Curated skills for Roblox Studio development.
inbharatai/claude-skills/skills/ab-test-designer Skill
28★ repoCurated Claude and Codex skill collection for local AI workflows, automation, research, and product-building.
galyarderlabs/galyarder-framework/integrations/antigravity/ab-test-setup Skill
20★ repoThe framework that powers your Agentic Company
eugenepyvovarov/mcpbundler-agent-skills-marketplace/ab-test-setup Skill
12★ repoagent skills marketplace for mcp bundler(can be used with other ai tools with support of agent skills markeplaces). some skills are mine, also borrowed skills(credited to authors)
hartmut-ux/ai-marketing-team/skills/analytics-reporting/.claude/skills/analytics-reporting Skill
11★ repo11 AI marketing skills for Kimi, Claude & Codex. Content strategy, PR, internal comms, change management, analytics & operations for SMEs and purpose-driven organisations.
alphaparkinc/claim-merchant-skill Skill
no license9★GenPark skill: Run pay-per-acquisition social drops, Plaid card-linked verification, and Venmo rewards payouts using Claim Merchants.
clamp-sh/analytics-skills/skills/analytics-diagnostic-method Skill
8★ repoSkills for AI agents to read web analytics like a senior analyst: diagnose traffic, judge channels, read funnels, declare typed events, and read A/B tests. Tool-maps for Amplitude, Clamp, GA4, Mixpanel, and PostHog.
DMARKOFF — DMARC, SPF & DKIM Analytics
dmarcoff/mcp/com.dmarkoff/mcp MCP server
no license8★ repoDMARC analytics for AI assistants — domain health, SPF/DKIM records, compliance stats, anomalies.
embeddedlayers/mcp-analytics/ai.mcpanalytics/analytics MCP server
7★ repoThe statistical analyst in your AI chat — validated, citable, re-runnable analysis of your data.
Linkedin analytics interpreter
TaplioOfficial/taplio-linkedin-claude-skills/skills/linkedin-analytics-interpreter Skill
5★ repoTaplio LinkedIn Cloud Skills: 17 free Claude Skills to write, plan, and grow your LinkedIn presence. Post writing, hooks, carousels, strategy, content calendars, and analytics, powered by the Taplio MCP.
Sudhakaran88/solopreneur-skills/skills/ab-test-setup Skill
5★ repo42 opinionated, research-backed marketing & growth skills for solopreneurs — as a Claude Code plugin.
hardness1020/claude-skills-management/skills/skills-analytics-dashboard Skill
5★ repoTrack, score, and manage your Claude Code skills across all projects with a local analytics dashboard.
thaolst/ai-growth-agents-for-marketers/skills/ab-test-analyzer Skill
5★ repoAI agents for growth marketing — built from real fintech campaigns. Prompts + Python.
Philidor DeFi Vault Risk Analytics
Philidor-Labs/philidor-mcp/io.philidor/defi-vaults MCP server
5★ repoSearch 700+ DeFi vaults, compare risk scores, analyze protocols. No API key needed.
celticht32/Couchbase-Skills-for-Claude.ai/skills/couchbase-analytics/cb-analytics-admin Skill
4★ repoThis is a collection of skills I have created for Couchbase for Claude.ai
fsbtactic-code/marketing-brain-skill/skills/marketing-brain Skill
4★ repoPortable marketing second brain for Codex, Claude Code, and Agent Skills with 502 sources for strategy, SMM, content, growth, CRO, and buyer psychology.
markdavidgan/apple-dev-skills/platforms/claude/skills/app-analytics Skill
3★ repoApple platform development skills for Claude Code, Cursor, Kimi Code, Antigravity, Codex CLI, and Agy.
m-binimran/creator-pack/skills/analytics-review Skill
3★ repoClaude Code pack for Instagram & Facebook content creators: FTC/Meta disclosure, copyright, brand-safety & no-fabricated-stats guardrails + skills for Reels/carousels/Stories/captions/repurposing/sponsorships, loops & review agents. Not legal advice.
jperrello/C0BALT_CUT/.claude/skills/analytics-feedback Skill
no license2★ repoInvestigation on using Claude Code to automatically generate profitable YouTube videos.
moses607/socialforge/skills/analytics-interpreter Skill
2★ repoSocialForge — 17 open-source Claude skills that turn any capable model into an AI social-media growth agency: competitor analysis, hooks, viral scripts, repurposing, trends, engagement, and an orchestrator. MIT.
Google search ads analytics docs
bsisduck/google-search-ads-analytics-docs/.claude/skills/google-search-ads-analytics-docs Skill
no license2★ repoOfficial Google docs (Search/SEO, Search Console, Ads, GA4) as a validated local knowledge base (English) + two Claude Code skills: cited retrieval and a multi-agent SEO audit. Reproducible, measured (92% recall@5).
Aidress skill find verified analytics reporting agent
Aidress-ai/aidress-skill-find-verified-analytics-reporting-agent Skill
2★Find a Verified Analytics Reporting Agent. Agent discovery, trust verification, and capability routing powered by Aidress — the coordination registry for autonomous AI agents. Use for data agent discovery, trust verification, and capability routing — via Aidress (https://api.aidress.ai).
Makiya1202/ai-agents-skills/skills/analytics-metrics Skill
no license2★ repo🧠 Enhance AI agents with a collection of skills for improved coding assistance, enabling efficient and production-ready solutions.
Linkedin analytics interpreter
TaplioOfficial/taplio-linkedin-plugin/skills/linkedin-analytics-interpreter Skill
2★ repoClaude Code plugin: 17 Claude Skills for LinkedIn bundled with the Taplio MCP. Write, plan, and grow your LinkedIn presence from Claude, on your real voice and analytics.
zavora-ai/skill-analytics-reporting Skill
no license2★Revenue intelligence skill for AI agents — metrics, funnels, anomaly detection, forecasting, and dashboards via mcp-analytics (28 tools)
agenkin/telemetrydeck-analytics/skills/analytics Skill
2★ repoTelemetryDeck product analytics for Claude Code — CLI + slash commands + progressive-disclosure TQL docs.
meirdick/growth-product-context/skills/growth-product-context Skill
2★ repoFree Laravel Boost skill for journey discovery. Scans routes, controllers & models to map AARRR user journeys.
Turbo-Puffin/measure-mcp-server/io.github.meetclawdius/measure-events MCP server
2★ repoPrivacy-first web analytics. Query pageviews, referrers, trends, and AI insights.
openpulsechain/public/io.github.openpulsechain/analytics MCP server
2★ repoPulseChain analytics: 28 tools — safety scores, signals, whale alerts, pair analytics, AML.
brian-a-au/bau-claude-skills/skills/adobe-analytics-concepts Skill
no license1★ repoPersonal collection of Claude Code skills
MARUCIE/openclaw-foundry/web/public/packs/ab-test-analyst/skills/pack-maturity/delivery-review Skill
1★ repoThe curated AI Agent skill marketplace — 37K+ vetted skills, S/A/B/C ratings, deploy anywhere
t0ddharris/compound-marketing/.claude/skills/ab-test-setup Skill
no license1★ repoScale your marketing without sacrificing quality.
MehdiBatExpert/MarketingPilot/commands/mktg-churn-prevent Skill
1★ repo10 Claude skills for B2B solo founder marketing - copy, conversion, launch, retention
offensive-tarichagranulosa259/seo-data Skill
1★Connect Claude to Google Search Console, Google Analytics 4, and Bing Webmaster Tools to analyze actual site data and performance metrics.
getformo/cli/skills/formo-analytics Skill
1★ repoFormo CLI and agent skill for product analytics, onchain data, and wallet intelligence.
whoisdev/unchurn-skills/skills/fighting-churn Skill
1★ repoAgent skills for Stripe-native SaaS founders fighting churn — by Unchurn (https://unchurn.dev)
IrfanSadiqRahat/constellation/agents/ab-test-engineer Skill
no license1★ repo200 role-specific AI agents across 20 teams with typed artifact pipelines, 14 methodology skills, and 15 pre-baked team formations. The virtual engineering org for Claude Code, Cursor, Codex CLI.
agent-k-labs/shipping-skills/skills/analytics-setup Skill
1★ repoAI agent skills for everything after the AI builds your app — launch, get users, grow. Works with Claude Code, Cursor, Windsurf.
m-binimran/marketing-pack/skills/ab-test Skill
1★ repoFull-stack Claude Code pack for marketers: FTC claim-substantiation, CAN-SPAM, deliverability, privacy & no-fabricated-metrics guardrails + skills for positioning, ad copy, landing pages, email, SEO, A/B tests & analytics, loops & review agents. Not legal advice.
carloslimaborges/wondel-auto-router/wondel-auto-router Skill
1★ repoMeta-skill that auto-routes tasks to wondel.ai framework skills — 11-lens multifocal baseline for engineering
lordbasilaiassistant-sudo/mcp-stripe-analytics/io.github.lordbasilaiassistant-sudo/stripe-analytics MCP server
no license1★ repoStripe analytics — revenue, customers, subscriptions, refunds, churn from Claude.
retain-so/mcp-server/io.github.retain-so/mcp-server MCP server
1★ repoModel Context Protocol server for Retain: let AI agents query churn risk and act on retention.
keypup-io/engineering-analytics-mcp-server/io.keypup/engineering-analytics MCP server
no license1★ repoGenerate answers & visualizations from your engineering data to track software development health.
engageable-tech/engageable-oss/tech.engageable/analytics MCP server
no license1★ repoUnified analytics MCP server for GA4, Mixpanel, and PostHog.
sarbak/strategy-skills/analytics-review Skill
0★ repoStrategy, SEO/GEO, and analytics skills for Claude Code — by Emotion Machine (emotionmachine.com)
SecureIVAI/my-claude-skills/customer-success-manager Skill
0★ repoReady-to-use Claude Code skills for customer success analytics, DISC profiling, leadership coaching, project scheduling, prompt engineering, and more. Download a ZIP, drop it into your Claude project, and go.
puukis/lstack/skills/analytics Skill
0★ repoA personal Claude Code environment. Persistent memory, loop detection, 15 skills, and lifecycle hooks. macOS, Linux, and Windows.
iker-gonzalez/antwork-skills/skills/antwork-analytics Skill
0★ repoAgent Skills for the Antwork MCP connector
vermapragya/analytics-skill/skills/ab-test-analysis Skill
0★ repoSkills library for product data scientists working with Claude
SkillMedev/saas-growth-stack/skills/churn-reduction Skill
0★ repoAcquisition, activation, retention — the full SaaS growth toolkit.
SkillMedev/performance-marketing/skills/ab-test-analyzer Skill
0★ repoAudit, test, and scale paid channels with rigorous, data-driven playbooks.