agentleFS
Layneformalized225Layneformalized225/ai-cofounder/skills/posthog-analytics/SKILL.md

posthog-analytics

Skill1 starsChanged 8 months agoMITView on GitHub

Raw PostHog data queries via MCP — event catalog, query recipes, dashboards, funnels, experiments. Use for specific data questions. For CEO-level metric interpretation and frameworks, use metrics-briefing instead.

7 other projects use a version of this, 1 of them edited.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

4 rules. 0 are common, 3 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 7 edited versions we read keep these.

  • 3

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

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

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

    Use exec to call: mcporter call posthog.<tool-name> <params>

    line 21
  2. Distinctive:

    If you have multiple projects:

    line 111
  3. Distinctive:

    Always segment by target cohort when possible

    line 153
  4. Distinctive:

    Follow output preferences from USER.md.

    line 155

“Common” is measured: kept by at least 6 in 10 of the 7 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

PostHog Analytics (via mcporter)

Direct access to PostHog data. Requires PostHog account + mcporter setup (see docs/adding-tools.md).

Projects

Configure your PostHog projects here:

NameIDUse
app[YOUR_PROJECT_ID]Main product analytics (DEFAULT)

Tool

Use exec to call: mcporter call posthog.<tool-name> <params>

Event Catalog

Configure your event catalog here. Common SaaS events to track:

Journey & Funnel Events

EventDescriptionKey Properties
signup_startedUser begins signupsource, utm_*
signup_completedUser completes signupmethod
activation_completedUser reaches key activation milestonetimeSincePrevious
feature_usedCore feature usagefeatureName, count

Common Funnel Stages

signup -> email_confirmed -> onboarding_started
-> first_value_moment -> return_visit
-> regular_usage -> power_user
-> team_invite

Customize this to match your product's activation funnel.

Person Properties (B2B-relevant)

PropertyTypeUse
$initial_utm_sourceStringFirst-touch attribution
$initial_utm_mediumStringFirst-touch attribution
$initial_utm_campaignStringFirst-touch attribution
$initial_referring_domainStringFirst-touch attribution
organizationIdStringB2B account grouping

Key Tools

Discovery

mcporter call posthog.event-definitions-list
mcporter call posthog.event-definitions-list q="signup"
mcporter call posthog.properties-list type=event eventName="your_event"
mcporter call posthog.properties-list type=person
mcporter call posthog.entity-search query="activation"

Natural Language Queries (recommended)

mcporter call posthog.query-generate-hogql-from-question question="..."

Best for:

  • Complex breakdowns by multiple properties
  • Account-level aggregations
  • Attribution analysis ($initial_* properties)
  • Time-between-events calculations

Saved Insights

mcporter call posthog.insights-get-all
mcporter call posthog.insight-get insightId="123"
mcporter call posthog.insight-query insightId="123"

Dashboards

mcporter call posthog.dashboards-get-all
mcporter call posthog.dashboard-get dashboardId=YOUR_DASHBOARD_ID

Experiments & Feature Flags

mcporter call posthog.experiment-get-all
mcporter call posthog.experiment-results-get experimentId=123 refresh=false
mcporter call posthog.feature-flag-get-all
mcporter call posthog.feature-flag-get-definition flagKey="my-flag"

Errors

mcporter call posthog.list-errors orderBy=occurrences dateFrom="2026-03-08T00:00:00Z"
mcporter call posthog.error-details issueId="uuid-here"

Surveys

mcporter call posthog.surveys-get-all
mcporter call posthog.survey-stats survey_id="uuid"

Switching Projects

If you have multiple projects:

mcporter call posthog.switch-project projectId=YOUR_OTHER_PROJECT_ID
# Switch back after:
mcporter call posthog.switch-project projectId=YOUR_DEFAULT_PROJECT_ID

Query Recipes

CEO Morning Briefing

# DAU yesterday
mcporter call posthog.query-generate-hogql-from-question question="How many unique users had events yesterday?"

# New signups yesterday
mcporter call posthog.query-generate-hogql-from-question question="How many signup events happened yesterday?"

# Funnel progression yesterday
mcporter call posthog.query-generate-hogql-from-question question="Show funnel stage transitions from yesterday, count by stage"

Weekly CEO Dashboard

# Funnel health
mcporter call posthog.query-generate-hogql-from-question question="Show funnel events in the last 7 days, count unique users for each stage transition"

# Active companies
mcporter call posthog.query-generate-hogql-from-question question="How many distinct organizationId values had any events in the last 7 days?"

# TTFV (time to first value)
mcporter call posthog.query-generate-hogql-from-question question="What is the average time from signup to first activation event, last 30 days?"

# Source attribution
mcporter call posthog.query-generate-hogql-from-question question="For activated users last 30 days, what are the top initial UTM sources?"

Output Format

Present results concisely:

  • Key number + trend (vs previous period)
  • Flag anomalies
  • Link to metric class (Primary CEO / Secondary / B2B bridge)
  • Always segment by target cohort when possible

Follow output preferences from USER.md.

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.