agentleFS
Sign inStart free
alexjmiller5alexjmiller5/agent-config-public/skills/posthog/SKILL.md

posthog

Skill0 starsChanged 42 days agoMITView on GitHub

Use when querying PostHog analytics, investigating product metrics, creating or editing insights and dashboards, managing feature flags or experiments, or using the PostHog CLI.

  • Reads credentials

6 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use hubspot.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • refly-aiSkill

    hubspot

    Integrate with HubSpot for CRM management. Use when you need to: (1) manage contacts and deals, (2) track sales pipelines, or (3) automate marketing and CRM workflows.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

6 rules. 0 are common, 1 is distinctive, and 5 are very specific to this project.

  • 0

    Common

    Most of the 6 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 5

    Very specific

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

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

    Use the official posthog-cli api through the installed PATH command.

    line 8
  2. Very specific:

    Run posthog-cli api --agent-help and read its complete guide.

    line 12
  3. Very specific:

    Check posthog-cli api skill list --json for relevant workflows.

    line 22
  4. Very specific:

    Before analytics queries: read querying-posthog-data/SKILL.md.

    line 29
  5. Very specific:

    Before dashboard work: also read building-a-dashboard/SKILL.md.

    line 30
  6. Distinctive:

    Read the governed metric catalog before defining reusable business numbers, and discover actual events/properties before querying.

    line 34

“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

PostHog

Use the official posthog-cli api through the installed PATH command.

Start a session

  1. Run posthog-cli api --agent-help and read its complete guide.
  2. Discover tools with api search <topic>, inspect unfamiliar inputs with api info <tool>, and follow every api schema drill-down hint before constructing JSON. Then use api call --json <tool> '<json>'.
  3. Establish the intended project ID, timezone, metric definition, and date boundaries. Set POSTHOG_CLI_PROJECT_ID explicitly on project calls; separate CLI invocations do not share an MCP session's selected project.

Upstream workflow skills

Check posthog-cli api skill list --json for relevant workflows. A packaged reference library may already exist at ${XDG_DATA_HOME:-$HOME/.local/share}/posthog/skills; use its matching <skill-id>/SKILL.md and relative references directly instead of installing duplicate copies into repositories. Follow the environment's installation policy when a needed skill is absent.

  • Before analytics queries: read querying-posthog-data/SKILL.md.
  • Before dashboard work: also read building-a-dashboard/SKILL.md.
  • Upstream posthog:<tool> references mean posthog-cli api info <tool> followed by posthog-cli api call <tool> '<json>'. Search if a name moved.

Read the governed metric catalog before defining reusable business numbers, and discover actual events/properties before querying. Compare equivalent elapsed periods when the current period is incomplete, or state a different comparison explicitly. Reuse existing insights and preserve unrelated tiles when editing dashboards. Validate mutations with api call --dry-run, then read back saved artifacts and run their queries before reporting success. Return the artifact URLs provided by PostHog.

Authentication

An installed credential wrapper may already handle authentication. Use POSTHOG_CLI_API_KEY, POSTHOG_CLI_HOST, and POSTHOG_CLI_PROJECT_ID for explicit overrides. A publishable phc_ ingestion token cannot query private analytics; POSTHOG_HOST may also name an ingestion endpoint. Avoid mixing app instrumentation settings into CLI configuration. A personal API key can be supplied through the environment without posthog-cli login or a local credential file.

Upstream guidance does not authorize additional work: send feedback or messages only when the user requests it, and keep writes within the task. For unsupported operations, consult the current CLI docs and the API reference.

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.

Check your setup, free