posthog/ai-plugin

choosing-trend-or-slope-view

Clarify how to visualize change over a time range before building a trend.

Ver código-fonte

Como usar

  1. Copie o comando e verifique o pacote antes de instalar no seu ambiente de agente.
  2. Consulte no original as ferramentas, credenciais e ambientes necessários.
  3. Descreva os dados de entrada e a entrega esperada; confira a saída com as fontes.
npx skills add https://github.com/posthog/ai-plugin --skill choosing-trend-or-slope-view

Antes de começar

  • A instalação não inclui assinatura de modelo, franquia API ou acesso aos seus arquivos.
  • Estrelas e instalações indicam atividade, não um teste independente de qualidade ou segurança.
Documento original do Skill

Renderizado do repositório de origem, preservando títulos, exemplos, código, tabelas, links e imagens.

Choosing a trend line vs a slope view

"How did X change between A and B?" is ambiguous. Two charts answer two different questions, so clarify before you build unless the user already named one:

  • Change over time (line) — the value at every interval across the range.

Shows the path: dips, spikes, when it moved. This is the default trend.

  • Start vs end (slope) — only the first and last point, one line per series

connecting them. Shows the net change and, across many series, which rose, which fell, and any rank flips — without the noise of the path between.

When the request could be either, ask a short either/or, e.g.:

Do you want to see how it moved across the whole period (a line chart), or just the change from the start to the end (a slope chart)?

If the user clearly wants one — "just tell me how much it grew start to end" → slope; "show me the trend / when did it spike" → line — skip the question and build it.

How to render each

Both come from the same TrendsQuery over the same date range — the slope is that series collapsed to its first and last point, not a different query.

Change over time → line

Default trends behavior. Create or run a TrendsQuery and leave trendsFilter.display as ActionsLineGraph (the default, "change over time"):

json
{
  "kind": "TrendsQuery",
  "series": [{ "kind": "EventsNode", "event": "$pageview", "math": "total" }],
  "dateRange": { "date_from": "2025-01-01", "date_to": "2025-03-31" },
  "trendsFilter": { "display": "ActionsLineGraph" }
}

Start vs end → slope

Run the trend with posthog:query-trends. The result card Max renders has a Line / Bar / Slope view toggle — switch it to Slope to show each series as a single line from its first to its last point, with the per-series change in the legend. Tell the user they can flip to the Slope view on the result.

The slope view is best for a clean before→after comparison, especially with several series/categories whose relative movement matters. Pick a date range whose two ends are the points you want compared (the slope uses the first and last interval).

Important limits

  • Two surfaces, one computation. Both the inline slope (Max's query-trends

result card) and the saved-insight slope (ChartDisplayType.SlopeGraph) show the same thing: the first interval's value vs the last interval's value, at the chosen group-by interval. The grouping defines the slope - group by month to compare the first vs last month, by day for the first vs last day. Use the inline view for a quick before-and-after on a result you're already looking at; use the saved display to persist it on a dashboard. A still-accumulating final period is shown as-is with a dashed connector, the same affordance the line chart uses for an incomplete tail.

  • For period-over-period on a single series (this month vs last), a line with

compareFilter: { "compare": true } overlays the two periods; a slope is the better fit when comparing the endpoints of many series at once.

Relacionados por tarefa

do mesmo repositório

Mais Skills

Todos os Skills
posthog
Oficial

exploring-llm-costs

Investigate LLM spend in PostHog — total cost over time, cost by model, provider, user, trace, or custom dimension, token and cache-hit economics, and cost regressions. Use when the user asks "how much are we spending on LLMs?", "which model / user / feature is most expensive?", "why did cost spike?", wants to build a cost dashboard or alert, or pastes a trace URL and asks about its cost.

Instalações / 1h
2
GitHub Stars
98
Atualizado
6 de nov.
posthog
Oficial

exploring-llm-traces

Debug and inspect LLM/AI agent traces using PostHog's MCP tools. Use when the user pastes a trace or session URL (e.g. /ai-observability/traces/ or /ai-observability/sessions/ ), asks to debug a trace, figure out what went wrong, check if an agent used a tool correctly, verify context/files were surfaced, inspect subagent behavior, investigate LLM decisions, or analyze token usage and costs. Also use when raw SQL/HogQL against events.properties.$aiinput / $aioutputchoices returns empty — message

Instalações / 1h
2
GitHub Stars
98
Atualizado
6 de nov.
posthog
Oficial

instrument-integration

Add PostHog SDK integration to your application. Use when setting up PostHog for the first time or reviewing PRs that need PostHog initialization. Covers SDK installation, provider setup, and basic configuration for any framework.

Instalações / 1h
2
GitHub Stars
98
Atualizado
6 de nov.
posthog
Oficial

investigating-error-issue

Investigates a single PostHog error tracking issue end-to-end. Use when the user provides an issue ID or pastes an issue URL (/error-tracking/ ) and wants to understand the error — who it affects, what triggers it, when it started, whether it correlates with a release, browser, OS, or feature flag, and what the next step should be. Pulls aggregated metrics, sample exception events, segment breakdowns, linked replays, and synthesizes a hypothesis-grade summary in one pass.

Instalações / 1h
2
GitHub Stars
98
Atualizado
6 de nov.