posthog/ai-plugin

context-layer-health-check

Semantic review of context wiki quality after deterministic consolidation

Quelltext ansehen

Verwendung

  1. Installationsbefehl kopieren und das Quellpaket vor der Installation in der eigenen Agentenumgebung prüfen.
  2. Benötigte Werkzeuge, Zugangsdaten und Hosts im Original prüfen.
  3. Eingabe und gewünschtes Ergebnis beschreiben und die Ausgabe mit den Quellen abgleichen.
npx skills add https://github.com/posthog/ai-plugin --skill context-layer-health-check

Vor dem Start

  • Die Installation umfasst weder Modellabo noch API-Kontingent oder Dateizugriffsrechte.
  • Sterne und Installationen zeigen Aktivität, keine unabhängige Qualitäts- oder Sicherheitsprüfung.
Originales Skill-Dokument

Aus dem Quell-Repository gerendert; Überschriften, Beispiele, Code, Tabellen, Links und Bilder bleiben erhalten.

Context layer health check

Read recent wiki-miss: lines from git log --merges and use them as the priority signal. Review for contradictory active claims, unsupported conclusions, repeated low-value activity, stale priorities the report cannot detect, near-duplicate subjects, concepts without an owning page, and sources worth backfilling.

Fix what evidence supports. Leave unresolved conflicts as **Disagreement:** markers and record remaining work in the run summary. Finish with scripts/lint and scripts/lint --report.

Do not edit AGENTS.md, CLAUDE.md, generated indexes, scripts/, or Space paths. The server owns wiki structure and tooling.

Verwandte Aufgaben

aus demselben Repository

Weitere Skills

Alle Skills
posthog
Offiziell

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.

Installationen / 1h
2
GitHub Stars
98
Aktualisiert
6. Nov.
posthog
Offiziell

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

Installationen / 1h
2
GitHub Stars
98
Aktualisiert
6. Nov.
posthog
Offiziell

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.

Installationen / 1h
2
GitHub Stars
98
Aktualisiert
6. Nov.
posthog
Offiziell

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.

Installationen / 1h
2
GitHub Stars
98
Aktualisiert
6. Nov.