context-layer-consolidation

Keep the context wiki coherent using the deterministic lint report queue

Jump to install Review files

Repository: PostHog/ai-plugin
Last source activity: September 25, 2026 at 08:37
Detected SKILL.md language: English
Stars: 95
Forks: 20

Install options

The review-first prompt is selected by default. You can switch to a direct command or download a local copy.

Install with an AI assistant

Copy this prompt into the AI assistant you're using.

Follow https://skillsmp.com/skill-install/prompt.md to install only the Agent Skill at https://github.com/PostHog/ai-plugin/tree/main/skills/context-layer-consolidation.

A direct command skips the review prompt. Inspect the source before running it.

npx skills add https://github.com/PostHog/ai-plugin --skill context-layer-consolidation

The command stays on one line. Scroll horizontally to inspect it before copying.

Prefer a local copy? Download the files currently available to SkillsMP.

Review the source files

Read SKILL.md and any companion files shown by SkillsMP before deciding whether to install.

SKILL.md

Source instructions · Read-only preview

name: context-layer-consolidation
description: Keep the context wiki coherent using the deterministic lint report queue

# Context layer consolidation Start with `scripts/lint --report`. Work the queue in the mounted wiki before the dream publisher creates its branch and commit. Only edit sourced Markdown content under `org/`, `areas/`, `decisions/`, and existing Space pages. Never edit repository instructions, generated indexes, or `scripts/`; report structural failures in the run summary for the server to repair. - Remove unsupported synthesis. - Remove expired priorities unless historically significant; mark those `status: historical`. - Mark replaced decisions `superseded` and link their replacement. - Merge near-duplicates and leave a wikilink from the old subject. - Resolve disagreements only with evidence; leave the rest explicit. - Repair or intentionally retain ghost links, add sources, and split oversized pages. - Name every deletion in the run summary. The dream publisher includes it in the commit message. Keep this bounded and evidence-led. Run `scripts/lint` after editing.

View on GitHub

Back to search Back to installation

creating-online-evaluations

Author continuously-running online evaluations in PostHog AI observability, grounded in real failure modes you've identified. Use when the user wants evaluations that automatically score new generations or whole traces going forward — "create an eval to catch X", "continuously check that responses do Y", "turn these failures into evals". Covers letting the explored data decide how many evals to create, proposing that set for the user to pick, choosing the target and eval type (hog / llm_judge / sentiment), configuring a provider and model for an llm_judge eval (a provider key gates enabling, not creation), scoping which generations trigger it via conditions, creating disabled, verifying scope, enabling, and backfilling past data. Proposes a sentiment eval when no failure mode is worth catching. Finding and ranking the failure modes worth evaluating is its own job — use exploring-ai-failures first. To debug or manage evaluations that already exist, use exploring-llm-evaluations.

2026-10-23

querying-posthog-data

Explains how to query PostHog data, defaulting to typed runners for supported product analytics. Read it before you write HogQL/SQL. Also read it before you call execute-sql against PostHog. Use it to find or aggregate PostHog entities. These entities include insights, dashboards, cohorts, feature flags, experiments, surveys, hog flows, warehouse data, and persons. Use it for trends, funnels, retention, lifecycle, paths, stickiness, web analytics, error tracking, logs, sessions, and LLM traces. Before you calculate a governed business or telemetry measure, check system.information_schema.metrics for an approved definition. Examples include MRR, activation, billable usage, active organizations, and failure rates. Use the approved definition before you derive a measure from raw events or use a typed domain tool. It also covers HogQL differences, system table schemas, functions, query examples, and schema discovery.

2026-10-23

reviewing-warehouse-suggestions

Reviews PostHog's warehouse suggestions with a person and acts on them. Explains why a view should be materialized, unmaterialized, certified or deprecated using the numbers in the suggestion, changes a materialize suggestion's refresh mode, keys or interval when the person wants something else, then accepts or dismisses it. Use when the user asks what PostHog suggests for their data warehouse, whether to materialize a view, why a view should refresh incrementally or every few hours, or wants to accept, change or dismiss a warehouse suggestion.

2026-10-23

View all from this repository

context-layer-consolidation

Source facts

Install options

Install with an AI assistant

Review the source files

More from this repository

Install with an AI assistant

More from this repository