- writing-pr-descriptions
Shapes a PR body into something a reviewer understands at a glance. Use ALWAYS before writing or editing a PR description, before `gh pr create` or `gh pr edit --body`, and when asked to improve an existing description. Puts the effect a person sees in the first line and the mechanism under it, routes each remaining fact to the form that carries it fastest (bullet, table, diagram, screenshot, collapsed block), cuts everything a reviewer does not need, then holds what survives to a checkable shape: one fact per bullet, sentences under 25 words, active voice, no idioms. Makes the body stand alone, so a reader who opens no files still knows why the PR is necessary and what it does, sizes the body to the change so a small PR reads as small, and makes every claim either linked to its evidence or labeled as unchecked. Ends with a scan test over the title and the first lines of Problem and Changes. Not for commit messages (see AGENTS.md, "Commit types") or user-facing product copy (see `/writing-user-facing-copy`).
Updated
- authoring-data-quality-checks
Adds and runs data quality checks (dbt-test style assertions) on a project's warehouse tables and saved-query views, and HogQL catalog metrics: not-null, uniqueness, accepted values, referential integrity, row-count bounds, freshness, and custom HogQL. Metrics support custom SQL checks only. Use when asked to test a model, validate a view, check for nulls or duplicates, add data quality checks, find out why a number looks wrong, or judge whether a warehouse table is trustworthy before using it in an analysis. To describe what data *means* (metrics, certifications, joins), see setting-up-data-catalog instead. Trigger terms: data quality, data test, dbt test, not null check, uniqueness check, freshness check, referential integrity, row count check, validate model, is this table trustworthy.
Updated
- authoring-scouts
How to author, edit, and adapt PostHog Signals scouts — the scheduled agents that scan a project and file what they find. Use to customize a canonical scout (narrow its scope, retune thresholds, add disqualifiers), tweak a scout's schedule or dry-run posture, write a new scout for a surface the fleet doesn't cover, build a measurement scout that records structured output (an LLM-judge scoring a sample on a schedule — a custom metric no query can compute), or steer a scout without editing it by leaving it a note. Covers the scout SKILL.md anatomy, the report contract, the structured-output channel, the dedupe + scratchpad-memory conventions, scout notes, the per-team skills-store path vs the canonical in-repo path, and the test loop. Trigger on "write/edit/customize a signals scout", "new scout for X", "tune my scout schedule", "make a scout that watches <event>", "score/judge/measure X with a scout", "structured output from a scout", "scout output to Slack", "leave a note for / give feedback to a scout".
Updated
- working-with-scouts
How to get real jobs done with PostHog Signals scouts — the scheduled agents that watch a project and write reports into the Signals inbox — and how to steer and customize the fleet over time. Use when a user wants to delegate a watching job ("have a scout keep an eye on X", "tell me if Y spikes"), wants a recurring judged metric from a scout ("score X on a schedule", "measure quality of Y"), wants to know which scout covers a surface, asks how to act on what scouts report, complains the fleet is noisy or quiet, or wants the fleet to get smarter over time (feedback loops, calibration, promoting one-off steers into policy). The operating manual for the human–scout working relationship; routes to `authoring-scouts` for write mechanics, `exploring-scouts` for run observability, and `inbox-exploration` for report triage. Trigger on "work with my scouts", "get more out of scouts", "have a scout watch X", "what do I do with this scout report", "calibrate/review my scout fleet".
Updated
- signals-scout-logs
Signals scout for PostHog logs. Watches for emerging and rate-shifted message patterns, volume bursts, severity-distribution shifts, service silence, and trace-correlated bursts.
Updated
- signals-scout-ai-observability
Signals scout for PostHog AI observability. Watches LLM traces for cost, latency, error, volume, and eval-performance regressions.
Updated
Curated setups
Skills grouped for one workflow and installable with one command.