Name: signals-scout-data-warehouse
Rating: 59.2 (1 reviews)
Author: PostHog

signals-scout-data-warehouse

Focused Signals scout for PostHog projects importing external data into the warehouse. Watches the import side — external data sources, per-table sync schemas, webhook push channels, and materialized views — for the moments an import quietly stops keeping its promise: a source connection in Error, a schema Failed or stuck Running, silent staleness behind a green Completed status, a broken webhook push channel, a row-volume cliff, and failed materialized views. When armed imports are healthy, switches to the optimization lane: reads the per-team `query_log` table for recurring, multi-user query time and read-bytes concentrated on warehouse tables or repeated query shapes, filing materialization candidates and unused matviews as P3 suggestions. Files each validated import contradiction as an inbox report; otherwise writes durable memory and closes out empty.

Quality

69%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./products/signals/skills/signals-scout-data-warehouse/SKILL.md

Quality

Content

63%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A thorough, highly actionable scout skill with a clear sequenced workflow and concrete SQL/REST guidance. Its main weaknesses are verbosity in the longer sections and a monolithic single-file structure that inlines content which could be split into references.

Suggestions

Move the MCP tools catalog and the exhaustive scratchpad key examples into a separate reference file (e.g. TOOLS.md / MEMORY-KEYS.md) and link to it, keeping SKILL.md as a lean overview.

Trim repeated hedging phrasing and consolidate the multi-paragraph footgun lists into tighter bullet points while preserving the load-bearing caveats.

Consider extracting the optimization-lane probes (hot tables, recurring shapes, matview waste) into an advanced reference, surfaced from the main Explore section.

Dimension	Reasoning	Score
Conciseness	The body is dense and largely avoids explaining basics Claude already knows, but at ~270 lines it is noticeably verbose — repeated hedging ('never assert', 'still hedge hard'), exhaustive scratchpad examples, and multi-paragraph footgun lists could be tightened without losing the load-bearing detail.	3 / 5
Actionability	Highly actionable: copy-paste-ready SQL sweeps with exact hygiene filters, specific REST tool calls with parameters, and exact scratchpad key formats; the `<NAMES>` placeholders are roster-dependent but explicitly justified, leaving only minor gaps.	4 / 5
Workflow Clarity	A clear sequenced workflow (close-out check → get oriented → profile shape → explore → save memory → decide → close out) with validation checkpoints (confirm source status, 7-day recheck before filing, matview waste candidacy gates) and edit/author/skip decision rails; this is a read-only scout so the destructive-cap does not apply, with only minor implicit-checkpoint gaps.	4 / 5
Progressive Disclosure	It is a single monolithic file with no bundle references; sections are well-organized with clear headers, but well over 50 lines of content (the full MCP tools catalog, exhaustive scratchpad examples, and optimization-lane detail) that could plausibly live in separate reference files is inlined.	3 / 5
	Total	14 / 20 Passed

Description

75%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A specific, well-scoped description that names many concrete capabilities and has a clear niche. Its main weakness is the absence of an explicit 'Use when...' trigger clause, which leaves the 'when' only weakly implied.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when a PostHog project imports external data into the warehouse and you need to audit whether armed imports are still delivering.'

Soften the domain jargon with one or two plainer synonyms (e.g. 'data imports' alongside 'external data sources') to broaden the natural trigger terms.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions across the import and optimization lanes — 'Watches... external data sources, per-table sync schemas, webhook push channels, and materialized views', 'reads the per-team `query_log` table', 'filing materialization candidates and unused matviews as P3 suggestions', 'Files each validated import contradiction as an inbox report' — giving comprehensive coverage of what the scout does.	5 / 5
Completeness	It clearly answers 'what' the scout does, but offers only an implied 'when' ('for PostHog projects importing external data into the warehouse') with no explicit 'Use when...' trigger clause; per the guideline a missing explicit trigger clause caps completeness at 3.	3 / 5
Trigger Term Quality	Good keyword coverage with natural PostHog-warehouse terms a user would say ('external data sources', 'sync schemas', 'webhook push channels', 'materialized views', 'query_log', 'inbox report'), though it leans somewhat domain-jargon-heavy and is missing a few plainer synonyms a non-specialist might use.	4 / 5
Distinctiveness Conflict Risk	The description carves a clear niche — a Signals scout scoped specifically to warehouse imports ('Watches the import side') — with distinct triggers and minimal overlap risk against other scouts.	5 / 5
	Total	17 / 20 Passed

Validation

87%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: PostHog/posthog
Path: products/signals/skills/signals-scout-data-warehouse/SKILL.md
Commit: 31f2a90

Reviewed: about 21 hours ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.