CtrlK
BlogDocsLog inGet started
Tessl Logo

auditing-warehouse-view-health

Audit the health of a PostHog project's materialized views (saved queries) — find every failed materialization and flag unused or stale materialized views that cost storage and compute. Use when the user asks "which of my views are broken?", "why is this materialized view failing?", "are any of my views wasting compute?", or wants a one-shot triage of view health. For source/sync health use `auditing-warehouse-source-health`.

75

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

85%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 focused, well-structured read-only audit skill with a clear workflow, concrete tool guidance, and explicit safety guardrails. The main improvement opportunity is reducing the repeated out-of-scope routing to a single authoritative statement.

Suggestions

Consolidate the out-of-scope routing note (currently stated in the intro, 'What counts as a view issue', and 'Important notes') into one place to reduce redundancy and token cost.

Consider a one-line concrete example of a HogQL failure fix in Step 2 to make the triage step more directly executable.

DimensionReasoningScore

Conciseness

Mostly lean with no concept-padding, but the out-of-scope routing for sources/syncs/destinations/transformations is restated three times (intro, 'What counts as a view issue', and 'Important notes') and could be trimmed.

4 / 5

Actionability

Concrete tools table with named endpoints, an exact materialized_view filter, a copy-paste-ready report format, and a sequenced workflow; guidance is actionable despite being instruction-only with no code, with only minor gaps.

4 / 5

Workflow Clarity

Clear 5-step sequence with explicit checkpoints (no-issues stop, hand-off confirmation gate) and an 'Important notes' checklist; the destructive-operation cap does not apply because the audit is explicitly read-only with confirmation required for any write.

5 / 5

Progressive Disclosure

Well-organized single-file skill under ~100 lines with clear section headers and no bundle files, so the simple-skill exception applies and structure alone earns full marks.

5 / 5

Total

18

/

20

Passed

Description

100%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 highly specific, well-scoped description with concrete actions, natural user-facing trigger phrases, explicit what-and-when guidance, and clear boundary routing to a sibling skill. It uses third-person voice throughout with no fluff or over-claims.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'find every failed materialization' and 'flag unused or stale materialized views that cost storage and compute' — covering the full audit scope comprehensively.

5 / 5

Completeness

Explicitly answers both what (audit materialized view health) and when (concrete 'Use when...' trigger phrases), matching the anchor for clearly answering both.

5 / 5

Trigger Term Quality

Includes natural phrases users would actually say ('which of my views are broken?', 'why is this materialized view failing?', 'are any of my views wasting compute?') with synonym variation and a broader-triage trigger.

5 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (materialized views) and explicitly routes sibling concerns to auditing-warehouse-source-health, minimizing conflict risk.

5 / 5

Total

20

/

20

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
PostHog/posthog
Reviewed

Table of Contents

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.