CtrlK
BlogDocsLog inGet started
Tessl Logo

auditing-warehouse-source-health

Audit the health of a PostHog project's data warehouse sources and syncs — find every broken or degraded source connection, sync schema, and webhook channel. Use when the user asks "why are my imports failing?", "what's broken with my sources?", "why is my warehouse data stale?", or wants a one-shot triage of source/sync health before deciding where to dig in. Produces a prioritized report grouped by severity, with recommended next steps. For materialized-view health use `auditing-warehouse-view-health`; for a single failing sync use `diagnosing-failed-warehouse-syncs`.

76

Quality

94%

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

88%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 strong, actionable audit workflow rich in non-obvious PostHog domain detail, with clear sequencing and validation checkpoints. The main weakness is redundancy between the workflow body and the closing 'Important notes' recap, plus no use of bundle files to offload detail.

Suggestions

Collapse the 'Important notes' section into the workflow steps where each point first arises, or trim it to only the points not already covered inline, to remove the recap redundancy.

Consider moving the detailed Step 4 webhook diagnostics and the report template into a references/ file (signaled one level deep) to slim the main SKILL.md and improve progressive disclosure.

The out-of-scope routing (materialized views, destinations, transformations) is stated three times (intro, issue table, Important notes) — consolidate to a single authoritative statement.

DimensionReasoningScore

Conciseness

The bulk is lean, domain-specific knowledge Claude would not already have (endpoint categories, status mappings, webhook edge cases), but the 'Important notes' section largely restates points already made in the body (read-only, empty=healthy, cascade, billing, active-failures-only, out-of-scope routing) and could be trimmed.

4 / 5

Actionability

Highly actionable for an instruction-only skill: names specific tools, filter types ('source', 'external_data_sync'), status values ('failed', 'billing_limit'), concrete prioritization order, a copy-paste report template, and exact webhook-info-retrieve field interpretations.

5 / 5

Workflow Clarity

Five clearly sequenced steps with explicit checkpoints — the empty-state guard in Step 1 ('tell the user their sources are healthy and stop'), ordered prioritization, a report template functioning as a checklist, and a read-only enforcement hand-off in Step 5.

5 / 5

Progressive Disclosure

Well-organized into clear headed sections (When to use, Available tools, What counts as an issue, Workflow, Important notes) making navigation easy, but it is a single ~155-line file with no external references and some inline redundancy between body and notes; above the 50-line simple-skill threshold so it does not qualify for the no-reference 5.

4 / 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.

An exemplary description: concrete actions, verbatim natural trigger phrases, explicit what-and-when, and clear boundary routing to sibling skills, all in concise third-person voice.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'Audit the health', 'find every broken or degraded source connection, sync schema, and webhook channel', 'Produces a prioritized report grouped by severity, with recommended next steps' — covering the audit comprehensively.

5 / 5

Completeness

Explicitly states both what it does (audit source/sync health, produce prioritized report) and when to use it, with concrete quoted trigger phrases — satisfying the strongest anchor.

5 / 5

Trigger Term Quality

Includes verbatim natural user phrases ('why are my imports failing?', 'what's broken with my sources?', 'why is my warehouse data stale?', 'one-shot triage of source/sync health') that users would actually say.

5 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (source/sync side of the warehouse) and explicitly routes adjacent cases to sibling skills ('For materialized-view health use auditing-warehouse-view-health; for a single failing sync use diagnosing-failed-warehouse-syncs'), 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.