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`.

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%

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

A well-structured, actionable audit skill with clear workflow sequencing and guardrails. Its only real weakness is conciseness — a couple of sections (triggers, out-of-scope categories) are duplicated and could be consolidated to trim tokens.

Suggestions

Remove the duplicate out-of-scope listing: it appears both in the 'What counts as a source/sync issue' table and again in 'Important notes' — keep one canonical location and cross-reference it.

Trim the 'When to use this skill' list, which largely restates the frontmatter description's triggers — either cut it or reduce it to novel entries not already in the description.

Consider merging the 'Webhook health is separate from schema health' note with the Step 4 webhook guidance so the webhook blind spot is explained once rather than across two sections.

DimensionReasoningScore

Conciseness

Mostly efficient and dense with non-obvious domain knowledge, but redundant: the description's triggers reappear in 'When to use' and the out-of-scope categories (materialized_view/destination/transformation) are stated twice — once in the table and again in 'Important notes'.

2 / 3

Actionability

Provides concrete endpoint names, exact status values to filter, a precise prioritization order, a rendered report template with realistic example data, and specific hand-off phrasings; absence of literal code is acceptable for an instruction-only API-call skill.

3 / 3

Workflow Clarity

Clear 5-step sequence with explicit checkpoints (stop-if-empty guard, cascade-aware prioritization, deeper checks gated on an explicit ask) and a read-only guardrail; the destructive/batch validation cap does not apply since the skill is explicitly read-only and defers remediation.

3 / 3

Progressive Disclosure

A single self-contained file organized into clear sections, with all references being one-level hand-offs to sibling skills rather than nested bundle references, and no content that obviously belongs in a separate file.

3 / 3

Total

11

/

12

Passed

Description

100%

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 strong, third-person description that names concrete actions, supplies natural user-voice triggers, answers both what and when, and cleanly differentiates from sibling skills. No meaningful weaknesses to address.

DimensionReasoningScore

Specificity

Lists multiple concrete actions ('find every broken or degraded source connection, sync schema, and webhook channel', 'Produces a prioritized report grouped by severity, with recommended next steps'), matching the score-3 anchor for multiple specific concrete actions.

3 / 3

Completeness

Clearly answers both what (audit source/sync health and produce a prioritized report) and when via an explicit 'Use when...' clause with concrete triggers, matching the score-3 anchor.

3 / 3

Trigger Term Quality

Includes direct user-voice quotes ('why are my imports failing?', 'what's broken with my sources?', 'why is my warehouse data stale?') — natural terms users would actually say, matching the score-3 anchor.

3 / 3

Distinctiveness Conflict Risk

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`'), giving it a clear niche unlikely to trigger the wrong skill.

3 / 3

Total

12

/

12

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.