CtrlK
BlogDocsLog inGet started
Tessl Logo

diagnosing-failed-warehouse-syncs

Diagnose why a data warehouse sync is failing and recommend the right recovery action. Use when the user asks "why isn't my Stripe/Postgres/Hubspot sync working?", "this table has been stuck for hours", "the data in the warehouse looks wrong", or wants to troubleshoot a specific source or schema. Covers source-level vs schema-level failures, stuck Running states, credential and schema-drift errors, incremental-field misconfig, CDC prerequisite failures, and the cancel / reload / resync / delete-data recovery actions.

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

High

Do not use without reviewing

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 highly actionable, well-sequenced diagnostic skill with concrete tooling, error-to-cause mapping, and proper destructive-action validation. Its main weakness is mild redundancy between the workflow and the Important notes recap, and a single-file structure that could offload the tools table and webhook deep-dive to references.

Suggestions

Remove or cross-reference the duplicated guidance in 'Important notes' (Running vs last_synced_at, resync is destructive, delete-data preserves config) that already appears in Step 4, keeping only net-new cautions like the destination-prefixed error note.

Move the 20-row Available tools table and the detailed webhook recovery sub-workflow (Step 4-I) into reference files, leaving a concise overview plus a pointer, to reduce the SKILL.md footprint and improve progressive disclosure.

Tighten the intro paragraph's 'Do not jump straight to resync' guidance so it is stated once and reinforced only in Step 5 rather than repeated across the intro, Step 4-D, and Important notes.

DimensionReasoningScore

Conciseness

Dense with operational specifics Claude would not know (serializer enum rewriting, webhook failures hidden behind green status) and free of basic-concept padding, but the 'Important notes' section recapitulates points already made in Step 4 (Running isn't always healthy, resync is destructive, delete-data preserves config), a minor redundancy that could be trimmed.

4 / 5

Actionability

Names exact tools, API fields (job_inputs, sync_type_config, incremental_field, last_synced_at), error substrings to match, and a per-root-cause fix; the webhook sub-workflow spells out numbered tool calls with parameters, giving fully executable guidance.

5 / 5

Workflow Clarity

A clearly sequenced five-step workflow with an explicit validation checkpoint (Step 5 requires explicit approval before destructive resync/delete-data/destroy actions) and a decision-tree feedback loop for webhook recovery, satisfying the destructive-operation validation requirement.

5 / 5

Progressive Disclosure

Well-organized with clear section headers (When to use, Available tools, Workflow, Example, Important notes) and no nested references, but the long tools table and the specialized webhook sub-workflow are inlined in a 230-line single file where a one-level-deep reference could keep the overview leaner.

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, quoted natural triggers, explicit what-and-when guidance, and a clearly scoped niche with low conflict risk. Third-person voice is maintained throughout with no fluff.

DimensionReasoningScore

Specificity

Lists multiple concrete actions and failure classes — 'source-level vs schema-level failures, stuck Running states, credential and schema-drift errors, incremental-field misconfig, CDC prerequisite failures, and the cancel / reload / resync / delete-data recovery actions' — giving comprehensive coverage rather than vague abstraction.

5 / 5

Completeness

Explicitly answers both 'what' (diagnose failures and recommend recovery action, with the covered failure types) and 'when' (a 'Use when...' clause with concrete trigger phrases), satisfying the top anchor.

5 / 5

Trigger Term Quality

Embeds natural quoted user phrases ('why isn't my Stripe/Postgres/Hubspot sync working?', 'this table has been stuck for hours', 'the data in the warehouse looks wrong') plus named sources and synonyms, matching the comprehensive anchor.

5 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (warehouse sync diagnosis and recovery) with distinct triggers; the related auditing skill is named only as an entry point, keeping conflict risk minimal.

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.