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

—

The risk profile of this skill

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.

The body is highly actionable and well-sequenced with proper validation around destructive operations, assuming Claude's intelligence throughout. Its main weakness is mild redundancy of the resync/destructive warnings and a long inline reference section that a bundle file could absorb.

Suggestions

Consolidate the repeated resync-is-destructive guidance into one canonical location (e.g., Step 5) and reference it from Step 4D and the Important notes to remove redundancy.

Move the error-substring-to-root-cause table (Step 3) and the recovery-action catalog (Step 4 A-I) into a references/ file (e.g., RECOVERY.md), keeping SKILL.md as a workflow overview that links to it.

Add an explicit post-recovery re-check step to the main workflow (not just the example), e.g. re-query the schema to confirm latest_error clears and status returns to Completed.

DimensionReasoningScore

Conciseness

Dense and mostly assumes Claude's competence with no filler, but the destructiveness/resync warnings recur across Step 4D, Step 5, and the Important notes, which could be consolidated.

4 / 5

Actionability

Provides named tool calls with parameters, an error-substring-to-fix mapping table, and a worked end-to-end example with copy-ready commands covering common cases.

5 / 5

Workflow Clarity

Clear top-down sequence (locate, classify, interpret error, recover, confirm) with an explicit pre-destructive approval checkpoint and a verify-after-fix step in the example.

5 / 5

Progressive Disclosure

Well-organized with clear headers and tables and no nested references, but the sizable error-fix and recovery A-I material is fully inlined with no bundle files to offload it.

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.

A high-quality description: third-person voice, concrete actions, explicit trigger phrasing, and a well-scoped niche with minimal overlap risk. It cleanly satisfies the what-and-when requirement with natural user language.

DimensionReasoningScore

Specificity

Names the core actions (diagnose failure, recommend recovery) and enumerates concrete failure categories and the cancel/reload/resync/delete-data recovery actions, giving comprehensive specific coverage.

5 / 5

Completeness

Explicitly answers both what (diagnose and recommend recovery) and when via a concrete "Use when..." clause with multiple trigger phrases.

5 / 5

Trigger Term Quality

Embeds natural verbatim user phrasings ("why isn't my Stripe/Postgres/Hubspot sync working?", "this table has been stuck for hours", "the data in the warehouse looks wrong") plus source-name synonyms.

5 / 5

Distinctiveness Conflict Risk

Occupies a clear niche with domain-specific vocabulary (Running states, CDC, incremental-field, resync/delete-data) and even references a sibling skill, 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.

Validation — 16 / 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.