setting-up-a-data-warehouse-source

Guide the user through connecting a new data warehouse source — Postgres, MySQL, Stripe, Hubspot, MongoDB, Salesforce, BigQuery, Snowflake, and so on. Use when the user wants to "connect Stripe", "import data from Postgres", "add a new data source", "sync my warehouse tables", or wants to pick sync methods for each table. Walks through source-type discovery, credential validation, table discovery, per-table sync_type selection, and the final create call. Also covers picking a good prefix and what to do right after creation.

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

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.

The body is highly actionable with clear workflows, validation checkpoints, and good progressive disclosure via the sync-types reference. Its main weakness is repetition of the webhook and prefix material across multiple sections, which inflates the token budget.

Suggestions

Consolidate the webhook two-step setup into Step 6 and have the one-step path and Important notes cross-reference it instead of restating the flow.

Move the prefix guidance to a single location (Step 4) and reference it from Important notes rather than repeating the load-bearing-prefix points.

Consider pulling the per-source credential key requirements (Stripe, Sentry, Twilio, etc.) into the sync-types reference or a dedicated reference file so the SKILL.md pre-flight section stays a concise checklist.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and information-dense, but several topics repeat across sections (webhook two-step setup in the one-step notes, Step 6, and Important notes; prefix guidance in Step 4 and Important notes), which is more than minor trimming.	3 / 5
Actionability	Fully executable guidance — exact tool names, concrete parameter shapes, a copy-paste JSON payload for create, and specific source-specific key requirements (Stripe rk_live_, Supabase pooler host/port).	5 / 5
Workflow Clarity	Clearly sequenced steps 1-7 with an ASCII flow diagram, validation checkpoints (db-schema before create, CDC prerequisites, webhook-info verification), and feedback loops (validate→fix→retry, webhook-fail→manual registration) for a batch/billing-sensitive operation.	5 / 5
Progressive Disclosure	Well-organized sections with the sync-type decision logic appropriately offloaded to references/sync-types.md (a real file) and clearly linked at the decision points; references are one level deep and well-signaled.	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.

The description is concrete, well-triggered, and self-contained — it names the domain, lists specific actions, provides natural trigger phrases, and scopes the skill clearly. It matches the top anchor on every dimension.

Dimension	Reasoning	Score
Specificity	Names the domain plus multiple concrete actions — "source-type discovery, credential validation, table discovery, per-table sync_type selection, and the final create call" plus prefix selection — matching the comprehensive-coverage anchor.	5 / 5
Completeness	Explicitly answers both what (discovery → validation → table selection → create → prefix) and when via a concrete "Use when the user wants to..." clause with multiple trigger phrases.	5 / 5
Trigger Term Quality	Surfaces natural user phrases ("connect Stripe", "import data from Postgres", "add a new data source", "sync my warehouse tables") alongside many source-type synonyms, giving comprehensive natural-term coverage.	5 / 5
Distinctiveness Conflict Risk	Scoped tightly to PostHog data-warehouse source setup with named source types and sync methods, occupying a clear niche with minimal overlap with other skills.	5 / 5
	Total	20 / 20 Passed

Validation

100%

Warnings & errors only

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
Path: products/warehouse_sources/skills/setting-up-a-data-warehouse-source/SKILL.md
Commit: 6fca5f8

Reviewed: 3 days ago

Table of Contents

Discovery Implementation Validation

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.