CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

implementing-warehouse-sources

Implement and extend PostHog Data warehouse import sources. Use when adding a new source under products/warehouse_sources/backend/temporal/data_imports/sources, adding datasets/endpoints to an existing source, or adding incremental sync, resumable imports, webhook ingestion, pagination, credentials validation, and source tests.

73

Quality

92%

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

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.

An authoritative, highly actionable guide to a complex production workflow with strong sequencing and validation, undermined only by monolithic inlining and a dangling bundle reference. Conciseness is good but not lean, with some rationale repetition across sections.

Suggestions

Create the missing references/oauth-app-deployment.md (or remove the link) so the one signaled bundle reference resolves.

Split the large self-contained sections (multi-schema SQL parity checklist, warehouse-parent fan-out, vendor API version metadata) into reference files and link to them from SKILL.md to reduce the inline wall of text.

De-duplicate the unreleasedSource guidance — state it once in the workflow step and reference it from the checklist and pitfalls instead of restating the full rationale three times.

DimensionReasoningScore

Conciseness

The body is dense with PostHog-specific operational knowledge Claude would not already know, so most tokens earn their place; however the unreleasedSource rationale is repeated across step 13, the checklist, and common pitfalls, and several rationale paragraphs run longer than strictly necessary.

4 / 5

Actionability

Copy-paste-ready commands ('pnpm run generate:source-configs', 'hogli build:openapi', 'DEBUG=1 python manage.py makemigrations'), concrete file paths, and executable code snippets cover the common cases end-to-end.

5 / 5

Workflow Clarity

A 15-step end-to-end workflow with an explicit verification checklist (curl against the live API, run tests, ruff), an implementation checklist, and feedback loops (verify-then-fix) gives clear sequencing with validation checkpoints for this batch/data-sync operation.

5 / 5

Progressive Disclosure

Section headers and a 'Read first' block give structure, but the skill is a monolithic ~890-line file with content that belongs in separate references (multi-schema SQL checklist, warehouse-parent fan-out, OAuth deployment) inlined, and its one signaled bundle reference, references/oauth-app-deployment.md, does not exist in the empty references/ directory.

3 / 5

Total

17

/

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 exemplary: third-person voice, a concrete what, an explicit 'Use when' clause enumerating the exact trigger scenarios, and a precise niche that minimizes conflict risk. No fluff or over-claims.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'adding a new source', 'adding datasets/endpoints', 'incremental sync, resumable imports, webhook ingestion, pagination, credentials validation, and source tests' — anchored to a specific path, giving comprehensive coverage.

5 / 5

Completeness

Explicitly answers both what ('Implement and extend PostHog Data warehouse import sources') and when ('Use when adding a new source... adding datasets/endpoints...') with concrete trigger phrases.

5 / 5

Trigger Term Quality

Covers the natural phrases a developer of this surface would say ('adding a new source', 'incremental sync', 'webhook ingestion', 'pagination', 'credentials validation') with enough synonym variation to match real requests.

5 / 5

Distinctiveness Conflict Risk

Narrowly scoped to PostHog Data warehouse import sources with a specific repo path, so it is clearly distinguishable from sibling skills and unlikely to trigger for the wrong one.

5 / 5

Total

20

/

20

Passed

Validation

81%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (890 lines); consider splitting into references/ and linking

Warning

relative_links

Relative link issues: 2 missing, 2 suspicious

Warning

referenced_paths_exist

Referenced path issues: 2 missing

Warning

Total

13

/

16

Passed

Repository

PostHog/posthog

Path

.agents/skills/implementing-warehouse-sources/SKILL.md

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.