CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

71

Quality

88%

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

77%

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

The skill body is highly actionable with a clear, validated workflow and concrete code/commands — its main weakness is conciseness and structure. It is long with genuine cross-section redundancy, and it leans on a single reference file where more content could be split out.

Suggestions

Consolidate the retry/throttling guidance into one section; 'Prefer the shared REST framework', 'Retry and throttling strategy', and the pitfalls entry all restate 'don't wrap tenacity around status codes', and the partition 'never use updated_at' rule is repeated three times — state each once and cross-reference.

Tighten the unreleasedSource step (currently ~20 lines) to the core rule plus one rationale; the why-it-matters detail can move to a reference or be trimmed since it is restated in the checklist.

Split large inline blocks into reference files — e.g. move the multi-schema SQL checklist and the DataWarehouseSourceCategory enum list into references/ and link to them — so the SKILL.md overview stays scannable and progressive disclosure improves.

DimensionReasoningScore

Conciseness

The body is dense and assumes Claude's competence (no basic-concept padding), but at ~780 lines it repeats itself: retry/throttling guidance appears in 'Prefer the shared REST framework', 'Retry and throttling strategy', and pitfalls; the 'never use updated_at' partition rule and the unreleasedSource warning are each restated several times, so it could be tightened.

2 / 3

Actionability

Provides copy-paste-ready code (base-class combos, resumable/webhook patterns, canonical_descriptions, get_non_retryable_errors, connection_host_fields), exact commands (pnpm run generate:source-configs, schema:build, DEBUG=1 ./bin/migrate, ruff), and concrete file paths throughout.

3 / 3

Workflow Clarity

A clearly sequenced 15-step end-to-end workflow with verification checkpoints (confirm the generated config class appears, run migrations only if needed), a dedicated 'API behavior verification checklist' feedback loop (docs AND curl), a full implementation checklist, and a 'Common pitfalls' error-recovery section.

3 / 3

Progressive Disclosure

There is one well-signaled, one-level-deep reference ([references/oauth-app-deployment.md], a real bundle file) and clear section headings, but the body is largely monolithic — substantial blocks like the multi-schema SQL checklist, canonical descriptions, and the full category enum list are inline rather than split into reference files.

2 / 3

Total

10

/

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.

The description is specific, complete, and distinct: it states concrete capabilities and gives an explicit 'Use when' trigger covering the main task variations a developer would name. It is a strong frontmatter description with no significant weaknesses.

DimensionReasoningScore

Specificity

Lists multiple specific concrete actions — 'adding a new source', 'adding datasets/endpoints', 'incremental sync, resumable imports, webhook ingestion, pagination, credentials validation, and source tests' — matching the anchor for enumerating concrete actions rather than vague language.

3 / 3

Completeness

Explicitly answers both what ('Implement and extend PostHog Data warehouse import sources') and when via a clear 'Use when adding a new source ... or adding incremental sync, resumable imports, webhook ingestion, pagination, credentials validation, and source tests' trigger clause.

3 / 3

Trigger Term Quality

Covers natural domain terms an engineer would actually say — 'adding a new source', 'adding datasets/endpoints to an existing source', 'incremental sync', 'webhook ingestion', 'pagination', 'credentials validation' — rather than generic or jargon-only phrasing.

3 / 3

Distinctiveness Conflict Risk

A clear, narrowly scoped niche — implementing/extending PostHog warehouse sources under a concrete path — with distinct triggers that are unlikely to fire for adjacent skills like documenting or version-bumping a source.

3 / 3

Total

12

/

12

Passed

Validation

87%

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

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (781 lines); consider splitting into references/ and linking

Warning

relative_links

Relative link issues: 1 missing, 2 suspicious

Warning

Total

14

/

16

Passed

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.