CtrlK
BlogDocsLog inGet started
Tessl Logo

testland/data-contract-extractor

Reads a data-product spec (data PRD, dataset README, lineage doc) and emits a structured data contract - schema (columns + types + nullability + PII flags), freshness SLA, volume bounds, distribution invariants, and ownership. The contract is consumable by data-quality tools such as dbt tests, Great Expectations, or Soda checks as their assertion baseline. Use when scoping a new data product or formalizing assertions on an existing one.

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

Low

Low-risk findings worth noting

Overview
Quality
Evals
Security
Files

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.

Highly actionable, well-structured content with a complete executable example and a clear gap-flagging workflow; minor room to tighten the overview aside and confirm the long body is appropriately partitioned.

Suggestions

Trim the Overview's terminology-provenance commentary about Andrew Jones / Chad Sanderson, or move it to a one-line footnote, to sharpen conciseness.

Ensure the worked examples referenced in references/examples.md cover the three promised scenarios (PRD to contract, minimal source with gap list, refactor) so the body's example offloading fully pays off.

DimensionReasoningScore

Conciseness

Mostly efficient with well-organized tables and an executable YAML example, but the Overview's practitioner-emergent-terminology commentary ("Andrew Jones / Chad Sanderson") is a minor aside that could be trimmed.

4 / 5

Actionability

Provides a complete, copy-paste-ready YAML contract covering all five sections, per-column field tables, a numbered extraction procedure, and an anti-patterns table with concrete fixes.

5 / 5

Workflow Clarity

Clear numbered extraction sequence (1-6) with an explicit gap-flagging feedback loop: the agent never fabricates, every gap becomes a question, and the contract is declared incomplete until filled.

5 / 5

Progressive Disclosure

Clear labeled sections with a one-level-deep reference to the real references/examples.md file for worked examples; the body is fairly long but appropriately split rather than monolithic.

4 / 5

Total

18

/

20

Passed

Description

92%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 strong, specific description that clearly states both the concrete outputs and the explicit use-when triggers, with distinct, low-conflict terminology.

DimensionReasoningScore

Specificity

Lists multiple concrete actions (emits schema, freshness SLA, volume bounds, distribution invariants, ownership) and concrete consumer tools (dbt tests, Great Expectations, Soda), giving comprehensive coverage of what the skill produces.

5 / 5

Completeness

Explicitly answers both 'what' (emits a structured data contract with the five listed sections) and 'when' ("Use when scoping a new data product or formalizing assertions on an existing one").

5 / 5

Trigger Term Quality

Includes natural practitioner phrases ("data PRD", "dataset README", "lineage doc", "data contract", "scoping a new data product") a user would say, but a few common synonyms or trigger phrasings could round it out.

4 / 5

Distinctiveness Conflict Risk

Has a clear niche (data contracts for data-quality tooling) with distinct triggers (data PRD, lineage doc, data contract) and minimal overlap risk with other skills.

5 / 5

Total

19

/

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.

Reviewed

Table of Contents