data-engineering

Transforms, validates, loads data in ETL pipelines. Use when building scrapers, validating NDJSON feeds, or importing data into CMS/DB targets.

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Medium

Suggest reviewing before use

Quality

Content

92%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 exceptionally concise, actionable skill body with a well-sequenced, validated destructive-import workflow. The only weakness is progressive disclosure: the body references REFERENCE.md and scripts that are not present in any bundle directory.

Suggestions

Provide the referenced ./REFERENCE.md (and the ./scripts/*.js files) in a references/ or scripts/ bundle so the one-level-deep pointers resolve.

If the scripts are intentionally out of scope, inline the key invocation contract or remove the references to avoid dead links.

Confirm the REFERENCE.md path casing/existence, since progressive-disclosure scoring relies on references that actually exist.

Dimension	Reasoning	Score
Conciseness	The body is lean and token-efficient — exact config values, required/optional field lists, and runnable commands with no padding or explanation of concepts Claude already knows.	5 / 5
Actionability	Fully executable guidance: concrete commands with flags ('node ./scripts/scrape-to-ndjson.js --out=data.ndjson --pages=100') and specific field/schema requirements that are copy-paste ready.	5 / 5
Workflow Clarity	A numbered five-step pipeline with explicit validation checkpoints (require 0 parse errors, ±5% counts, no duplicates), feedback loops (isolate failures, fix selectors, re-run), snapshots, and revert-on-failure for a destructive batch import.	5 / 5
Progressive Disclosure	Structure is clean with a one-level-deep pointer to REFERENCE.md, but no bundle directories exist, so the referenced REFERENCE.md and ./scripts/*.js files do not resolve and navigation is effectively broken.	3 / 5
	Total	18 / 20 Passed

Description

83%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, concise description that uses third person and answers both what and when with concrete, domain-specific triggers. It is held back from top marks only by slightly broad action verbs and minor synonym coverage.

Dimension	Reasoning	Score
Specificity	Names the ETL domain and three concrete actions ('Transforms, validates, loads data'), giving several specific actions; not a 5 because the actions are the canonical high-level ETL stages rather than granular operations.	4 / 5
Completeness	Clearly answers both 'what' ('Transforms, validates, loads data in ETL pipelines') and 'when' ('Use when building scrapers, validating NDJSON feeds, or importing data into CMS/DB targets') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Natural trigger phrases ('building scrapers, validating NDJSON feeds, or importing data into CMS/DB targets') cover the main cases; a few common synonyms or variations are missing, so not a 5.	4 / 5
Distinctiveness Conflict Risk	The ETL/scraper/NDJSON/CMS-DB niche is clearly distinct with specific triggers, but 'transforms/validates/loads data' has minor overlap risk with general data-processing skills, so not a 5.	4 / 5
	Total	17 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 1 missing	Warning

	Total	15 / 16 Passed

Repository: monkilabs/opencastle
Path: src/orchestrator/skills/data-engineering/SKILL.md
Commit: fa0c341

Reviewed: 5 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.