data-engineering

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

Quality

90%

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

96%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.

Excellent body content: fully executable commands, a concrete data schema, and a five-step pipeline with explicit validation checkpoints and recovery paths for every risky operation. The only weakness is that the files it references (REFERENCE.md and the scripts) are not present in the bundle, making the disclosed navigation unverifiable.

Suggestions

Ship REFERENCE.md and the four scripts (scrape-to-ndjson.js, validate-ndjson.js, dry-import.js, import.js) alongside SKILL.md so the referenced paths and commands actually resolve.

If the bundle intentionally omits them, add a one-line note in SKILL.md stating where these files live (e.g., repository path) so Claude is not left with dead references.

Dimension	Reasoning	Score
Conciseness	The body is lean with zero padding or explanation of concepts Claude already knows — every line carries project-specific facts (exact config values, field schema, numeric thresholds). It matches the anchor-5 "every token earns its place" example; there is nothing to trim that would drop it to 4.	5 / 5
Actionability	The bash pipeline block gives copy-paste-ready commands with flags ("node ./scripts/scrape-to-ndjson.js --out=data.ndjson --pages=100"), plus a concrete required/optional field schema and specific acceptance criteria (50–200 record sample, 0 parse errors, ±5% counts). This matches the fully-executable anchor 5; not 4 because no key details are missing for the common path.	5 / 5
Workflow Clarity	A clear five-step sequence with explicit validation checkpoints and feedback loops: dry-run sample with "fix extractor selectors and re-run the sample", "require 0 parse errors", staging dry-run with revert/dedupe-adjust, snapshot before write, and "revert to the snapshot on failure". This matches the anchor-5 validate→fix→retry pattern, and the batch/destructive feedback-loop cap does not apply since validation is thorough.	5 / 5
Progressive Disclosure	The structure is exemplary — a clearly signaled one-level reference ("Project-specific sources, full schema, full scraper and extended validator: [REFERENCE.md](./REFERENCE.md)") and well-organized sections. However, the referenced paths (./REFERENCE.md and the ./scripts/*.js commands) do not exist in the provided bundle, so navigation cannot be verified, leaving a minor gap at anchor 4 rather than 5.	4 / 5
	Total	19 / 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 description in third person that explicitly states both what the skill does and when to use it, with concrete natural-language triggers. Minor room to grow in specificity of the actions and broader trigger synonym coverage. No suggestions needed given the strength of the result.

Dimension	Reasoning	Score
Specificity	"Transforms, validates, loads data in ETL pipelines" names three concrete actions, matching the several-specific-actions-with-minor-gaps anchor; it falls short of 5 because "data" stays generic with no detail on what is transformed or how. It clearly exceeds the 1-2-concrete-actions anchor.	4 / 5
Completeness	Both parts are explicit: "Transforms, validates, loads data in ETL pipelines" answers what, and "Use when building scrapers, validating NDJSON feeds, or importing data into CMS/DB targets" gives concrete when-triggers — exactly the anchor-5 pattern. Anchor 4 requires a less explicit "when", which does not apply.	5 / 5
Trigger Term Quality	Natural terms a user would say are present ("building scrapers", "validating NDJSON feeds", "importing data into CMS/DB targets", "ETL"), giving good coverage as in the anchor-4 example; it misses common synonyms and variations like "web scraping", "crawler", or ".ndjson" needed for a 5.	4 / 5
Distinctiveness Conflict Risk	The scraper/NDJSON/CMS-import niche is mostly distinct with specific triggers, matching "mostly distinct; minor overlap risk". The generic ETL framing leaves some overlap with general data-processing skills, so it does not reach the clear-niche anchor 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: c0f4566

Reviewed: 1 day 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.