data-engineering
Transforms, validates, and loads data in ETL pipelines. Use when building scrapers, validating NDJSON feeds, or importing data into CMS/DB targets.
100
100%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
Quality
Discovery
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.
This is a strong, well-crafted description that concisely covers specific capabilities, includes an explicit 'Use when' clause with natural trigger terms, and carves out a distinct niche around ETL/data pipeline work. It uses proper third-person voice and avoids vague language or unnecessary verbosity.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'transforms', 'validates', and 'loads data in ETL pipelines', plus mentions scrapers, NDJSON feeds, and CMS/DB targets as concrete use cases. | 3 / 3 |
Completeness | Clearly answers both 'what' (transforms, validates, loads data in ETL pipelines) and 'when' (explicit 'Use when' clause covering building scrapers, validating NDJSON feeds, or importing data into CMS/DB targets). | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'ETL', 'scrapers', 'NDJSON', 'feeds', 'importing data', 'CMS', 'DB', 'validates', 'pipelines'. These cover common variations of how users would describe data pipeline work. | 3 / 3 |
Distinctiveness Conflict Risk | The combination of ETL pipelines, NDJSON feeds, scrapers, and CMS/DB targets creates a clear niche that is unlikely to conflict with general data processing or database skills. The specificity of 'NDJSON' and 'ETL' strongly narrows the domain. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
100%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is an excellent skill file that is concise, highly actionable, and well-structured. The numbered workflow with explicit checkpoints and recovery steps is particularly strong for a data pipeline context involving destructive batch operations. The progressive disclosure to REFERENCE.md is clean and well-signaled.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Every section earns its place: schema table is compact, workflow steps are dense with checkpoints, code examples are minimal but functional. No unnecessary explanations of what NDJSON is or how browsers work—assumes Claude's competence throughout. | 3 / 3 |
Actionability | Provides executable bash pipeline commands, a complete inline Zod-based NDJSON validator, specific config values (retryLimit, timeout), and a concrete schema table. Guidance is copy-paste ready and specific. | 3 / 3 |
Workflow Clarity | The 5-step workflow includes explicit checkpoints at each stage, recovery actions for failures, a backup step before destructive import, and a revert-on-failure instruction. This is a textbook example of validation-gated workflow with feedback loops for a batch/destructive operation. | 3 / 3 |
Progressive Disclosure | SKILL.md serves as a concise overview with clear one-level-deep references to REFERENCE.md for full scraper code, extended validators, and project-specific schemas. Content is appropriately split between inline essentials and external detail. | 3 / 3 |
Total | 12 / 12 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.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- monkilabs/opencastle
- Commit
18c6f2c
- 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.