Tessl • The management layer for AI agent skills

SkillPublic

data-engineering-data-pipeline

You are a data pipeline architecture expert specializing in scalable, reliable, and cost-effective data pipelines for batch and streaming data processing.

Quality

44%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.agent/skills/data-engineering-data-pipeline/SKILL.md

Quality

Content

33%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.

The body is a well-intentioned but hollow shell: it is token-lean yet delivers essentially no actionable guidance, with an empty Instructions section, no workflow or validation steps, and 12 dangling references to sub-skill files absent from the bundle. As written, invoking the skill gives Claude nothing to execute.

Suggestions

Populate the empty "Instructions" section with a sequenced workflow (e.g., gather requirements → select architecture → implement ingestion/transformation → validate data quality → deploy monitoring) with explicit validation checkpoints, which is mandatory for batch operations per the rubric.

Ship the 12 referenced ./sub-skills/ files or remove the links and inline the essential guidance; fix the duplicate numbering so each knowledge module has a unique identifier.

Add at least a few executable examples (an Airflow DAG skeleton, a dbt model, or a Great Expectations suite) so the capability bullets translate into copy-paste-ready guidance.

Dimension	Reasoning	Score
Conciseness	The body is lean with no explanations of concepts Claude already knows and a tight capability list; the only waste is the persona line repeating the frontmatter description verbatim and an empty "Instructions" header, which keeps it just below the 'every token earns its place' anchor.	4 / 5
Actionability	"Core Capabilities" offers high-level hints ("Build workflow orchestration with Airflow/Prefect", "Transform data using dbt and Spark") but no code, commands, or specific steps, and the "Instructions" section is literally empty while all 12 sub-skill links point to files that do not exist in the bundle. It is not 1 because the named technologies give some concrete anchors, and not 3 because no guidance in the body is executable.	2 / 5
Workflow Clarity	The body contains no steps or sequence at all — pipeline design, implementation, and monitoring are multi-step batch operations, yet no workflow, ordering, or validation checkpoints are stated anywhere, matching the 'steps missing; no validation' anchor.	1 / 5
Progressive Disclosure	The 12 sub-skill references are listed one level deep and clearly signaled, but none of the referenced ./sub-skills/ files exist in the bundle, so progressive disclosure resolves to nothing; duplicate module numbering (two series both starting at "1.") and the empty "Instructions" header make navigation further broken. Not 3 because the references do not resolve to real content, and not 1 because the SKILL.md itself is sectioned and references are not buried or nested.	2 / 5
	Total	9 / 20 Passed

Description

31%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.

The description is a second-person persona statement that names the domain but gives no concrete actions, no trigger phrases, and no use-when guidance. It would leave Claude unable to reliably decide when to invoke this skill over adjacent data-engineering skills.

Suggestions

Rewrite in third person as concrete capabilities, e.g. "Designs ETL/ELT, Lambda, Kappa, and Lakehouse architectures; implements batch and streaming ingestion with Airflow, dbt, and Spark; sets up data quality checks and pipeline monitoring."

Add an explicit trigger clause covering natural variations, e.g. "Use when the user mentions data pipelines, ETL/ELT, data ingestion, workflow orchestration, dbt, Airflow, or batch/streaming processing."

Remove the persona framing ("You are a ... expert") and vague qualifiers ("scalable, reliable, and cost-effective") in favor of specific, verifiable capabilities.

Dimension	Reasoning	Score
Specificity	The description names the domain ("data pipelines for batch and streaming data processing") but lists no concrete actions, matching the anchor for minimal/generic actions; the second-person voice ("You are a data pipeline architecture expert") triggers the rubric's 1-point penalty, reducing it from 2 to 1.	1 / 5
Completeness	There is no 'Use when...' clause or equivalent trigger guidance, and the 'what' is a vague persona statement ("specializing in scalable, reliable, and cost-effective data pipelines") rather than a list of capabilities, fitting the 'vague what and no when' anchor. It is not 3 because the 'what' never states concrete capabilities, and not 1 because the domain is explicitly named.	2 / 5
Trigger Term Quality	"data pipeline", "batch", "streaming", and "data processing" are natural keywords users would say, but common variations for this domain (ETL, ELT, data engineering, ingestion, orchestration, Airflow, dbt) are missing, matching the 'some relevant keywords but missing variations' anchor.	3 / 5
Distinctiveness Conflict Risk	"Data pipeline architecture" is somewhat specific, but the broad phrase "data processing" plus the absence of concrete trigger phrases leaves real overlap risk with general data-engineering, ETL, and data-analysis skills, fitting the 'somewhat specific but could still overlap' anchor rather than the mostly-distinct anchor.	3 / 5
	Total	9 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 12 missing	Warning

	Total	14 / 16 Passed

Repository: Dokhacgiakhoa/Agent-Skills-4-Vibe-Coding-CLI
Path: .agent/skills/data-engineering-data-pipeline/SKILL.md
Revision: c4a059b

Reviewed: 11 hours ago

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.

data-engineering-data-pipeline

Table of Contents

Is this your skill?