Tessl • The package manager for agent skills

SkillPublic

preprocessing-data-with-automated-pipelines

Design and implement repeatable preprocessing pipelines for cleaning, encoding, transforming, and validating ML input data.

Quality

62%

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 ./bundled/skills/preprocessing-data-with-automated-pipelines/SKILL.md

Quality

Content

51%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 skill body is commendably concise and well-structured, but it stays at a descriptive level: it gives no executable guidance and fails to point to the substantial bundled scripts and references. Adding concrete commands and links to the existing bundle files would substantially raise actionability and workflow clarity.

Suggestions

Reference and show how to run the bundled scripts (e.g. `python scripts/pipeline.py --config config.yaml`, `python scripts/validate_data.py ...`) so the body is executable rather than descriptive.

Add an explicit sequenced workflow with a validation checkpoint (validate -> transform -> re-validate) and a feedback loop for failed validation.

Link the bundled references and assets from the body (e.g. "See references/data_validation_schemas.md", "Sample input: assets/example_data.csv") to complete progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The body is lean and well-organized with no padded explanation of concepts Claude already knows; every section earns its place.	5 / 5
Actionability	The body only describes outputs ("a preprocessing pipeline plan or implementation sketch", "clear sequencing") with no executable code or commands, and never references the bundled executable scripts.	2 / 5
Workflow Clarity	A rough sequence (clean, encode, transform, validate) is named but steps are undefined, no concrete commands are given, and there is no validation checkpoint for this batch pipeline.	2 / 5
Progressive Disclosure	Sections are well-organized, but eight bundle files (scripts/, references/, assets/) exist and none are linked or signaled from the body, leaving navigation incomplete.	3 / 5
	Total	12 / 20 Passed

Description

58%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 concise and names concrete preprocessing actions, giving it solid specificity and distinctiveness. Its main weakness is the absence of an explicit "Use when..." trigger clause, which caps completeness and leaves the activation conditions implicit.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user asks to build or automate a repeatable cleaning/encoding/transformation pipeline for ML input data."

Include natural synonyms and concrete artifacts users mention (e.g. "CSV", "feature engineering", "data wrangling") to improve trigger term coverage.

Sharpen the boundary from siblings (e.g. contrast with scikit-learn / ml-pipeline-workflow) within the description to lower conflict risk.

Dimension	Reasoning	Score
Specificity	Names the ML-input domain and several concrete actions ("cleaning, encoding, transforming, and validating"), though coverage of pipeline actions is broad rather than exhaustive.	4 / 5
Completeness	The description clearly states what the skill does but provides no explicit "Use when..." trigger clause, so the "when" is only weakly implied.	3 / 5
Trigger Term Quality	Relevant terms like "preprocessing pipelines" and "ML input data" appear, but common variations, synonyms, and concrete file types users would say are missing.	3 / 5
Distinctiveness Conflict Risk	"repeatable preprocessing pipelines" is a fairly distinct niche, though it retains some overlap risk with closely related ML preprocessing skills.	4 / 5
	Total	14 / 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
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: foryourhealth111-pixel/Vibe-Skills
Path: bundled/skills/preprocessing-data-with-automated-pipelines/SKILL.md
Revision: 5ce2258

Reviewed: 27 days 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.

preprocessing-data-with-automated-pipelines

Table of Contents

Is this your skill?