compression-optimizer

Compression Optimizer - Auto-activating skill for Data Pipelines. Triggers on: compression optimizer, compression optimizer Part of the Data Pipelines skill category.

1.07x

Quality

Does it follow best practices?

Impact

85%

1.07x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./planned-skills/generated/11-data-pipelines/compression-optimizer/SKILL.md

Evaluation results

71%

Data Lake Ingestion: Compression Format Selection

Multi-format compression benchmark

Criteria

Without context

With context

Multiple algorithms tested

100%

Compression ratio reported

100%

Speed metrics reported

100%

Output integrity validated

100%

Error handling present

10%

Configurable parameters

30%

40%

Summary report file

100%

Streaming / chunk-based processing

Step-by-step structure

87%

Best-format recommendation

100%

Without context: $0.4418 · 1m 47s · 22 turns · 23 in / 6,977 out tokens

With context: $0.5278 · 1m 55s · 28 turns · 26 in / 7,746 out tokens

93%

15%

Analytics Platform: Optimise Batch ETL Storage Costs

Spark pipeline compression configuration

Criteria

Without context

With context

Columnar output format

100%

Compression codec configured

100%

Spark codec property set

66%

100%

Does not use CSV for output

100%

Error handling present

70%

Modular code structure

100%

Logging or progress output

12%

50%

Codec justification documented

100%

Step-by-step pipeline flow

87%

100%

Configurable output path

100%

Without context: $0.3379 · 1m 49s · 18 turns · 18 in / 5,800 out tokens

With context: $0.4221 · 1m 43s · 24 turns · 311 in / 5,675 out tokens

92%

IoT Sensor Archive: Memory-Efficient Compression Pipeline

Streaming data compression pipeline

Criteria

Without context

With context

Chunk-based processing

100%

Streaming compression API used

100%

Round-trip validation

100%

Configurable chunk size

100%

Error handling present

20%

70%

Context managers used

100%

Throughput or progress metrics

100%

Operation log or summary

100%

Step-by-step documented flow

62%

100%

Large file cleanup

100%

28%

Without context: $0.3360 · 1m 11s · 19 turns · 19 in / 4,986 out tokens

With context: $0.5727 · 2m 2s · 31 turns · 410 in / 7,283 out tokens

Repository: jeremylongshore/claude-code-plugins-plus-skills
Commit: 0c08951

Evaluated: 17 days ago
Agent: Claude Code
Model: Claude Sonnet 4.6

Table of Contents

Data Lake Ingestion: Compression Format Selection Analytics Platform: Optimise Batch ETL Storage Costs IoT Sensor Archive: Memory-Efficient Compression Pipeline

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.