Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

File Format Converter · dicklesworthstone | DecimalAI

dicklesworthstone/file-format-converter

NewSkillScoreMaintained

Convert file format converter operations. Auto-activating skill for Data Pipelines. Triggers on: file format converter, file format converter Part of the Data Pipelines skill category. Use when working with file format converter functionality. Trigger with phrases like "file format converter", "file converter", "file".

by dicklesworthstone

Links this skill to your agents and keeps it current with the author’s updates.

Automatic

Data Engineer pack

1 · One-time — install the CLI (docs ↗)

pip install decimalai

2 · Get the skill — writes .claude/skills/dicklesworthstone-file-format-converter/SKILL.md

decimalai skills pull dicklesworthstone-file-format-converter --out .claude/skills/

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/dicklesworthstone-file-format-converter/SKILL.md https://app.decimal.ai/s/dicklesworthstone-file-format-converter/SKILL.md

Raw file: /s/dicklesworthstone-file-format-converter/SKILL.md ↗ · machine-readable summary at /s/dicklesworthstone-file-format-converter.json ↗

In productionGlobal

how this skill behaves on real traffic · last 30 days

No production data for this skill yet — usage numbers appear here once agents start running it.

Anonymized aggregate across every org using this skill — proof from real production use, not a demo.

Does this skill help? · Benchmark: with vs. withoutsign in to run this on your agents

23 test cases from the publisher’s eval.yaml · each run twice on gemini-3.6-flash — with the skill injected, then without · last run 22d ago

No measurable change+26% tokens0% turns87% of whole cases pass with skill (20/23)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-19	✗→✓	▲ Improved	38%	0%
case-16	✓→✗	▼ Worse	14%	0%
case-01	✓→✓	＝ Same ✓	12%	0%
case-02	✓→✓	＝ Same ✓	41%	0%
case-04	✓→✓	＝ Same ✓	4%	0%

Showing 5 of 23 cases

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/10/2026

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

dicklesworthstone / pi_agent_rust

tests/ext_conformance/artifacts/plugins-community/skills/11-data-pipelines/file-format-converter/SKILL.md

View on GitHub ↗

License MITImported 8/10/2026Version v1

Skill contents

SKILL.md

File Format Converter

Overview

This skill provides automated assistance for file format converter tasks within the Data Pipelines domain.

When to Use

This skill activates automatically when you:

Mention "file format converter" in your request
Ask about file format converter patterns or best practices
Need help with data pipeline skills covering etl, data transformation, workflow orchestration, and streaming data processing.

Instructions

Provides step-by-step guidance for file format converter
Follows industry best practices and patterns
Generates production-ready code and configurations
Validates outputs against common standards

Examples

Example: Basic Usage Request: "Help me with file format converter" Result: Provides step-by-step guidance and generates appropriate configurations

Prerequisites

Relevant development environment configured
Access to necessary tools and services
Basic understanding of data pipelines concepts

Output

Generated configurations and code
Best practice recommendations
Validation results

Error Handling

| Error | Cause | Solution | |-------|-------|----------| | Configuration invalid | Missing required fields | Check documentation for required parameters | | Tool not found | Dependency not installed | Install required tools per prerequisites | | Permission denied | Insufficient access | Verify credentials and permissions |

Resources

Official documentation for related tools
Best practices guides
Community examples and tutorials

Related Skills

Part of the Data Pipelines skill category. Tags: etl, airflow, spark, streaming, data-engineering

Illustrative Want to see what dicklesworthstone/file-format-converter would put in front of your model? Preview the rendered body and check its trigger phrases — no LLM call, no signup.

Latest benchmark · publisher runVerified

8/30/2026, 06:09 UTC · 23 cases

Lift

87% vs 87%

Agent turns

1.0 vs 1.0

Tokens

+26%

2,495.17 vs 1,979.7

fail → pass · 1pass → pass · 19fail → fail · 2pass → fail · 1

Per-case results (23)

Case	Status	Duration (ms)			Turns			Tokens			Tool calls
Case	Status	Without	With	Δ	Without	With	Δ	Without	With	Δ	Without	With	Δ
case-01 I have a 40GB CSV log file `web_logs.csv` that exceeds available RAM. I need a Python script using pandas or PyArrow to convert this file to Parquet format without causing an Out-Of-Memory (OOM) error. How should the file reading and writing be structured?	pass→pass	20,082	42,392	+111%	1	1	0%	2,957	3,322	+12%	0	0	—
case-02 We are converting `customers.csv` containing columns `customer_id` (e.g., '00123') and `zip_code` (e.g., '02134') to Parquet using PyArrow or pandas. Automatic type inference turns these string values into integers, losing leading zeros. How do we ensure these columns maintain string types during conversion?	pass→pass	13,219	14,797	+12%	1	1	0%	1,646	2,323	+41%	0	0	—
case-03 When converting raw JSON data files to Parquet format for query engine performance in Amazon Athena, what compression codec balances fast query decompression speeds with high compression ratios?	fail→fail	16,238	17,150	+6%	1	1	0%	1,856	2,549	+37%	0	0	—
case-04 We have line-delimited JSON logs `events.json` with nested objects like `user.id` and `user.geo.country`. We need to convert this to a flat CSV file using Python pandas. How should nested JSON structures be handled before writing to CSV?	pass→pass	17,299	16,844	-3%	1	1	0%	2,508	2,609	+4%	0	0	—
case-05 In a PySpark ETL job converting raw CSV files `transactions.csv` to Parquet format, several lines contain corrupted column counts or malformed characters. We need to convert valid records while isolating corrupted lines. How should `spark.read.option` be configured?	pass→pass	19,165	18,564	-3%	1	1	0%	2,884	3,114	+8%	0	0	—
case-06 We need to convert a set of CSV records into Apache Avro format using Python `fastavro`. Can Avro files be generated without defining an explicit Avro JSON schema definition?	pass→pass	15,930	17,792	+12%	1	1	0%	2,037	2,804	+38%	0	0	—
case-07 When converting a high-volume dataset with repeated string status codes (e.g., 'PENDING', 'APPROVED', 'REJECTED') to Parquet using PyArrow, how does dictionary encoding improve storage efficiency?	pass→pass	20,782	20,324	-2%	1	1	0%	2,850	3,189	+12%	0	0	—
case-08 We are converting a multi-gigabyte dataset of sales events into Parquet format using PySpark. We need to query this data by `year` and `month`. How should the `DataFrameWriter` be configured to store the Parquet dataset in a hive-style partitioned directory structure?	pass→pass	14,805	17,062	+15%	1	1	0%	1,840	2,611	+42%	0	0	—
case-09 We want to convert a 10GB `orders.csv` file into `orders.parquet` using DuckDB in Python with minimal code and maximum performance. What DuckDB SQL command or Python API call performs this conversion directly in embedded DuckDB?	pass→pass	12,387	14,688	+19%	1	1	0%	1,397	2,087	+49%	0	0	—
case-10 When converting timestamp data from CSV to Parquet using PyArrow for downstream consumption in Apache Spark, standard PyArrow nanosecond timestamps cause incompatible type errors in Spark. What parameter should be passed to `pyarrow.parquet.write_table`?	fail→fail	8,356	13,838	+66%	1	1	0%	1,473	1,935	+31%	0	0	—
case-11 We have legacy mainframe text files `account_data.txt` where fields are defined by fixed character widths (e.g. bytes 0-10 ID, 10-30 Name, 30-40 Balance). We need to convert this to Parquet using pandas. Which pandas function parses this file structure?	pass→pass	6,728	11,737	+74%	1	1	0%	1,273	1,778	+40%	0	0	—
case-12 We have a stream of newline-delimited JSON logs where new fields appear in later rows. When converting these JSON lines to Parquet using PySpark, reading across files causes schema mismatch errors. How should schema handling be configured in PySpark?	pass→pass	15,213	23,130	+52%	1	1	0%	2,624	3,646	+39%	0	0	—
case-13 We receive monthly multi-tab Excel files (`financials.xlsx`) containing 500,000 rows across tabs. We need a Python script to extract each worksheet and save it as an individual Parquet file. What pandas class parses sheet names without reading full sheet contents into memory?	pass→pass	14,814	14,949	+1%	1	1	0%	1,789	2,383	+33%	0	0	—
case-14 In an Apache Spark ETL pipeline, we need to convert legacy Hive ORC formatted data stored in S3 into Delta Lake table format without re-writing or duplicating all underlying data files. What Spark Delta command performs this in-place format conversion?	pass→pass	7,862	9,913	+26%	1	1	0%	1,443	2,135	+48%	0	0	—
case-15 We have large XML files containing hierarchical web order payloads (`<orders><order>...</order></orders>`). We need to convert this XML dataset into Parquet using PySpark. Which library format option enables `spark.read.format` to parse XML records?	pass→pass	12,558	14,948	+19%	1	1	0%	1,501	2,279	+52%	0	0	—
case-16 When converting a pandas DataFrame with missing values (NaN) loaded from a CSV file into JSON format, `df.to_json()` by default can emit NaN float tokens. How do we ensure missing float values are represented properly as null or handled cleanly?	pass→fail	20,102	20,309	+1%	1	1	0%	2,911	3,305	+14%	0	0	—
case-17 We have vector mapping data in GeoJSON format (`polygons.geojson`). We need to convert this file into GeoParquet format in Python. Which library should be used to read and export the spatial DataFrame?	pass→pass	12,391	9,425	-24%	1	1	0%	1,406	2,127	+51%	0	0	—
case-18 When converting financial transaction CSV data containing high-precision currency values (e.g. `1234567.89012`) to Parquet using PySpark, default float inference can introduce binary rounding errors. How should numeric precision be preserved during format conversion?	pass→pass	19,491	13,374	-31%	1	1	0%	2,753	2,981	+8%	0	0	—
case-19 An in-memory process produces an Apache Arrow IPC byte stream (`RecordBatchStreamReader`). We need to write this streaming Arrow data directly into a Parquet file without intermediate disk conversions. What PyArrow module methods perform this conversion?	fail→pass	14,518	16,748	+15%	1	1	0%	1,946	2,677	+38%	0	0	—
case-20 When converting raw JSON event streams to Apache ORC format using PySpark, what DataFrameWriter options specify ORC format and set compression to ZLIB?	pass→pass	8,206	6,149	-25%	1	1	0%	1,522	1,553	+2%	0	0	—
case-21 In Apache Airflow 2.x, we need a DAG schedule interval that runs every weekday (Monday through Friday) at 02:30 AM UTC. What cron expression string should be assigned to the `schedule` parameter?	pass→pass	10,119	9,566	-5%	1	1	0%	1,052	1,241	+18%	0	0	—
case-22 A PostgreSQL query regularly executes `SELECT * FROM sales WHERE user_id = 123 AND created_at >= '2023-01-01' ORDER BY created_at DESC;`. How should a composite B-tree index be defined on the `sales` table to optimize both filtering and sorting?	pass→pass	14,417	15,193	+5%	1	1	0%	1,791	2,204	+23%	0	0	—
case-23 In an Apache Kafka consumer streaming pipeline, we want to prevent message loss when processing messages before writing them to downstream storage. Should consumer offset commits be configured as auto-commit (`enable.auto.commit=true`) or manual commit (`enable.auto.commit=false`)?	pass→pass	11,387	17,584	+54%	1	1	0%	2,074	2,537	+22%	0	0	—

These cases were also screened by the skill’s intent / safety pass.See the Trust review ↗Reproduce this benchmark in Colab ↗

How this skill was measured

DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 23 cases were attempted. The headline lift of 0 percentage points is the difference between those two pass rates over the 23 comparable cases. 1 case got worse with the skill loaded, and it is included in that figure.

Model measured: gemini-3.6-flash
Graded by: gemini-3.6-flash
Grading method: judged
Verification: verified
Pass rate without the skill: 87%
Pass rate with the skill: 87%
Cases attempted: 23
Cases counted toward lift: 23
Cases that regressed: 1
Skill version measured: v1
Run completed: 8/30/2026, 06:09 UTC

Measured example — same prompt, with vs. without the skill · from the benchmark run · case case-19

Prompt

An in-memory process produces an Apache Arrow IPC byte stream (`RecordBatchStreamReader`). We need to write this streaming Arrow data directly into a Parquet file without intermediate disk conversions. What PyArrow module methods perform this conversion?

Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.

Show both answers

SkillScore blends 4 signalsno signals yet

BenchmarkRun a verified benchmark with positive lift

Live evalNeeds ≥10 evaluated traces in 30 days

AI ratingNeeds ≥10 rated traces

AdoptionNeeds ≥10 serves across ≥2 orgs in 30 days

Efficiency · separate axis (at equal correctness)+0% turns+26% tokens

Shown for transparency; not credited unless a verified run shows no correctness regression.

No signals yet — run a benchmark or collect evaluated traces to earn a score.

Verified on gemini-3.6-flash · re-tested 22 days ago

Other measured skills in the registry, with their headline benchmark lift.