Official agent skill

Convert File

by duckdb in duckdb/duckdb-skills

Convert any data file to another format: CSV, Parquet, JSON, Excel, GeoJSON, and more.

OfficialMITAuto-check: notesDocuments & Office

Install Convert File

skills CLI
$ npx skills add duckdb/duckdb-skills --skill convert-file -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install duckdb/duckdb-skills convert-file --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/duckdb/duckdb-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/convert-file .claude/skills/convert-file && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
convert-file
GitHub stars
599
Used in
1 other repo
Token cost
~720 tokens
SKILL.md length
305 words
Files
1
Skills in repo
8
Repo updated
First seen
Licence
MIT

At a glance

Convert any data file to another format: CSV, Parquet, JSON, Excel, GeoJSON, and more.

  • Works in 3 steps: Resolve input and output → Convert → Report
  • The user says convert to parquet
  • SKILL.md covers Step 1 — Resolve input and…, Step 2 — Convert and Step 3 — Report
  • Calls duckdb

What it does

Convert File is an agent skill from duckdb/duckdb-skills, published by the product's own GitHub organization. Convert any data file to another format: CSV, Parquet, JSON, Excel, GeoJSON, and more. Use when the user says "convert to parquet", "save as xlsx", "export as JSON", "make this a CSV", "turn into parquet", or any variation of format-to-format conversion for data files. Also triggers when the user wants to write Parquet, Excel, or other binary formats that Claude cannot produce natively.

Its SKILL.md is about 720 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Documents & Office, covering Excel spreadsheets, DataFrames and CSV and tabular files. It works with Microsoft Excel and DuckDB. The licence is MIT.

When your agent uses it

  • The user says convert to parquet
  • Make this a CSV
  • Turn into parquet
  • Any variation of format-to-format conversion for data files

Example prompts

  • “convert to parquet”
  • “save as xlsx”
  • “export as JSON”
  • “/convert-file”

Requirements

  • Pre-approved tools (allowed-tools): Bash

Workflow steps

3 steps, taken from the step headings in SKILL.md.

  1. Resolve input and output
  2. Convert
  3. Report

What it can do on your machine

Read from SKILL.md and the folder at commit 7feda8e. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Bash

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • duckdb

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Convert File loads about 720 tokens when it runs. Until then it costs about 101 tokens; SKILL.md has 305 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~101
When it runs · the whole SKILL.md, loaded when a task matches
~720

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

  • NotePre-approves every shell command (allowed-tools: Bash)SKILL.md
    allowed-tools: Bash

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from duckdb/duckdb-skills at commit 7feda8e, republished under its MIT licence (© duckdb). 305 words, ~720 tokens.

Download SKILL.mdSave it as .claude/skills/convert-file/SKILL.md (or your agent's skills folder).
name
convert-file
description
Convert any data file to another format: CSV, Parquet, JSON, Excel, GeoJSON, and more. Use when the user says "convert to parquet", "save as xlsx", "export as JSON", "make this a CSV", "turn into parquet", or any variation of format-to-format conversion for data files. Also triggers when the user wants to write Parquet, Excel, or other binary formats that Claude cannot produce natively.
allowed-tools
Bash
argument-hint
<input-file> [output-file]

You are helping the user convert a data file from one format to another using DuckDB.

Input file: $0 Output file: ${1:-}

Step 1 — Resolve input and output

Input: $0. If it's a bare filename (no /), resolve to a full path with find "$PWD" -name "$0" -not -path '*/.git/*' 2>/dev/null | head -1.

Output: If $1 is provided, use it as the output path. If not, default to the same stem as the input with a .parquet extension (e.g., data.csv → data.parquet).

Infer the output format from the output file extension:

ExtensionFormat clause
.parquet, .pq(default, no clause needed)
.csv(FORMAT csv, HEADER)
.tsv(FORMAT csv, HEADER, DELIMITER '\t')
.json(FORMAT json, ARRAY true)
.jsonl, .ndjson(FORMAT json, ARRAY false)
.xlsx(FORMAT xlsx) — requires INSTALL excel; LOAD excel;
.geojson(FORMAT GDAL, DRIVER 'GeoJSON') — requires LOAD spatial;
.gpkg(FORMAT GDAL, DRIVER 'GPKG') — requires LOAD spatial;
.shp(FORMAT GDAL, DRIVER 'ESRI Shapefile') — requires LOAD spatial;

Step 2 — Convert

Run a single DuckDB command. Prepend extension loads as needed based on both the input and output formats.

bash
duckdb -c "
<EXTENSION_LOADS>
COPY (FROM '<INPUT_PATH>') TO '<OUTPUT_PATH>' <FORMAT_CLAUSE>;
"

For remote inputs (s3://, https://, etc.), prepend the same protocol setup as read-file:

ProtocolPrepend
s3://LOAD httpfs; CREATE SECRET (TYPE S3, PROVIDER credential_chain);
gs:// / gcs://LOAD httpfs; CREATE SECRET (TYPE GCS, PROVIDER credential_chain);
https:// / http://LOAD httpfs;

If the user mentions partitioning (e.g., "partition by year"), add PARTITION_BY (col) to the format clause. This only works with Parquet and CSV output.

If the user mentions compression (e.g., "use zstd"), add CODEC 'zstd' for Parquet output.

Step 3 — Report

On success, report:

  • Input file and detected format
  • Output file, format, and size (ls -lh)
  • Row count if quick to compute

On failure:

  • duckdb: command not found → delegate to /duckdb-skills:install-duckdb
  • Missing extension → install it and retry
  • Input parse error → suggest the user check the input format or try /duckdb-skills:read-file first to inspect it

© duckdb, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/convert-file of duckdb/duckdb-skills.

Open the folder on GitHubat commit 7feda8e

Used in 1 other repository

We found 1 copy of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in duckdb/duckdb-skills, which our catalogue first saw on October 7, 2026.

Compare with similar skills

Convert File next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Convert File compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Convert File this skillduckdb/duckdb-skills5991 repos~720Automated safety check: NotesMIT
Excel ParserHarryoung/efka104—~2.3kAutomated safety check: PassApache-2.0
Sn Da Image CaptionMichaelYang-lyx/AIDABench1111 repos~2kAutomated safety check: PassNone
Generate CodebookAperivue/medsci-skills329—~1.1kAutomated safety check: PassMIT
Tabular Cleanupgaasher/Agent-Loop-Skills174—~4kAutomated safety check: PassMIT
Matlab Import Export Datamatlab/matlab-agentic-toolkit1.1k—~3.6kAutomated safety check: PassCustom licence

Similar skills

  • Excel Parser

    Harryoung/efka

    Smart Excel/CSV file parsing with intelligent routing based on file complexity analysis.

    104 GitHub stars~2.3k tokensUpdated 6 mo ago
    Documents & OfficeAuto-check passed
  • Sn Da Image Caption

    MichaelYang-lyx/AIDABench

    图片理解与数据提取 skill。当图片文件(.png/.jpg/.jpeg/.gif/.webp/.bmp)是主要输入且用户需要理解、提取数据或分析图片内容时使用。提供预配置的 caption 脚本(scripts/caption.py),通过 vision 模型将图片转为文本描述,无需额外配置 API Key。覆盖:(1) 通过 scripts/caption.py…

    111 GitHub starsUsed in 1 repo~2k tokens
    Documents & OfficeAuto-check passed
  • Generate Codebook

    Aperivue/medsci-skills

    A skill your agent uses when a tabular dataset (CSV, Excel, Parquet, Stata, SAS) needs a data dictionary.

    329 GitHub stars~1.1k tokensUpdated 2 days ago
    Documents & OfficeAuto-check passed
  • Tabular Cleanup

    gaasher/Agent-Loop-Skills

    A skill your agent uses when the user has a messy tabular data dump (CSV/TSV/parquet/Excel/JSON) and wants it iteratively cleaned to an inferred data contract — a checklist of deterministic…

    174 GitHub stars~4k tokensUpdated 3 mo ago
    Documents & OfficeAuto-check passed
  • Matlab Import Export Data

    matlab/matlab-agentic-toolkit

    Read or write data files in MATLAB. An agent skill from matlab/matlab-agentic-toolkit.

    1.1k GitHub stars~3.6k tokensUpdated 7 days ago
    Documents & OfficeAuto-check passed
  • Codebook

    brycewang-stanford/Auto-Empirical-Research-Skills

    Auto-generates a Markdown codebook from a dataset (CSV, DTA, Excel, Parquet) with types and summary statistics.

    4.5k GitHub stars~527 tokensUpdated 2 days ago
    Documents & OfficeAuto-check: notes

More from duckdb/duckdb-skills

All 8 skills in this repo
  • Spatial

    duckdb/duckdb-skills

    Official

    Answer questions about spatial data using DuckDB. An agent skill from duckdb/duckdb-skills.

    599 GitHub starsUsed in 1 repo~1k tokens
    Auto-check: notes
  • S3 Explore

    duckdb/duckdb-skills

    Official

    Explore and query data on S3, Cloudflare R2, GCS, MinIO, or any S3-compatible storage.

    599 GitHub starsUsed in 1 repo~848 tokens
    Auto-check: notes
  • Read File

    duckdb/duckdb-skills

    Official

    Read any data file (CSV, JSON, Parquet, Avro, Excel, spatial, SQLite) or remote URL (S3, HTTPS).

    599 GitHub starsUsed in 1 repo~917 tokens
    Auto-check: notes
  • Attach DB

    duckdb/duckdb-skills

    Official

    Attach a DuckDB database file for use with /duckdb-skills:query.

    599 GitHub starsUsed in 1 repo~1.2k tokens
    Auto-check: notes
  • Duckdb Docs

    duckdb/duckdb-skills

    Official

    Search DuckDB and DuckLake documentation and blog posts. An agent skill from duckdb/duckdb-skills.

    599 GitHub starsUsed in 1 repo~1.4k tokens
    Auto-check: notes
  • Query

    duckdb/duckdb-skills

    Official

    Run SQL queries against the attached DuckDB database or ad-hoc against files.

    599 GitHub starsUsed in 1 repo~2k tokens
    Auto-check: notes

Questions about Convert File

What does Convert File do?

Convert any data file to another format: CSV, Parquet, JSON, Excel, GeoJSON, and more. Convert File is an agent skill from duckdb/duckdb-skills, published by the product's own GitHub organization. Convert any data file to another format: CSV, Parquet, JSON, Excel, GeoJSON, and more.

When should I use Convert File?

Convert File fits situations like: the user says convert to parquet; make this a CSV; turn into parquet; any variation of format-to-format conversion for data files.

How do I install Convert File in Claude Code?

Run `npx skills add duckdb/duckdb-skills --skill convert-file -a claude-code`. Or copy the skill folder (skills/convert-file in duckdb/duckdb-skills) into .claude/skills/convert-file in your project. Claude Code loads it when a task matches its description.

How do I install Convert File in Codex?

Run `npx skills add duckdb/duckdb-skills --skill convert-file -a codex`. Or copy the skill folder (skills/convert-file in duckdb/duckdb-skills) into .agents/skills/convert-file in your project. Codex loads it when a task matches its description.

Can I use Convert File in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add duckdb/duckdb-skills --skill convert-file -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/convert-file, .gemini/skills/convert-file, .github/skills/convert-file and .opencode/skills/convert-file in your project.

What does Convert File need to run?

Going by SKILL.md and its folder, Convert File needs the command-line tools its instructions call (duckdb). Its frontmatter pre-approves these tools: Bash.

Does Convert File access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Convert File safe to install?

Our automated static check of SKILL.md found notes only (pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.

What licence does Convert File use?

Convert File is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Convert File use?

About 720 tokens (SKILL.md is roughly 2.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Convert File?

Skills that share tags, products or a category with Convert File: Excel Parser (Harryoung/efka, 104 stars), Sn Da Image Caption (MichaelYang-lyx/AIDABench, 111 stars), Generate Codebook (Aperivue/medsci-skills, 329 stars) and Tabular Cleanup (gaasher/Agent-Loop-Skills, 174 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Convert File?

duckdb (a GitHub organization, an official publisher) maintains it in duckdb/duckdb-skills, which has 599 GitHub stars. The repository holds 8 skills in this directory. The repository was last updated on April 23, 2026.

Source: duckdb/duckdb-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.