duckdb-sql

duckdb-sql is a skill for Claude Code, Codex from malue-ai/dazee-small. It costs 26 tokens per session (682 once invoked), scanned A, original, MIT.

A tool for running SQL queries directly on CSV, Parquet, and JSON files. DuckDB is a small database engine that can read these files without importing them into a database first.

In plain words
What is it for?
Use it to filter and summarize datasets, calculate aggregates, compare files, join data from multiple files, and use features such as window functions.
Why use it?
It avoids setting up a database and makes large-file analysis and complex queries easier than manually processing rows.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to filter and summarize datasets, calculate aggregates, compare files, join data from multiple files, and use features such as window functions.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/malue-ai/dazee-small/duckdb-sql
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add malue-ai/dazee-small --skill duckdb-sql
Clone the repo
git clone --depth 1 https://github.com/malue-ai/dazee-small

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for duckdb-sql

README.md
[![agentmods](https://agentmods.dev/badge/skills/malue-ai/dazee-small/duckdb-sql/github.svg)](https://agentmods.dev/skills/malue-ai/dazee-small/duckdb-sql)
Your own site
<a href="https://agentmods.dev/skills/malue-ai/dazee-small/duckdb-sql"><img src="https://agentmods.dev/badge/skills/malue-ai/dazee-small/duckdb-sql/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for duckdb-sql

Your own site · 80×15
<a href="https://agentmods.dev/skills/malue-ai/dazee-small/duckdb-sql"><img src="https://agentmods.dev/badge/skills/malue-ai/dazee-small/duckdb-sql.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 26 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 682 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00026 $0.00682
Opus 5 $0.00013 $0.00341
Sonnet 5 $0.00005 $0.00136
Haiku 4.5 $0.00003 $0.00068

Measured 9d ago against content hash 1de3182690e1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

duckdb-sql scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/library/duckdb-sql/SKILL.md · 100 lines

What it actually says

DuckDB SQL 分析引擎

用 SQL 直接查询 CSV、Parquet、JSON 文件,无需导入数据库。适合大数据集分析。

使用场景

  • 用户说「用 SQL 分析这个 CSV 文件」「这个数据集有多少行」
  • 数据量大(>10万行),excel-analyzer 处理较慢时
  • 用户需要复杂聚合、JOIN、窗口函数等 SQL 功能
  • 用户说「对比这两个 CSV 文件的差异」

与 excel-analyzer 的区别

工具 擅长 局限
excel-analyzer 小数据集、图表、格式化输出 大数据集慢
duckdb-sql 大数据集、复杂 SQL、多文件 JOIN 不做格式化输出

执行方式

Python API

import duckdb

con = duckdb.connect()

# 直接查询 CSV
result = con.sql("SELECT * FROM 'data.csv' LIMIT 10").fetchdf()

# 聚合分析
result = con.sql("""
    SELECT category, COUNT(*) as count, AVG(price) as avg_price
    FROM 'sales.csv'
    GROUP BY category
    ORDER BY count DESC
""").fetchdf()

# 多文件 JOIN
result = con.sql("""
    SELECT o.order_id, c.name, o.total
    FROM 'orders.csv' o
    JOIN 'customers.csv' c ON o.customer_id = c.id
    WHERE o.total > 1000
""").fetchdf()

# 查询 Parquet
result = con.sql("SELECT * FROM 'data.parquet' WHERE year = 2026").fetchdf()

# 通配符查询多文件
result = con.sql("SELECT * FROM 'logs/*.csv'").fetchdf()

命令行用法

# 安装
pip install duckdb

# 交互式
python3 -c "import duckdb; print(duckdb.sql(\"SELECT count(*) FROM 'data.csv'\").fetchone())"

常用分析模式

-- 数据概览
SUMMARIZE SELECT * FROM 'data.csv';

-- 去重计数
SELECT COUNT(DISTINCT user_id) FROM 'events.csv';

-- 窗口函数:排名
SELECT *, RANK() OVER (PARTITION BY department ORDER BY salary DESC) as rank
FROM 'employees.csv';

-- 导出结果
COPY (SELECT * FROM 'data.csv' WHERE status = 'active') TO 'output.csv';

输出规范

  • 查询结果以表格格式展示(前 20 行 + 总行数)
  • 大结果集自动截断,提示用户添加 LIMIT
  • 查询耗时超过 5 秒时显示进度提示
Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 9d ago First seen · 100 lines · 26 tokens per session scan A 1de3182690e1

Subscribe to this mod's changes

duckdb-sql is a skill published in the GitHub repository malue-ai/dazee-small (36 stars, last pushed 5mo ago), licensed MIT. It adds 26 tokens to every session and 682 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

Related

Other skills, from other repositories

create-pr

Creates a GitHub PR with a Linear-ticket-prefixed title and a decision-led, narrative description for Prisma 8. Use when the user wants to create a pull request, open a PR, or submit changes for review.

prisma/orm · 48 tokens

schema-exploration

Lists tables, describes columns and data types, identifies foreign key relationships, and maps entity relationships in a database. Use when the user asks about database schema, table structure, column types, what tables exist, ERD, foreign keys, or how entities relate.

langchain-ai/deepagents · 57 tokens

ha-data-stores

Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…

shiwenwen/hope-agent · 115 tokens

nornicdb-cypher-queries

Pick fast, predictable Cypher query shapes in NornicDB — point lookups, batch retrieval, pagination, search, traversal, batched UNWIND/MERGE writes, cleanup, multi-tenant isolation. Use when writing or reviewing Cypher whose latency or throughput matters; maps user intent to the executor's hot-path query templates.

orneryd/NornicDB · 79 tokens

supabase

Supabase / PostgREST Row-Level-Security playbook — pull the anon (or leaked servicerole) key out of the frontend JS, map tables from the auto-generated OpenAPI spec, test anonymous RLS READ disclosures (PII/secret leaks), and anonymous RLS WRITE abuse (insert/update/delete — e.g. forging…

PentesterFlow/agent · 120 tokens

volcengine-rds-postgresql

A tool for operating PostgreSQL databases hosted by Volcano Engine's managed database service. PostgreSQL is a relational database used to store structured application data.

bytedance/agentkit-samples · 63 tokens