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.
npx skills add alivirgo/Major-AI-Skills --skill duckdbgit clone --depth 1 https://github.com/alivirgo/Major-AI-SkillsWrote 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.
[](https://agentmods.dev/skills/alivirgo/major-ai-skills/duckdb)<a href="https://agentmods.dev/skills/alivirgo/major-ai-skills/duckdb"><img src="https://agentmods.dev/badge/skills/alivirgo/major-ai-skills/duckdb/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.
<a href="https://agentmods.dev/skills/alivirgo/major-ai-skills/duckdb"><img src="https://agentmods.dev/badge/skills/alivirgo/major-ai-skills/duckdb.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00045 | $0.01263 |
| Opus 5.5 | $0.00018 | $0.00505 |
| Sonnet 5.5 | $0.00009 | $0.00253 |
| Haiku 4.5 | $0.00005 | $0.00126 |
Grade A, and why
duckdb 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 22d 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.
How it starts
The opening of the file, as written. The whole thing — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DuckDB Analytical SQL AI Skill Guide
Overview & Engine Architecture
DuckDB is an embedded columnar OLAP engine: runs in-process (Python/R/JDBC/CLI), vectorized execution, reads Parquet/CSV/JSON directly without a server. Ideal for notebooks, CI data checks, and local lake queries—not a substitute for fleet-scale warehouse serving.
Parquet/CSV/S3 (httpfs)
-> DuckDB in-process
-> SQL (join/window/aggregate)
-> Arrow/DataFrame / COPY export
Optional .duckdb file for persistent views
When to use / when not to
Use when
- Ad-hoc SQL on local or lake files; replacing heavy pandas groupbys
- CI validation of datasets (row counts, schema contracts)
- Prototyping transforms before
@dbton Snowflake/BigQuery
Do not use when
- Many concurrent writers or multi-tenant serving layer needed (
@postgresql,@snowflake) - Data exceeds single-node RAM without spill tuning—consider
@sparkor warehouse - Untrusted remote URLs without reviewing
httpfscredential scope
Operational Capabilities & Agent Directives
- Connection safety: One writer per
.duckdbfile; useread_onlyconnections for parallel readers; avoid NFS locking surprises. - Remote access:
INSTALL httpfs; LOAD httpfs;only when needed; secrets via env vars (AWS_*), never committed keys. - Performance: Project columns early; predicate pushdown on
read_parquet; useEXPLAIN ANALYZEon slow queries. - Resource limits:
PRAGMA threads=N; PRAGMA memory_limit='4GB';on shared CI runners to prevent OOM kills. - Schema drift:
union_by_name=trueon multi-file Parquet; explicit casts in views for stable contracts. - Backup/migration:
.duckdbis a file—copy while no writer or use export; Parquet lake remains source of truth for immutable pipelines. - Exactly-once myth: DuckDB does not coordinate distributed exactly-once; downstream pipelines still need idempotent loads.
Production examples
Parquet analytics
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 22d ago Changed · +54 lines · +13 tokens per session 86bca7ff1cfa
- 1mo ago Changed df07903f9705
- 1mo ago First seen · 99 lines · 32 tokens per session scan A 450633e72911
duckdb is a skill published in the GitHub repository alivirgo/Major-AI-Skills (2 stars, last pushed yesterday), licensed MIT. It adds 45 tokens to every session and 1,263 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-05.
Other skills, from other repositories
duckdb
Use when analytical SQL must run in-process with no server: Parquet/CSV/JSON/Arrow queried in place, OLAP embedded in an app or notebook, a slow pandas groupby on multi-GB data, or S3/lakehouse data read without downloading. NOT a multi-user analytics server (that is clickhouse-analytics), NOT an app's transactional…
analytical-databases-expert
Design and query columnar analytical stores: DuckDB, ClickHouse and cloud warehouses, including file formats, partitioning, sort keys and cost control. Use when the user mentions DuckDB, ClickHouse, Parquet, columnar storage, OLAP, a data warehouse or lakehouse, analytical queries over large tables, or when the task…
accounting-software-selection
Scores shortlisted accounting packages against 57 evidence-backed fields, emitted as CSV, SQL, JSON Schema or Notion on request. Use for choosing accounting software.
360-feedback-system
360 feedback register: reviewer, subject, review cycle, visibility, due date and score, as CSV, SQL, JSON Schema or Notion on request. Use for 360 reviews or peer feedback cycles.
access-matrix
Access matrix of role-by-module permissions, with per-role scope, confidentiality level and SME tier, as CSV, SQL, JSON Schema or Notion on request. Use for access reviews.
admin-access-register
Admin account register: system, main and backup admin, seats, plan, 2FA, shared logins and access-review dates, as CSV, SQL, JSON Schema or Notion on request. Use for access reviews.