Agent skill

Tinybird Datafile Rules

by TryGhost in TryGhost/Ghost

Rules for writing Tinybird datasources, pipes, endpoints and materialized views, with SQL constraints, optimization habits and deduplication patterns.

MITAuto-check passedDatabases

Install Tinybird Datafile Rules

skills CLI
$ npx skills add TryGhost/Ghost --skill tinybird -a claude-code

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

GitHub CLI
$ gh skill install TryGhost/Ghost tinybird --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/TryGhost/Ghost.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/tinybird .claude/skills/tinybird && 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
tinybird
GitHub stars
55k
Token cost
~417 tokens
SKILL.md length
157 words
Files
15
Skills in repo
7
Repo updated
First seen
Licence
MIT

At a glance

Rules for writing Tinybird datasources, pipes, endpoints and materialized views, with SQL constraints, optimization habits and deduplication patterns.

  • Creating or editing Tinybird datasource, pipe or connection files
  • SKILL.md covers When to Apply, Rule Files and Quick Reference
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
  • Optimizing an endpoint's SQL query

What it does

The skill applies when creating, editing or reviewing Tinybird resources such as `.datasource`, `.pipe` and `.connection` files, writing or tuning SQL, designing endpoint schemas, organizing project layers, or working with materialized views and copy pipes. It points to fourteen rule files covering project files, build and deploy, datasources, pipes, endpoints, materialized views and join prefilters, sinks, copy files, connections, SQL, endpoint optimization, tests and deduplication.

A quick reference gives the key behaviors: local project files are the source of truth, the build target comes from `dev_mode` in `tinybird.config.json`, and `tb deploy` targets Tinybird Cloud production. Commands like `tb sql` and `tb logs` default to local unless `--cloud` or a branch option is given. SQL is SELECT-only, with Tinybird templating rules and strict parameter handling. MergeTree is the default engine and AggregatingMergeTree suits materialized targets. Queries should filter early, select only needed columns and push complex work later in the pipeline.

When your agent uses it

  • Creating or editing Tinybird datasource, pipe or connection files
  • Optimizing an endpoint's SQL query
  • Designing a materialized view or copy pipe
  • Adding deduplication to a Tinybird data model

Example prompts

  • “Add a pipe that counts page views per day and expose it as an endpoint.”
  • “Review this pipe file and tighten the SQL so it filters early and selects fewer columns.”
  • “Create a materialized view that aggregates member signups by hour.”

Requirements

  • The Tinybird CLI (`tb`) and a Tinybird project

What it can do on your machine

Read from SKILL.md and the folder at commit 7aecaf7. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    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

Tinybird Datafile Rules loads about 417 tokens when it runs. Until then it costs about 36 tokens; SKILL.md has 157 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~36
When it runs · the whole SKILL.md, loaded when a task matches
~417

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 passed

The automated check found no risky patterns in SKILL.md.

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 TryGhost/Ghost at commit 7aecaf7, republished under its MIT licence (© TryGhost). 157 words, ~417 tokens.

Download SKILL.mdSave it as .claude/skills/tinybird/SKILL.md (or your agent's skills folder). This skill also uses 14 other files; get the full folder from GitHub.
name
tinybird
description
Tinybird file formats, SQL rules, optimization patterns, and best practices for datasources, pipes, endpoints, and materialized views.

Tinybird Best Practices

Guidance for Tinybird file formats, SQL rules, optimization patterns, and data modeling. Use this skill when creating or editing Tinybird datafiles.

When to Apply

  • Creating or updating Tinybird resources (.datasource, .pipe, .connection)
  • Writing or optimizing SQL queries
  • Designing endpoint schemas and data models
  • Organizing project structure and data layers
  • Working with materialized views or copy pipes
  • Implementing deduplication patterns
  • Reviewing or refactoring Tinybird project files

Rule Files

  • rules/project-files.md
  • rules/build-deploy.md
  • rules/datasource-files.md
  • rules/pipe-files.md
  • rules/endpoint-files.md
  • rules/materialized-files.md
  • rules/materialized-join-prefilter.md
  • rules/sink-files.md
  • rules/copy-files.md
  • rules/connection-files.md
  • rules/sql.md
  • rules/endpoint-optimization.md
  • rules/tests.md
  • rules/deduplication-patterns.md

Quick Reference

  • Project local files are the source of truth.
  • Build target comes from tinybird.config.json dev_mode (local or branch).
  • tb deploy targets Tinybird Cloud production.
  • Commands like tb sql and tb logs default to local unless --cloud or --branch=<branch-name> is set.
  • SQL is SELECT-only with Tinybird templating rules and strict parameter handling.
  • Use MergeTree by default; AggregatingMergeTree for materialized targets.
  • Filter early, select only needed columns, push complex work later in the pipeline.

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

Files

SKILL.md and 14 other files in .agents/skills/tinybird of TryGhost/Ghost.

  • SKILL.md
  • rules/build-deploy.md
  • rules/connection-files.md
  • rules/copy-files.md
  • rules/datasource-files.md
  • rules/deduplication-patterns.md
  • rules/endpoint-files.md
  • rules/endpoint-optimization.md
  • rules/materialized-files.md
  • rules/materialized-join-prefilter.md
  • rules/pipe-files.md
  • rules/project-files.md
  • rules/sink-files.md
  • rules/sql.md
  • rules/tests.md

Open the folder on GitHubat commit 7aecaf7

Compare with similar skills

Tinybird Datafile Rules 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.

Tinybird Datafile Rules compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Tinybird Datafile Rules this skillTryGhost/Ghost55k—~417Automated safety check: PassMIT
SQL Optimization InterviewerPrepLabsAI/InterviewMentor112—~2.1kAutomated safety check: PassMIT
Optimizing Query By IdAltimateAI/data-engineering-skills127—~919Automated safety check: PassMIT
Optimizing Query TextAltimateAI/data-engineering-skills127—~1.7kAutomated safety check: PassMIT
Analyzing Dataastronomer/agents450—~1.3kAutomated safety check: PassApache-2.0
Optimizing Databricks SQLAltimateAI/data-engineering-skills127—~6.7kAutomated safety check: PassMIT

Similar skills

  • SQL Optimization Interviewer

    PrepLabsAI/InterviewMentor

    A Data Engineering interviewer focused on database performance.

    112 GitHub stars~2.1k tokensUpdated today
    DatabasesAuto-check passed
  • Optimizing Query By Id

    AltimateAI/data-engineering-skills

    Optimizes Snowflake query performance using query ID from history.

    127 GitHub stars~919 tokensUpdated 6 days ago
    DatabasesAuto-check passed
  • Optimizing Query Text

    AltimateAI/data-engineering-skills

    Optimizes Snowflake SQL query performance from provided query text.

    127 GitHub stars~1.7k tokensUpdated 6 days ago
    DatabasesAuto-check passed
  • Analyzing Data

    astronomer/agents

    Queries the data warehouse with SQL and answers business questions about data.

    450 GitHub stars~1.3k tokensUpdated 2 days ago
    DatabasesAuto-check passed
  • Optimizing Databricks SQL

    AltimateAI/data-engineering-skills

    Analyze DBSQL queries, including SQL embedded in notebooks (spark.sql(...), %sql cells), for anti-patterns, lint issues, and performance problems, using Databricks-specific dialect and platform…

    127 GitHub stars~6.7k tokensUpdated 6 days ago
    DatabasesAuto-check passed
  • Snowflake Development

    sickn33/agentic-awesome-skills

    Comprehensive Snowflake development assistant covering SQL best practices, data pipeline design (Dynamic Tables, Streams, Tasks, Snowpipe), Cortex AI functions, Cortex Agents, Snowpark Python, dbt…

    47k GitHub starsUsed in 2 repos~2.1k tokens
    DatabasesAuto-check passed

More from TryGhost/Ghost

  • Moves a package from another TryGhost repository into Ghost as an internal workspace package while keeping its Git history, with checkpoints for the steps that need an administrator.

    55k GitHub stars~3.8k tokensUpdated today
    Auto-check passed
  • Moves a legacy internal Ghost package from JavaScript and CommonJS to TypeScript and ESM in three focused commits that keep git file history intact.

    55k GitHub stars~1.2k tokensUpdated today
    Auto-check passed
  • Adds a private developer-experiments feature flag to Ghost, covering the backend registration, the Labs settings toggle and the test snapshot updates.

    55k GitHub stars~486 tokensUpdated today
    Auto-check passed
  • Guidance for running the Tinybird tb CLI: choosing local, branch or cloud workflows, building and deploying, loading data, handling tokens and secrets, and CI/CD.

    55k GitHub stars~388 tokensUpdated today
    Auto-check passed
  • Ghost Commit Workflow

    TryGhost/Ghost

    Guides the agent through making a focused git commit in the Ghost repository: inspect state, stage only relevant files, follow the contributing rules, then verify.

    55k GitHub stars~286 tokensUpdated today
    Auto-check passed
  • Admin7 Feature Flags

    TryGhost/Ghost

    Add, consume, review, or remove Admin 7 milestone flags using Ghost's existing Labs conventions.

    55k GitHub stars~169 tokensUpdated today
    Auto-check passed

Works with

Questions about Tinybird Datafile Rules

What does Tinybird Datafile Rules do?

Rules for writing Tinybird datasources, pipes, endpoints and materialized views, with SQL constraints, optimization habits and deduplication patterns. connection` files, writing or tuning SQL, designing endpoint schemas, organizing project layers, or working with materialized views and copy pipes. It points to fourteen rule files covering project files, build and deploy, datasources, pipes, endpoints, materialized views and join prefilters, sinks, copy files, connections, SQL, endpoint optimization, tests and deduplication.

When should I use Tinybird Datafile Rules?

Tinybird Datafile Rules fits situations like: creating or editing Tinybird datasource, pipe or connection files; optimizing an endpoint's SQL query; designing a materialized view or copy pipe; adding deduplication to a Tinybird data model.

How do I install Tinybird Datafile Rules in Claude Code?

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

How do I install Tinybird Datafile Rules in Codex?

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

Can I use Tinybird Datafile Rules 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 TryGhost/Ghost --skill tinybird -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/tinybird, .gemini/skills/tinybird, .github/skills/tinybird and .opencode/skills/tinybird in your project.

What does Tinybird Datafile Rules need to run?

SKILL.md names no scripts, command-line tools or credentials: Tinybird Datafile Rules is instructions for the agent only. Our summary lists: The Tinybird CLI (`tb`) and a Tinybird project.

Does Tinybird Datafile Rules 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 Tinybird Datafile Rules safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Tinybird Datafile Rules use?

Tinybird Datafile Rules 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 Tinybird Datafile Rules use?

About 417 tokens (SKILL.md is roughly 1.7k 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 Tinybird Datafile Rules?

Skills that share tags, products or a category with Tinybird Datafile Rules: SQL Optimization Interviewer (PrepLabsAI/InterviewMentor, 112 stars), Optimizing Query By Id (AltimateAI/data-engineering-skills, 127 stars), Optimizing Query Text (AltimateAI/data-engineering-skills, 127 stars) and Analyzing Data (astronomer/agents, 450 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Tinybird Datafile Rules?

TryGhost (a GitHub organization) maintains it in TryGhost/Ghost, which has 55,493 GitHub stars. The repository holds 7 skills in this directory. The repository was last updated on October 7, 2026.

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