New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Suggesting Dbt Bouncer Checks

by godatadriven in godatadriven/dbt-bouncer

Analyzes a dbt project and suggests dbt-bouncer checks that already pass (for existing projects) or a sensible starter config (for greenfield projects).

MITAuto-check passedData & Analytics

Install Suggesting Dbt Bouncer Checks

skills CLI
$ npx skills add godatadriven/dbt-bouncer --skill suggesting-dbt-bouncer-checks -a claude-code

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

GitHub CLI
$ gh skill install godatadriven/dbt-bouncer suggesting-dbt-bouncer-checks --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/godatadriven/dbt-bouncer.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/suggesting-dbt-bouncer-checks .claude/skills/suggesting-dbt-bouncer-checks && 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
suggesting-dbt-bouncer-checks
GitHub stars
136
Token cost
~1k tokens
SKILL.md length
460 words
Files
3 (incl. references)
Skills in repo
3
Repo updated
First seen
Licence
MIT

At a glance

Analyzes a dbt project and suggests dbt-bouncer checks that already pass (for existing projects) or a sensible starter config (for greenfield projects).

  • Works in 6 steps: Inspect the project. Read… → Codify what is already true. Suggest… → Scope aggressively. Use include/exclude… → …
  • Adding dbt-bouncer to a project
  • SKILL.md covers Additional Resources, Prerequisites, Workflow: existing project… and Workflow: new project…, plus 1 more section
  • Calls dbt and pip

What it does

Suggesting Dbt Bouncer Checks is an agent skill from godatadriven/dbt-bouncer. Analyzes a dbt project and suggests dbt-bouncer checks that already pass (for existing projects) or a sensible starter config (for greenfield projects). Use when adding dbt-bouncer to a project, creating or extending a dbt-bouncer.yml config, or enforcing dbt conventions with dbt-bouncer.

Its SKILL.md is about 1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 3 other files, including reference files (for example `references/check-catalog.md` and `references/config-reference.md`).

It sits in Data & Analytics, covering Data pipelines and ETL. It works with dbt and Python. The repository describes itself as: Configure and enforce conventions for your dbt project. The licence is MIT.

When your agent uses it

  • Adding dbt-bouncer to a project
  • Extending a dbt-bouncer.yml config
  • Enforcing dbt conventions with dbt-bouncer

Example prompts

  • “Use the suggesting-dbt-bouncer-checks skill to analyz a dbt project and suggests dbt-bouncer checks that already pass (for existing projects) or a…”
  • “/suggesting-dbt-bouncer-checks”

Requirements

  • Python 3

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

  1. Inspect the project. Read dbt_project.yml, the models/ directory layout, and a sample of model .yml property files. Identify
  2. Codify what is already true. Suggest checks that formalize existing conventions, e.g. if all staging models start with stg_, suggest…
  3. Scope aggressively. Use include/exclude (regex on file path) to limit each check to where the convention actually holds.
  4. Use severity: warn for aspirational checks. Checks the team wants but doesn't yet satisfy should be warnings, either per-check or globally…
  5. Validate before proposing. Always run dbt-bouncer run against the drafted config and iterate until it exits 0 (warnings are acceptable…
  6. Present the config with rationale. For each suggested check, state in one line which observed convention it codifies.

What it can do on your machine

Read from SKILL.md and the folder at commit 07a2359. 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

    Shell commands in SKILL.md call:

    • dbt
    • pip

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

  • Network

    No URLs in SKILL.md. Its commands use pip, which can reach the network depending on how they are called.

    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

Suggesting Dbt Bouncer Checks loads about 1k tokens when it runs, and up to ~2.1k if it reads all its reference files. Until then it costs about 80 tokens; SKILL.md has 460 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~80
When it runs · the whole SKILL.md, loaded when a task matches
~1k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~2.1k

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 godatadriven/dbt-bouncer at commit 07a2359, republished under its MIT licence (© godatadriven). 460 words, ~1,016 tokens.

Download SKILL.mdSave it as .claude/skills/suggesting-dbt-bouncer-checks/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.
name
suggesting-dbt-bouncer-checks
description
Analyzes a dbt project and suggests dbt-bouncer checks that already pass (for existing projects) or a sensible starter config (for greenfield projects). Use when adding dbt-bouncer to a project, creating or extending a dbt-bouncer.yml config, or enforcing dbt conventions with dbt-bouncer.
user-invocable
true
metadata.author
godatadriven

Suggest dbt-bouncer checks for a dbt project

dbt-bouncer enforces conventions in dbt projects by running checks against dbt artifacts (manifest.json, catalog.json, run_results.json). This skill helps you propose a dbt-bouncer.yml config tailored to a project.

Additional Resources

Prerequisites

  • dbt-bouncer installed (pip install dbt-bouncer).
  • A manifest.json in the project's target/ directory. If missing, run dbt parse (fast, does not hit the warehouse).
  • catalog.json is only needed for catalog_checks (requires dbt docs generate). Prefer manifest_checks when the catalog is unavailable.

Workflow: existing project (brownfield)

The golden rule: suggested checks must pass against the current project. Never suggest a config that breaks CI on day one.

  1. Inspect the project. Read dbt_project.yml, the models/ directory layout, and a sample of model .yml property files. Identify:
    • Layer structure (e.g. staging/, intermediate/, marts/) and naming prefixes (stg_, int_).
    • Documentation habits (are descriptions populated? which layers?).
    • Testing habits (unique/not_null on marts? relationship tests?).
    • Source conventions (freshness, loader, file naming).
  2. Codify what is already true. Suggest checks that formalize existing conventions, e.g. if all staging models start with stg_, suggest check_model_names with model_name_pattern: ^stg_ and include: ^models/staging.
  3. Scope aggressively. Use include/exclude (regex on file path) to limit each check to where the convention actually holds.
  4. Use severity: warn for aspirational checks. Checks the team wants but doesn't yet satisfy should be warnings, either per-check or globally at the top of the config.
  5. Validate before proposing. Always run dbt-bouncer run against the drafted config and iterate until it exits 0 (warnings are acceptable, errors are not). Do not modify any model SQL or YAML to make a check pass — adjust the check's scope or severity instead.
  6. Present the config with rationale. For each suggested check, state in one line which observed convention it codifies.
Show full SKILL.md (154 more words)Show less

Workflow: new project (greenfield)

No existing conventions to respect, so suggest an opinionated baseline:

  1. Start from the low-controversy checks in check-catalog.md: naming per layer, lineage rules between layers, check_model_has_properties_file, check_model_description_populated, check_model_has_unique_test, source freshness/loader checks.
  2. Match the config to the project's planned layer structure (ask the user if unclear).
  3. Set coverage checks (check_model_documentation_coverage, check_model_test_coverage) with achievable thresholds that can be ratcheted up later.
  4. Recommend wiring dbt-bouncer into pre-commit and CI so conventions are enforced from the first model.

Guardrails

  • Never edit models, sources, seeds, or property files to satisfy a check unless the user explicitly asks.
  • Only suggest check names that exist in the installed dbt-bouncer version. Verify with the documentation or by running the drafted config — unknown check names fail config validation.
  • Prefer manifest_checks over catalog_checks/run_results_checks unless the corresponding artifacts are freshly generated.
  • One convention per check entry; the same check name can appear multiple times with different include scopes.

© godatadriven, 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 2 other files (references) in skills/suggesting-dbt-bouncer-checks of godatadriven/dbt-bouncer.

  • SKILL.md
  • references/check-catalog.md
  • references/config-reference.md

Open the folder on GitHubat commit 07a2359

Compare with similar skills

Suggesting Dbt Bouncer Checks 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.

Suggesting Dbt Bouncer Checks compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Suggesting Dbt Bouncer Checks this skillgodatadriven/dbt-bouncer136—~1kAutomated safety check: PassMIT
Dbt Parser Refreshyu-iskw/dbt-artifacts-parser118—~716Automated safety check: PassApache-2.0
Package Version Bumpyu-iskw/dbt-artifacts-parser118—~700Automated safety check: PassApache-2.0
Data Quality Frameworkswshobson/agents40k11 repos~1.1kAutomated safety check: PassMIT
Senior Data Engineerbenchflow-ai/skillsbench1.8k—~5.9kAutomated safety check: PassMIT
Senior Data Engineeralirezarezvani/claude-skills28k3 repos~1.4kAutomated safety check: PassMIT

Similar skills

  • Dbt Parser Refresh

    yu-iskw/dbt-artifacts-parser

    Refreshes dbt artifact schemas from dbt-labs/dbt-core and regenerates Pydantic parser classes.

    118 GitHub stars~716 tokensUpdated 3 days ago
    Data & AnalyticsAuto-check passed

  • Package Version Bump

    yu-iskw/dbt-artifacts-parser

    Bumps the dbt-artifacts-parser package semver, prepares a PyPI release, and aligns GitHub Releases with version.

    118 GitHub stars~700 tokensUpdated 3 days ago
    Data & AnalyticsAuto-check passed

  • Data Quality Frameworks

    wshobson/agents

    Sets up data quality checks with Great Expectations, dbt tests and data contracts, with checkpoints and pass-fail reports for pipelines.

    40k GitHub starsUsed in 11 repos~1.1k tokens
    Data & AnalyticsAuto-check passed

  • Senior Data Engineer

    benchflow-ai/skillsbench

    World-class data engineering skill for building scalable data pipelines, ETL/ELT systems, real-time streaming, and data infrastructure.

    1.8k GitHub stars~5.9k tokensUpdated 2 mo ago
    Data & AnalyticsAuto-check passed

  • Senior Data Engineer

    alirezarezvani/claude-skills

    Data engineering skill for building scalable data pipelines, ETL/ELT systems, and data infrastructure.

    28k GitHub starsUsed in 3 repos~1.4k tokens
    Data & AnalyticsAuto-check passed

  • Senior Data Engineer

    davila7/claude-code-templates

    World-class data engineering skill for building scalable data pipelines, ETL/ELT systems, and data infrastructure.

    33k GitHub starsUsed in 1 repo~1.4k tokens
    Data & AnalyticsAuto-check passed

More from godatadriven/dbt-bouncer

  • New Check

    godatadriven/dbt-bouncer

    Scaffold a new dbt-bouncer check class with tests. An agent skill from godatadriven/dbt-bouncer.

    136 GitHub stars~1.1k tokensUpdated yesterday
    Auto-check passed

  • Build Artifacts

    godatadriven/dbt-bouncer

    Regenerate dbt test fixtures after dbtproject changes. An agent skill from godatadriven/dbt-bouncer.

    136 GitHub stars~399 tokensUpdated yesterday
    Auto-check passed

Works with

Categories

Questions about Suggesting Dbt Bouncer Checks

What does Suggesting Dbt Bouncer Checks do?

Analyzes a dbt project and suggests dbt-bouncer checks that already pass (for existing projects) or a sensible starter config (for greenfield projects). Suggesting Dbt Bouncer Checks is an agent skill from godatadriven/dbt-bouncer. Analyzes a dbt project and suggests dbt-bouncer checks that already pass (for existing projects) or a sensible starter config (for greenfield projects).

When should I use Suggesting Dbt Bouncer Checks?

Suggesting Dbt Bouncer Checks fits situations like: adding dbt-bouncer to a project; extending a dbt-bouncer.yml config; enforcing dbt conventions with dbt-bouncer.

How do I install Suggesting Dbt Bouncer Checks in Claude Code?

Run `npx skills add godatadriven/dbt-bouncer --skill suggesting-dbt-bouncer-checks -a claude-code`. Or copy the skill folder (skills/suggesting-dbt-bouncer-checks in godatadriven/dbt-bouncer) into .claude/skills/suggesting-dbt-bouncer-checks in your project. Claude Code loads it when a task matches its description.

How do I install Suggesting Dbt Bouncer Checks in Codex?

Run `npx skills add godatadriven/dbt-bouncer --skill suggesting-dbt-bouncer-checks -a codex`. Or copy the skill folder (skills/suggesting-dbt-bouncer-checks in godatadriven/dbt-bouncer) into .agents/skills/suggesting-dbt-bouncer-checks in your project. Codex loads it when a task matches its description.

Can I use Suggesting Dbt Bouncer Checks 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 godatadriven/dbt-bouncer --skill suggesting-dbt-bouncer-checks -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/suggesting-dbt-bouncer-checks, .gemini/skills/suggesting-dbt-bouncer-checks, .github/skills/suggesting-dbt-bouncer-checks and .opencode/skills/suggesting-dbt-bouncer-checks in your project.

What does Suggesting Dbt Bouncer Checks need to run?

Going by SKILL.md and its folder, Suggesting Dbt Bouncer Checks needs the command-line tools its instructions call (dbt and pip). Our summary lists: Python 3.

Does Suggesting Dbt Bouncer Checks access the network?

SKILL.md contains no URLs. Its commands use pip, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Suggesting Dbt Bouncer Checks 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 Suggesting Dbt Bouncer Checks use?

Suggesting Dbt Bouncer Checks 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 Suggesting Dbt Bouncer Checks use?

About 1k tokens (SKILL.md is roughly 4.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 1.1k tokens, read only when the agent opens those files.

What are the alternatives to Suggesting Dbt Bouncer Checks?

Skills that share tags, products or a category with Suggesting Dbt Bouncer Checks: Dbt Parser Refresh (yu-iskw/dbt-artifacts-parser, 118 stars), Package Version Bump (yu-iskw/dbt-artifacts-parser, 118 stars), Data Quality Frameworks (wshobson/agents, 40k stars) and Senior Data Engineer (benchflow-ai/skillsbench, 1.8k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Suggesting Dbt Bouncer Checks?

godatadriven (a GitHub organization) maintains it in godatadriven/dbt-bouncer, which has 136 GitHub stars. The repository holds 3 skills in this directory. The repository was last updated on October 9, 2026.

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