Agent skill

New Check

by godatadriven in godatadriven/dbt-bouncer

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

Install New Check

skills CLI

$ npx skills add godatadriven/dbt-bouncer --skill new-check -a claude-code

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

GitHub CLI

$ gh skill install godatadriven/dbt-bouncer new-check --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/.agents/skills/new-check .claude/skills/new-check && 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/

Paste into Claude Code

Install the "new-check" agent skill from https://github.com/godatadriven/dbt-bouncer/tree/main/.agents/skills/new-check into .claude/skills/new-check/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "new-check", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/godatadriven/dbt-bouncer/tree/main/.agents/skills/new-check

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add godatadriven/dbt-bouncer --skill new-check -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install godatadriven/dbt-bouncer new-check --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/godatadriven/dbt-bouncer.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.agents/skills/new-check .agents/skills/new-check && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "new-check" agent skill from https://github.com/godatadriven/dbt-bouncer/tree/main/.agents/skills/new-check into .agents/skills/new-check/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "new-check", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add godatadriven/dbt-bouncer --skill new-check -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install godatadriven/dbt-bouncer new-check --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/godatadriven/dbt-bouncer.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.agents/skills/new-check .cursor/skills/new-check && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "new-check" agent skill from https://github.com/godatadriven/dbt-bouncer/tree/main/.agents/skills/new-check into .cursor/skills/new-check/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "new-check", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/godatadriven/dbt-bouncer.git --path .agents/skills/new-check

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add godatadriven/dbt-bouncer --skill new-check -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install godatadriven/dbt-bouncer new-check --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/godatadriven/dbt-bouncer.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.agents/skills/new-check .gemini/skills/new-check && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "new-check" agent skill from https://github.com/godatadriven/dbt-bouncer/tree/main/.agents/skills/new-check into .gemini/skills/new-check/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "new-check", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install godatadriven/dbt-bouncer new-check

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add godatadriven/dbt-bouncer --skill new-check -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/godatadriven/dbt-bouncer.git skills-src && mkdir -p .github/skills && cp -r skills-src/.agents/skills/new-check .github/skills/new-check && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "new-check" agent skill from https://github.com/godatadriven/dbt-bouncer/tree/main/.agents/skills/new-check into .github/skills/new-check/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "new-check", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add godatadriven/dbt-bouncer --skill new-check -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install godatadriven/dbt-bouncer new-check --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/godatadriven/dbt-bouncer.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.agents/skills/new-check .opencode/skills/new-check && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "new-check" agent skill from https://github.com/godatadriven/dbt-bouncer/tree/main/.agents/skills/new-check into .opencode/skills/new-check/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "new-check", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: new-check
GitHub stars: 136
Token cost: ~1.1k tokens
SKILL.md length: 378 words
Files: 1
Skills in repo: 3
Repo updated: Oct 9, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

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

Works in 6 steps: Determine Check Location → Write the Check → Decorator API Reference → …
Tasks that involve Data pipelines and ETL
SKILL.md covers 1. Determine Check Location, 2. Write the Check, 3. Decorator API Reference and 4. Register the Check, plus 2 more sections
Calls mise

What it does

New Check is an agent skill from godatadriven/dbt-bouncer. Scaffold a new dbt-bouncer check class with tests

Its SKILL.md is about 1.1k 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 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

Tasks that involve Data pipelines and ETL

Example prompts

“/new-check”

Requirements

Python 3

Workflow steps

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

Determine Check Location
Write the Check
Decorator API Reference
Register the Check
Write Tests
Verify

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:
- mise
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

New Check loads about 1.1k tokens when it runs. Until then it costs about 15 tokens; SKILL.md has 378 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~15
When it runs · the whole SKILL.md, loaded when a task matches: ~1.1k

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). 378 words, ~1,149 tokens.

Download SKILL.mdSave it as .claude/skills/new-check/SKILL.md (or your agent's skills folder).

name: new-check
description: Scaffold a new dbt-bouncer check class with tests

Create a New Check

Follow these steps to add a new check to dbt-bouncer.

1. Determine Check Location

Category: manifest, catalog, or run_results?
Resource type: model, source, seed, exposure, macro, etc.?
File: place in the appropriate submodule under src/dbt_bouncer/checks/<category>/.

2. Write the Check

Use the @check decorator, passing the rule code. Everything else is inferred from the function signature:

python

from dbt_bouncer.check_framework.decorator import check, fail

@check(code="XX000")
def check_model_xxx(model):
    """Check description."""
    if some_condition:
        fail(f"`{model.unique_id}` failed because ...")

3. Decorator API Reference

code is the only argument @check takes. All other metadata is inferred from the function signature:

code — the check's unique rule code, e.g. MO048. See "Assign a rule code" below.
name — the function name (must match the name: value in YAML config).
iterate_over — the first positional parameter (excluding ctx). If there are none, the check is global (runs once with context only).
params — keyword-only arguments (after *) become user-configurable Pydantic fields.
ctx — optional; only include in the signature if the function actually uses it.
Parameter ordering — must be (resource, ctx, *, params). Resource first, ctx second. Putting ctx before the resource breaks iterate_over inference. For context-only checks, use (ctx, *, params).

Simple check (resource only)

python

@check(code="MO021")
def check_model_description_populated(model):
    """Models must have a populated description."""
    if not model.description or len(model.description.strip()) < 4:
        fail(f"`{model.unique_id}` does not have a populated description.")

Check with params

python

@check(code="MO038")
def check_model_names(model, *, model_name_pattern: str):
    """Models must have a name matching the supplied regex."""
    import re
    if not re.match(model_name_pattern, model.name, re.IGNORECASE):
        fail(f"`{model.unique_id}` does not match pattern `{model_name_pattern}`.")

Context-only check (no resource iteration)

python

@check(code="MO044")
def check_model_test_coverage(ctx, *, min_model_test_coverage_pct: float = 100):
    """Set the minimum percentage of models that have at least one test."""
    ...

`fail()` — raises `DbtBouncerFailedCheckError`

python

fail("message")

Show full SKILL.md (192 more words)Show less

Assign a rule code

Every check needs a unique rule code: a 2-letter resource prefix plus a 3-digit number, e.g. MO048. Two steps:

Pass it to the decorator: @check(code="MO048").
Add the matching member to the resource's *RuleCode enum in src/dbt_bouncer/enums.py, keeping alphabetical order:
python
```
class ModelRuleCode(StrEnum):
    CHECK_MODEL_XXX = "MO048"
```

Use the next free number for the prefix — read the enum to find it. Never reuse or renumber a published code; users reference codes in their config.

Prefixes: CA catalog, EX exposure, LI lineage, MA macro, ME metadata, MO model, RR run results, SE seed, SM semantic model, SN snapshot, SO source, TE test, UT unit test.

4. Register the Check

Add the check to dbt-bouncer-example.yml
Validate: dbt-bouncer run --config-file dbt-bouncer-example.yml
Ensure alphabetical ordering is maintained

5. Write Tests

Use check_passes / check_fails from dbt_bouncer.testing:

python

from dbt_bouncer.testing import check_fails, check_passes

def test_pass():
    check_passes("check_model_xxx", model={"name": "valid"}, my_param="value")

def test_fail():
    check_fails("check_model_xxx", model={"name": "invalid"}, my_param="value")

# For context-dependent checks:
def test_with_context():
    check_passes("check_model_xxx",
                 model={"name": "m1"},
                 ctx_models=[{"name": "m1"}, {"name": "m2"}])

Resource dicts are auto-merged with sensible defaults (no fixture setup needed)
ctx_* kwargs build the CheckContext automatically
Include at least one happy path and one unhappy path test
Ensure __init__.py exists in the test subdirectory

6. Verify

bash

mise run generate-schema
mise run generate-rule-codes-doc
mise run test-unit
prek run --all-files

The rule-codes-doc-check hook fails if a check has no code, if a declared code is unused, or if docs/checks/rule_codes.md has drifted.

Files

Just SKILL.md in .agents/skills/new-check of godatadriven/dbt-bouncer.

Open the folder on GitHubat commit 07a2359

Compare with similar skills

New Check 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.

New Check compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
New Check this skillgodatadriven/dbt-bouncer	136	—	~1.1k	Automated safety check: Pass	MIT	yesterday
Dbt Parser Refreshyu-iskw/dbt-artifacts-parser	118	—	~716	Automated safety check: Pass	Apache-2.0	3 days ago
Package Version Bumpyu-iskw/dbt-artifacts-parser	118	—	~700	Automated safety check: Pass	Apache-2.0	3 days ago
Data Quality Frameworkswshobson/agents	40k	11 repos	~1.1k	Automated safety check: Pass	MIT	6 days ago
Senior Data Engineerbenchflow-ai/skillsbench	1.8k	—	~5.9k	Automated safety check: Pass	MIT	2 mo ago
Senior Data Engineeralirezarezvani/claude-skills	28k	3 repos	~1.4k	Automated safety check: Pass	MIT	1 mo ago

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

Questions about New Check

What does New Check do?

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

When should I use New Check?

New Check fits situations like: tasks that involve Data pipelines and ETL.

How do I install New Check in Claude Code?

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

How do I install New Check in Codex?

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

Can I use New Check 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 new-check -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/new-check, .gemini/skills/new-check, .github/skills/new-check and .opencode/skills/new-check in your project.

What does New Check need to run?

Going by SKILL.md and its folder, New Check needs the command-line tools its instructions call (mise). Our summary lists: Python 3.

Does New Check 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 New Check 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 New Check use?

New Check 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 New Check use?

About 1.1k tokens (SKILL.md is roughly 4.6k 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 New Check?

Skills that share tags, products or a category with New Check: 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 New Check?

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.

Install New Check

Facts

At a glance

What it does

When your agent uses it

Example prompts

Requirements

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

Create a New Check

1. Determine Check Location

2. Write the Check

3. Decorator API Reference

Simple check (resource only)

Check with params

Context-only check (no resource iteration)

fail() — raises DbtBouncerFailedCheckError

Assign a rule code

4. Register the Check

5. Write Tests

6. Verify

Files

Compare with similar skills

Similar skills

More from godatadriven/dbt-bouncer

Related

Questions about New Check

`fail()` — raises `DbtBouncerFailedCheckError`