A workflow for stabilizing a converted ETL unit, where ETL means a process that extracts, transforms, and loads data. It supports units from tools such as SSIS and Informatica and records the result in the migration registry.

It runs scans, creates a work plan, performs test-driven fixes across pipeline steps and dbt projects, and continues until final validation is clean.

It gives the converted pipeline a defined testing and repair stage before deployment, instead of treating conversion as finished code.

migrate-etl — Skill for Claude Code by sfc-gh-dflippo

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 sfc-gh-dflippo/snowflake-dbt-demo --skill migrate-etl

Clone the repo

git clone --depth 1 https://github.com/sfc-gh-dflippo/snowflake-dbt-demo

Made for: Claude Code.

Or install snowflake-migration, the plugin that ships this one along with the rest of its 72 skills, 7 agents.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/sfc-gh-dflippo/snowflake-dbt-demo/migrate-etl/github.svg)](https://agentmods.dev/skills/sfc-gh-dflippo/snowflake-dbt-demo/migrate-etl)

Your own site

<a href="https://agentmods.dev/skills/sfc-gh-dflippo/snowflake-dbt-demo/migrate-etl"><img src="https://agentmods.dev/badge/skills/sfc-gh-dflippo/snowflake-dbt-demo/migrate-etl/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/sfc-gh-dflippo/snowflake-dbt-demo/migrate-etl"><img src="https://agentmods.dev/badge/skills/sfc-gh-dflippo/snowflake-dbt-demo/migrate-etl.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 45 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,850 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.

Model	Per session	Once invoked
Fable 5.1	$0.00045	$0.02850
Opus 5	$0.00023	$0.01425
Sonnet 5	$0.00009	$0.00570
Haiku 4.5	$0.00005	$0.00285

Measured 2d ago against content hash 4fdae7d6a3c0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

migrate-etl 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 2d 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.

.claude/skills/snowflake-migration/skills/migration/migrate-objects/migrate-etl/SKILL.md · 137 lines

How it starts

The opening of the file, as written. The whole thing — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Migrate ETL

Wraps actions/etl-stabilization/SKILL.md so it runs as a state-machine task on a single ETL code unit.

The platform of an ETL code unit is recorded on its registry entry as source.platform (ssis, informatica, …). etl-stabilization already covers every supported platform via per-platform profiles in actions/etl-stabilization/platforms/. This skill does not replicate that work — it only:

Resolves the converted-artifacts folder and source-definition paths from the registry entry.
Invokes etl-stabilization against them.
Updates codeStatus.stabilization on the registry entry when etl-stabilization finishes (or the unit is excluded).

Scope

Stabilization for this version means: run etl-stabilization until its Final Validation phase reports clean. That covers everything etl-stabilization does — scan, ROADMAP, phased TDD across orchestration elements and dbt sub-projects, EWI fixes, etc.

After stabilization: the unit advances to deploy. Deploying the stabilized ETL to Snowflake is handled by scai code deploy through the deploy tool (see Step 4), not by this skill and not by hand-running snow. Deploy is no longer terminal for ETL — once deployed, the unit advances to etlSeed and etlValidate to compare the live source package against the Snowflake output.

This skill is the orchestrated (registry-backed) entry point for ETL stabilization. It claims the unit and records the result on the registry, then delegates the actual fixing to etl-stabilization.

Step 0: Claim Ownership

The ETL unit must be claimed before stabilization begins, so it is registered in MIGRATION_REGISTRY.claims, shows the current user as owner, and appears in my_objects_summary alongside SQL objects. Resolve <etl_id> first: the executor passes object_id; if entered by name ("fix ETL package …"), locate the unit via migration_status(mode="my_objects_summary") (already-claimed) or migration_status(mode="next_objects") (not yet claimed).

Read the full file on GitHub · 137 lines

Files

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.

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.

2d ago First seen · 137 lines · 45 tokens per session scan A 4fdae7d6a3c0

Subscribe to this mod's changes

migrate-etl is a skill published in the GitHub repository sfc-gh-dflippo/snowflake-dbt-demo (33 stars, last pushed 3d ago), licensed Apache-2.0. It adds 45 tokens to every session and 2,850 once invoked, about $0.0002 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 2026-09-10.

Data and AI TDD Testing

writing-evals

Scaffolds evaluation suites for the Axiom AI SDK. Generates eval files, scorers, flag schemas, and config from natural-language descriptions. Use when creating evals, writing scorers, setting up flag schemas, or configuring axiom.config.ts.

openclaw/clawhub · 55 tokens

ai-observability-promptfoo

Testing and evaluation framework for LLM prompts and applications -- promptfooconfig.yaml, assertions, model-graded evals, red teaming, CI/CD integration, custom providers, and comparative evaluation.

agents-inc/skills · 46 tokens

evo-simpo-loss

Implement the SimPO (Simple Preference Optimization) loss function for the SimPOTrainer class. Use when reproducing the SimPO paper's loss computation, injecting the simpoloss method into simpotrainer.py, running unit tests, and generating validated loss outputs.

Zhang-Henry/CoEvoSkills · 60 tokens

migrate-etl