Data lifecycle
Skill Methasit-Pun/data_engineer_claude_skills/00-start-here/data-lifecycle
Practical guides, prompts, and Python code for applying Anthropic's Claude Skills to data engineering and pipeline automation
npx -y skills add Methasit-Pun/data_engineer_claude_skills --skill data-lifecycleAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
2 things to look at
- no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
- 1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Umbrella skill for running a data project end-to-end through its lifecycle stages — discover sources → profile the data → architect the platform → build the medallion pipeline → refactor the code. Use this whenever the user is kicking off a new data project, asks "where do I start" or "what are the steps", or is somewhere mid-lifecycle and unsure which stage skill applies. This skill ROUTES to the stage sub-skills (data-sourcing, data-profiling, data-architecture, medallion-design, notebook-refactor) and sequences them, pulling in the right one for the user's current stage.
SKILL.md
2.7 KB, 529 tokens by cl100k_base, as published. Nobody here has run it
Data Project Lifecycle (Router)
This is a router skill covering a data project from "we have an objective" to "the code is clean." Figure out which stage the user is in, then invoke the matching stage skill with the Skill tool. A greenfield project runs the stages in order; a mid-flight project jumps to its stage.
The lifecycle
| Stage | Question it answers | Invoke sub-skill |
|---|---|---|
| 1. Discover | What data do I need and where do I get it? | data-sourcing |
| 2. Profile | What does the data actually look like? (checks + ER) | data-profiling |
| 3. Architect | How should the whole platform be structured, on what infra, at what cost? | data-architecture |
| 4. Build | Design the bronze/silver/gold pipeline, gold-first | medallion-design |
| 5. Refactor | Make the resulting notebook/code reviewable | notebook-refactor |
Routing rules
- "New project / where do I start" → begin at stage 1 (
data-sourcing) and proceed in order, confirming each stage's output before advancing. - User already has data in hand → start at stage 2 (
data-profiling). - Sources + shape known, needs a plan → stage 3 (
data-architecture). - Architecture decided, ready to build layers → stage 4 (
medallion-design). - Working code that's messy → stage 5 (
notebook-refactor) — can run anytime, independent of the others. - Invoke by name, e.g.
Skill(skill="data-architecture"). For a task spanning stages, invoke each in sequence and carry the output forward.
How this router relates to the others
The lifecycle produces work that the topic routers deepen:
- Stage 3
data-architecturedelegates cloud + cost to → [[cloud-data-infra]] - Stage 4
medallion-designdefers pipeline mechanics to → [[data-pipelines]] and the model to → [[data-modeling]] - Profiling & building both hand validation/governance to → [[data-reliability]]
- ML objectives branch to → [[ml-feature-engineering]]
Use this router for "what stage am I in"; use the topic routers for "go deep on pipelines/modeling/reliability/cloud."
What ships with it
Read from the repository
Just SKILL.md. No reference files, no scripts.
Gives 0 of the 12 instructions most architecture codebase skills give in 529 tokens
Counted across 811 of the 1,134 authors here whose files we hold, read 2026-08-07
- Ask the user which candidate to explorein 45 of 811, across 15 files
- Apply the deletion test to suspected shallow modulesin 43 of 811, across 15 files
- Read any relevant architecture decision records firstin 31 of 811, across 8 files
- Use exact glossary terms in every suggestionin 30 of 811, across 10 files
- Accept dependencies instead of creating themin 24 of 811, across 5 files
- Include before and after visualisations for each candidatein 24 of 811, across 5 files
- Read the domain glossary before exploringin 24 of 811, across 6 files
- Return results instead of producing side effectsin 23 of 811, across 4 files
- Explore the codebase for shallow modules and frictionin 23 of 811, across 3 files
- Introduce seams only where things varyin 22 of 811, across 3 files
- Reduce the number of methodsin 21 of 811, across 2 files
- Design deep modules with small interfacesin 21 of 811, across 3 files
Said here and by no other author read
- identify the user's current data project stage
- invoke the matching stage skill via the Skill tool
- run greenfield project stages sequentially
- jump mid-flight projects to their current stage
- confirm a stage's output before advancing to the next
- invoke each required skill by name
Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.