Is the Architecting Data skill free?

Yes. The skill itself is free from ancoleman/ai-design-components. SkillProof publishes the install command and an independent test verdict at no cost.

What is the Architecting Data SkillProof Score?

8.4/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 7/10, docs & honesty 4/5.

How do I install Architecting Data?

Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.

Can I use Architecting Data with Cursor, Copilot, Gemini CLI, Codex or other AI tools?

The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.

Architecting Data

Decision frameworks for data lake vs warehouse vs lakehouse, table formats, mesh readiness

by ancoleman · ancoleman/ai-design-components

Tested · Works

Install — copy the command Download source ↗

Test report

Verdict: Tested · Works
Score: 8.4/10
Tested: Jul 21, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Aug 10, 2026 · 4953514

Fetched SKILL.md at skills/architecting-data/SKILL.md; frontmatter parses with name+description. Spot-checked 3 referenced files raw (references/decision-frameworks.md, references/medallion-pattern.md, examples/dbt-project/stg_customers.sql) — all HTTP 200; no security smells. For the output test I wrote both a baseline and a strictly skill-following answer to one task (120-person SaaS, 4-person data team, mixed BI+ML on Postgres, cost-sensitive, mesh?). Baseline hedged (warehouse-or-lakehouse, mesh "probably premature"); the skill run applied the 6-factor mesh readiness score (~13/30 → "Build foundation first"), landed decisively on Lakehouse+Iceberg via the decision tree and 50-500 org bracket with cost figures, and specified bronze/silver/gold with dimensional-vs-wide modeling.

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

Installs cleanly 5/5
Triggers reliably 5/5
Output vs. baseline 7/10
Docs & honesty 4/5

What Architecting Data does

Advisory skill that guides data-platform architecture decisions: storage paradigm (lake/warehouse/lakehouse), modeling approach (dimensional/normalized/data vault/wide), open table format (Iceberg/Delta/Hudi), medallion layering, and a 6-factor data-mesh readiness score. Triggers when designing or modernizing a data platform, choosing centralized vs decentralized patterns, or selecting table formats and governance. Pure knowledge plus reference files and a dbt example; no external tools required to use it.

How to install Architecting Data

git clone --depth 1 https://github.com/ancoleman/ai-design-components.git /tmp/architecting-data-src
mkdir -p ~/.claude/skills
cp -R /tmp/architecting-data-src/skills/architecting-data ~/.claude/skills/architecting-data
# No dependencies. Pure-knowledge skill: SKILL.md + references/*.md + examples/dbt-project.
# Repo also ships an interactive ./install.sh (installs all 76 skills) if you want the full set.

Skills live in ~/.claude/skills/ (global) or .claude/skills/ (per-project). Restart Claude Code after installing.

Commands — how to trigger Architecting Data

/architecting-data Decision frameworks for data lake vs warehouse vs lakehouse, table formats, mesh readiness

It also activates on plain-language prompts like these:

Should we use a lakehouse or warehouse here
Design a medallion architecture for this data
Choose between Iceberg and Delta Lake for us

Frequently asked questions

Is the Architecting Data skill free?: Yes. The skill itself is free from ancoleman/ai-design-components. SkillProof publishes the install command and an independent test verdict at no cost.
Does Architecting Data work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 21, 2026. Verdict: Tested · Works. Fetched SKILL.md at skills/architecting-data/SKILL.md; frontmatter parses with name+description. Spot-checked 3 referenced files raw (references/decision-frameworks.md, references/medallion-pattern.md, examples/dbt-project/stg_customers.sql) — all HTTP 200; no security smells. For the output test I wrote both a baseline and a strictly skill-following answer to one task (120-person SaaS, 4-person data team, mixed BI+ML on Postgres, cost-sensitive, mesh?). Baseline hedged (warehouse-or-lakehouse, mesh "probably premature"); the skill run applied the 6-factor mesh readiness score (~13/30 → "Build foundation first"), landed decisively on Lakehouse+Iceberg via the decision tree and 50-500 org bracket with cost figures, and specified bronze/silver/gold with dimensional-vs-wide modeling.
What is the Architecting Data SkillProof Score?: 8.4/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 7/10, docs & honesty 4/5.
How do I install Architecting Data?: Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
Can I use Architecting Data with Cursor, Copilot, Gemini CLI, Codex or other AI tools?: The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.