magnus/agent-skills
Watch
1
1
Fork
You've already forked agent-skills
 0
Code Issues Pull requests Projects Releases 5 Packages Wiki Activity Actions

feat: add data-architect skill #2

Merged
magnus merged 1 commit from feat/data-architect-skill into main 2026-05-21 22:34:16 -04:00
Conversation 1 Commits 1 Files changed 12 +1568
jasper commented 2026-05-21 22:33:54 -04:00
Contributor
Copy link

Summary

A virtual data architect skill for teams who don't have access to a human architect. Designed for data engineers who may not know what questions to ask — includes a QuickScan, proactive discovery flow, and "I don't know where to start" mode.

What's included

11 files, ~1500 lines total:

  • SKILL.md — Activation persona with symptom-based triggers, QuickScan (8 yes/no diagnostic questions), proactive discovery flow, consulting patterns, and boundaries
  • references/architecture-patterns.md — Kimball vs Inmon vs Data Vault vs Lakehouse decision framework with Mermaid decision trees
  • references/cloud-platform-comparison.md — Snowflake vs BigQuery vs Redshift vs Databricks with Mermaid selection tree
  • references/vendor-evaluation.md — Data catalog, ETL, and orchestration comparisons with Mermaid selection tree
  • references/governance-maturity.md — DAMA-DMBOK framework + 6-stage maturity model
  • references/anti-patterns.md — 13 named anti-patterns with symptoms, root causes, and remediations
  • references/compliance-by-framework.md — GDPR, HIPAA, CCPA, SOX, PCI DSS, BCBS 239 with industry cross-reference
  • references/case-studies.md — 6 real-world architecture transformations
  • references/discovery-framework.md — 5-phase consulting process for architecture engagements
  • scripts/governance-assessment.py — Interactive 15-question maturity assessment
  • templates/adr-template.md — Architecture Decision Record template

Privacy

All files have been scrubbed of personal or identifying information. Zero personal references detected across all 11 files.

## Summary A virtual data architect skill for teams who don't have access to a human architect. Designed for data engineers who may not know what questions to ask — includes a QuickScan, proactive discovery flow, and "I don't know where to start" mode. ## What's included **11 files, ~1500 lines total:** - `SKILL.md` — Activation persona with symptom-based triggers, QuickScan (8 yes/no diagnostic questions), proactive discovery flow, consulting patterns, and boundaries - `references/architecture-patterns.md` — Kimball vs Inmon vs Data Vault vs Lakehouse decision framework with Mermaid decision trees - `references/cloud-platform-comparison.md` — Snowflake vs BigQuery vs Redshift vs Databricks with Mermaid selection tree - `references/vendor-evaluation.md` — Data catalog, ETL, and orchestration comparisons with Mermaid selection tree - `references/governance-maturity.md` — DAMA-DMBOK framework + 6-stage maturity model - `references/anti-patterns.md` — 13 named anti-patterns with symptoms, root causes, and remediations - `references/compliance-by-framework.md` — GDPR, HIPAA, CCPA, SOX, PCI DSS, BCBS 239 with industry cross-reference - `references/case-studies.md` — 6 real-world architecture transformations - `references/discovery-framework.md` — 5-phase consulting process for architecture engagements - `scripts/governance-assessment.py` — Interactive 15-question maturity assessment - `templates/adr-template.md` — Architecture Decision Record template ## Privacy All files have been scrubbed of personal or identifying information. Zero personal references detected across all 11 files.
A virtual data architect for teams without one. Includes:
- 8 reference files covering architecture patterns, cloud platforms,
  governance maturity, anti-patterns, compliance, vendor evaluation,
  case studies, and discovery frameworks
- Interactive governance maturity assessment script
- ADR template for capturing architecture decisions
- 4 Mermaid decision trees for common architecture choices
- QuickScan and proactive discovery flow for users who don't know
  where to start

No personal or identifying information included.
magnus merged commit 2058db71d2 into main 2026-05-21 22:34:16 -04:00
jasper reviewed 2026-05-21 22:45:38 -04:00
jasper left a comment
Copy link

Review Summary

Jasper (automated review)

PR is already merged — this is a post-merge review for awareness.

Issues Found

  1. Typo: Extra space in Q8 (data-architect/SKILL.md, line ~113)
    **Q8 : Schema management.** has a space before the colon. Q1-Q7 use **Q1:, **Q2: etc. without the space.

  2. Dead code in governance-assessment.py — json_prompt() function is defined but never called. The JSON mode handling in main() just prints an error and returns. Either remove the dead function or implement JSON output.

  3. Documentation mismatch — SKILL.md says --json output is "Planned" but the script actually accepts --json (returning an error message). These are inconsistent.

Positive Notes

  • Excellent depth and breadth of reference material (~1500 lines across 11 files)
  • Clean YAML frontmatter with description, compatibility, and metadata
  • Mermaid decision trees in architecture-patterns, cloud-platform-comparison, and vendor-evaluation
  • Good anti-pattern naming with practical remediations
  • Privacy-scrubbed as claimed
  • No hardcoded secrets, paths, or credentials
  • ADR template and governance assessment script add real session value
  • README entry is well-written and descriptive

Verdict

No blocking issues. The nits above are minor and can be addressed in a follow-up PR if desired.

## Review Summary **Jasper (automated review)** PR is already merged — this is a post-merge review for awareness. ### Issues Found 1. **Typo: Extra space in Q8** (`data-architect/SKILL.md`, line ~113) `**Q8 : Schema management.**` has a space before the colon. Q1-Q7 use `**Q1:`, `**Q2:` etc. without the space. 2. **Dead code in governance-assessment.py** — `json_prompt()` function is defined but never called. The JSON mode handling in `main()` just prints an error and returns. Either remove the dead function or implement JSON output. 3. **Documentation mismatch** — SKILL.md says `--json` output is "Planned" but the script actually accepts `--json` (returning an error message). These are inconsistent. ### Positive Notes - Excellent depth and breadth of reference material (~1500 lines across 11 files) - Clean YAML frontmatter with description, compatibility, and metadata - Mermaid decision trees in architecture-patterns, cloud-platform-comparison, and vendor-evaluation - Good anti-pattern naming with practical remediations - Privacy-scrubbed as claimed - No hardcoded secrets, paths, or credentials - ADR template and governance assessment script add real session value - README entry is well-written and descriptive ### Verdict No blocking issues. The nits above are minor and can be addressed in a follow-up PR if desired.
Sign in to join this conversation.
Reviewers
No reviewers
Labels
Clear labels   
community-feedback
Originates from community review

  
enhancement
New feature or request

  
skill-upgrade
Skill enhancement or refactor

No labels
community-feedback
enhancement
skill-upgrade
Milestone
Clear milestone
No items
No milestone
Projects
Clear projects
No items
No project
Assignees
Clear assignees
No assignees
1 participant
Notifications
Due date
The due date is invalid or out of range. Please use the format "yyyy-mm-dd".

No due date set.

Dependencies

No dependencies set

Reference
magnus/agent-skills!2
No description provided.