SkillsAdd

hainrixz/claude-db

stack-detect

Detects the database stack(s) of a project — paradigm, engine, ORM, platform, and the authoritative source_of_truth — by wrapping scripts/detect-stack.mjs.

First seen Jun 17, 2026

Installation

$ npx skills add hainrixz/claude-db --skill stack-detect
View on skills.sh ↗ GitHub repository ↗

Summary

  • Detects the database stack(s) of a project — paradigm, engine, ORM, platform, and the authoritative source_of_truth — by wrapping scripts/detect-stack.mjs.
  • Emits the stacks array plus routing (which paradigm profile and module set each stack drives) and the source_of_truth precedence.
  • Never guesses an engine; an empty result routes to /claude-db:start.
  • Invoked by db-orchestrator (Phase 1); not usually called directly.

Similar popular skills

Related neighbors and high-traction skills in the same topics — useful to compare before installing.

supabase-postgres-best-practices Shared topics
supabase/agent-skills

Postgres best practices maintained by Supabase, for Postgres running anywhere. Load this skill …

391.6K installs
prisma-cli Shared topics
prisma/skills

Prisma ORM CLI commands reference covering init, generate, migrate, db, dev, complete, studio, …

267K installs
supabase Shared topics
supabase/agent-skills

Use when doing ANY task involving Supabase. Triggers: Supabase products (Database, Auth, Edge F…

263K installs
neon-postgres Shared topics
neondatabase/agent-skills

>- Guides and best practices for working with Lakebase Postgres, the database behind Neon. Cove…

146.5K installs
firebase-data-connect Shared topics
firebase/agent-skills 142.2K installs
detect Similar name
launchdarkly/ai-tooling

Detect repository stack for LaunchDarkly SDK onboarding: languages, frameworks, package manager…

2.3K installs

Also in this package

Other skills from hainrixz/claude-db · top by installs.

npx skills add hainrixz/claude-db
db-connection-pooling 68 db-normalization 67 db-multitenancy 66 db-security-access 64 audit 64 db-indexing 64 fix 63 checklist 63 db-index-hygiene 63 db-types-precision 62

Browse all from hainrixz/claude-db

More details

Agent compatibility

Declared targets from SKILL.md / docs. Unmarked agents are not listed — the skill may still install via the CLI.

Claude Code Not declared
Cursor Not declared
Codex Not declared
GitHub Copilot Not declared
Windsurf Not declared
Gemini CLI Not declared
Cline Not declared
OpenCode Not declared

Repository health

Stars 19
License LICENSE
Default branch main
Open issues 0
Status Active

Skill metadata

Parsed from SKILL.md frontmatter.

Allowed toolsRead, Glob, Bash

Package contents

Files included with this skill beyond the listing page.

  • skill md SKILL.md 3,331 B
  • docs SUMMARY.md 445 B

History

  1. First seen on skills.sh
  2. First recorded snapshot · 62 installs

SKILL.md

stack-detect (Phase 1 — detect)

Classifies the project into one or more { paradigm, engine, orm, platform, sourceoftruth, confidence, files } stacks. This is the deterministic front door of every audit: it picks the paradigm profile the scorer re-normalizes over (scripts/score.mjs → PROFILES) and the module set each auditor runs.

What to do

  1. Resolve the target directory ($ARGUMENTS path, else the project root / cwd).
  2. Run the detector and read its JSON stdout:

``bash node scripts/detect-stack.mjs --dir "<dir>" ``

It returns { stacks: [...], files_scanned }. Never edit or re-implement it — it is tested foundation.

  1. Empty stacks → there is nothing to audit offline. Do not guess an engine. Route the user to /claude-db:start (the guided wizard) or invite a plain-language description of the intended database. Surface the detector's hint verbatim.

Source-of-truth precedence (see references/detection-signals.md)

When several sources describe one database, authority is, in order:

  1. Live Tier-1 introspection (via the introspect skill) — beats any file.
  2. Declarative / generated artifact — schema.prisma, Drizzle *_snapshot.json, structure.sql, schema.rb, generated migration SQL → confidence: established.
  3. Migration SQL over ORM program source.
  4. ORM program source (schema.ts, models.py, Mongoose/CDK) → confidence: directional.

directional stacks parsed from program source never raise a severity-5 cap — they nudge toward a generated artifact or Tier-1. When a declarative artifact and ORM source disagree, that is schema drift, owned by db-migration-safety (M22).

Routing emitted per stack

For each detected stack, emit the routing the orchestrator needs:

  • paradigm → selects the score.mjs profile and --paradigm flag (relational | document | key-value | wide-column | vector | time-series | graph).
  • module set → M0 engine-selection (recommendation, unscored) + M1..M22 filtered to the paradigm's profile modules. Categories whose modules emit no scored finding go inactive — e.g. a document store is never penalised for missing foreign keys.
  • sourceoftruth + confidence → the parse reliability ceiling carried into every finding (Tier 0(a) reliable vs 0(b) best-effort).

Multi-store

Return all stacks (e.g. Postgres primary + Redis cache). The orchestrator audits each, scores each with its own --paradigm, and rolls up worst-of-across-stores per axis (see references/scoring-model.md → Multi-store rollup), naming the flooring store.

Output

Emit the raw stacks array, the per-stack routing (paradigm profile + module set), and the sourceoftruth precedence note. Keep narration tight. Respond in the user's language (EN/ES).