メニュー
Regenerates TypeScript types from dbt artifact JSON schemas. Use when the user asks to update parsers, sync with upstream, refresh types, or regenerate parser types from existing schemas.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Upgrade outdated npm dependencies in the pnpm monorepo (recursive update, latest, targeted packages). Use when the user asks to upgrade dependencies, bump packages, refresh lockfile, pnpm update, outdated packages, latest versions, or dependency refresh—not monorepo release versions.
Format code, run linters and static analysis, and find unused code (ESLint + Knip). Use when the user asks to fix lint, format code, run formatters, find dead code, unused exports, run knip, fix style, tidy code, or run eslint --fix.
Manage Architecture Decision Records (ADRs). Use this to initialize, create, list, and link ADRs to document architectural evolution. Requires 'adr-tools' to be installed.
Use at the end of a coding session to summarize outcomes, failures, inefficiencies, and root causes, then output a concise postmortem report with ranked improvements for next time. Output only in chat; do not edit project files unless the user explicitly asks. Skip nit-picks and one-off mistakes.
Interactively bump package versions for the parser package. Use when the user asks to bump version, increment version, set release version, or release dbt-artifacts-parser.
Interactive deep research and decision support: frame the real problem (XY-aware), ask exactly 10 multiple-choice questions one at a time, then produce a rigorous comparative evaluation (default 5 approaches, 0–100 scores) and recommendation. Use when the user wants structured discovery before committing to a solution, a scored comparison of approaches, or to avoid jumping straight to an answer—especially for architecture, strategy, or high-stakes trade-offs.
| name | dbt-parser-refresh |
| description | Regenerates TypeScript types from dbt artifact JSON schemas. Use when the user asks to update parsers, sync with upstream, refresh types, or regenerate parser types from existing schemas. |
| compatibility | Requires pnpm, Node.js |
Activate this skill when the user says or implies:
resources/)packages/dbt-artifacts-parser/resources/json-schema/ (and legacy resources/<category>/ when used).
pnpm --filter dbt-artifacts-parser gen:types or bash packages/dbt-artifacts-parser/scripts/generate.shcd packages/dbt-artifacts-parser && pnpm gen:typespackages/dbt-artifacts-parser/resources/json-schema/{catalog,manifest,run-results,sources,semantic_manifest}/ (JSON Schemas for codegen; kept separate from resources/manifest/ etc. so fixture discovery does not treat schemas as artifacts). Each *_vN.json file is turned into src/<category>/vN.ts. Legacy resources/<category>/ is still accepted for catalog/sources when present.catalog, manifest, run-results, sources, semantic_manifest.*_vN.json files in each category directory.src/<category>/vN.ts yourself (partial regen does not delete absent versions). When adding a new major version, update hand-maintained src/<category>/index.ts (exports, Parsed* unions, parse helpers).src/index.ts: still regenerated by generate.sh (catalog re-export); category index.ts files are not overwritten.This repo has no download script. To add new schema versions, copy JSON schema files (e.g. from dbt-labs/dbt-core under schemas/dbt/ on GitHub raw, or https://schemas.getdbt.com/) into the appropriate packages/dbt-artifacts-parser/resources/json-schema/<category>/ directory (use *_vN.json filenames), then run the generate command above.
Full regenerate (all categories and versions):
pnpm --filter dbt-artifacts-parser gen:types
Or from repo root using the script directly:
bash packages/dbt-artifacts-parser/scripts/generate.sh