hhh-dialect-verify-reportlisted

One-shot CUBRID dialect verification + report. Runs the hibernate-core test suite against one or ALL CUBRID versions, diffs pass/fail vs a baseline (a prior run's JSON, results dir, or .tgz), and ALWAYS produces a Korean Word (.docx) 비교 분석 report. Use when you want the full 'verify → measure → report' pipeline for a CUBRIDDialect change in one go, or to test across all CUBRID versions. Composes the hhh-dialect-verify and report skills. Triggers on phrases like 'dialect 검증하고 리포트까지', 'CUBRID 전체 버전 테스트 + 보고서', 'verify the dialect and write the report', 'run all CUBRID versions and report'.
Srltas/claude-skills · ★ 0 · Data & Documents · score 69

Install: claude install-skill Srltas/claude-skills

# CUBRID dialect verify → report (one-shot) Run the hibernate-core suite against CUBRID (one version or the full matrix), diff vs a baseline, and **always** generate the Word 비교 분석 report. This orchestrates two installed skills: **hhh-dialect-verify** (`parse_results.py`, measurement) and **report** (`build_report.js`, document). ⚠️ Long-running: the full suite is ~30 min **per version** (≈2.5 h for `--all-versions`). Use `--tests '<filter>'` for a quick smoke check first. ## Step 0: Prereqs - Installed skills: **`hhh-dialect-verify`** and **`report`** (both under `~/.claude/skills/`). - Hibernate repo (default `~/Devel/hibernate`), Docker, `python3`, and for the report: `node` + global `docx`, plus the report venv (matplotlib). See the report skill's Step 0. - Optional: the **Understand-Anything** plugin (`/understand-*` commands). If installed, Step 3 can add a change-impact (영향 범위) note; the pipeline runs fine without it. ## Step 1: Run the orchestrator (verify across versions) ```bash bash <skill-base-dir>/assets/run_verify.sh \ --baseline ~/Devel/cubrid-fullsuite-10.2-2026-06-13.tgz \ --all-versions # or: --versions 10.2,11.4 (add --tests '<filter>' for a fast run) ``` Per version it starts CUBRID (`CUBRID_IMAGE=...:<v> ./db.sh cubrid`), runs `:hibernate-core:test -Pdb=cubrid`, parses results, and diffs vs the baseline. Writes `verify-out/summary.json` (+ per-version `<v>.json`, `run-<v>.log`) and prints a table: `version · total · faile