venturo-id/venturo-claude

Grades a Claude Code session against the 7-dimension vibe-coding rubric; outputs scored JSON + Bahasa Indonesia coaching. v0.6.0 (anti-gaming): bobot rubrik direbalance (15/15/15/18/20/12/5); misses WAJIB ≥2 per sesi → total_score maks 98; score caps deterministik dari work_evidence (sesi pendek/tanpa friksi tertangani dibatasi); deteksi prompt sintetis dari first_user_prompt; scripts/validate.py jadi gerbang mekanis wajib sebelum upload; first_user_prompt dikirim ke leaderboard untuk audit; hard reject transcript non-Claude-Code. v0.5.0: dimensi delegation menilai orkestrasi skill & subagent secara terukur (D1 subagent / D2 skill / D3 MCP) dari sinyal ground-truth (toolUseResult, attributionSkill) yang sukar dipalsukan; sesi tanpa skill+subagent ≤6/15; digest.py emit tool_usage+signal_availability (→ raw_payload, tanpa perubahan BE); laundering compact ditutup; calibration anchor + evidence-first di prompt grader. v0.4.1: file sementara /tmp per-transkrip (fix baca digest basi lintas sesi). v0.4.0: prompt_analysis dikirim, plus usage_totals/type_counts/grademe_version. v0.3.0: mandatory live-session grading, digest.py preprocessing, session_name + compacted, endpoint venturo.pro.

QA Engineer Automation plugin for Playwright E2E testing with auto-scenario generation and validation

Go backend development automation for Venturo skeleton - Guided workflows for features, entities, endpoints, and adapters

Database design and API contract planning - Generate ERD, DBML, PostgreSQL migrations, and API contracts following audit standards

React frontend development automation for Venturo skeleton - Guided workflows for features from OpenAPI specs