Menyelaraskan vibe coding dengan AI code review kinerja.venturo.id - snapshot mentah 25 context review production + simulator skor (port 1:1 mesin skor kinerja-be), ambang struktur multi-bahasa (Go, Python, TS/JS presisi via go/ast, ast, TypeScript compiler API; PHP, Swift, Kotlin, Dart, Java heuristik), kinerja_status.py (deteksi stack, pelanggaran, gate commit/trivial/agent-docs/doc-sync, prediksi skor; kontrak JSON untuk mod HUD), skill venturo-kinerja-rules/precheck/pr, agent read-only kinerja-file-explorer & kinerja-verifier, dan hook ambang, guard pesan commit, guard CLAUDE.md, pengingat doc-sync, serta peringatan rules basi.
Plugin venturo-kinerja from marketplace venturo-tools in venturo-id/venturo-claude. Commands read from the repo's manifest — 16 days ago.
This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.
venturo-kinerja-prUse when the user asks for /venturo-kinerja-pr, wants a pull request description written, or is about to open a PR in a repository scored by the Kinerja AI code review — validates commit messages against the Kinerja gates and drafts a factual PR description from the diff and the Space issue. Prepare
venturo-kinerja-precheckUse when the user asks for /venturo-kinerja-precheck, wants a self-review or predicted Kinerja score before pushing or opening a pull request, or asks "berapa skor PR ini nanti" — reviews the local diff with the same workflow, rules and scoring formula as the Kinerja AI code review and lists fixes r
venturo-kinerja-rulesUse when writing, modifying, or refactoring code (Go, TypeScript/JavaScript/React/Next.js/Node, PHP/Laravel/CodeIgniter/Slim, Python, Swift, Kotlin, Dart/Flutter, Java), API routes/controllers/DTOs, database migrations, or CLAUDE.md/AGENTS.md in a repository whose pull requests are scored by the Kin
kinerja-file-explorerRead-only explorer for one changed code file during a Kinerja-style precheck. Given a file path and the symbols changed in the diff, finds each symbol's direct callers, callees and tests, and flags candidate problems for the main agent to verify. Never edits files.
kinerja-verifierRead-only verifier for one candidate finding in a Kinerja-style precheck. Tries to prove or disprove the claim from the code and returns CONFIRMED or REJECTED with path:line evidence. Use before a candidate finding is written into the precheck report. Never edits files.
"${CLAUDE_PLUGIN_ROOT}"/hooks/run.sh session_start
"${CLAUDE_PLUGIN_ROOT}"/hooks/run.sh guard_commit
"${CLAUDE_PLUGIN_ROOT}"/hooks/run.sh post_edit
"${CLAUDE_PLUGIN_ROOT}"/hooks/run.sh stop_doc_sync
Paket standar tim Venturo dalam satu install - guard hook (tolak penghapusan destruktif, git push --force, dan baca/tulis .env dengan audit log), quality gate Go/TS, 3 subagent (api-contract-reader, code-reviewer, test-writer), 7 server MCP tim tanpa kredensial, skill venturo-arsenal-check + venturo-contract, dan arsenal-setup.sh yang idempotent untuk memasang sisa kurasi perkakas tim.
2 skills · 3 agents · 7 MCP servers · hooks
QA Engineer Automation plugin for Playwright E2E testing with auto-scenario generation and validation
3 skills · 4 commands · 3 agents
Go backend development automation for Venturo skeleton - Guided workflows for features, entities, endpoints, and adapters
6 commands
Database design and API contract planning - Generate ERD, DBML, PostgreSQL migrations, and API contracts following audit standards
4 commands
Grades a Claude Code session against the 7-dimension vibe-coding rubric; outputs scored JSON + Bahasa Indonesia coaching. v0.7.x: skoring jadi deterministik penuh — seluruh perhitungan nilai pindah ke scripts/validate.py (`--score`), subagent grader hanya mengembalikan misses + saran, plus 25 counter anti-cheap-ritual dan applicability clamp untuk sesi tanpa kerja substantif. 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.
1 skill
React frontend development automation for Venturo skeleton - Guided workflows for features from OpenAPI specs
1 command
Matt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).
39 skills
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
15 skills · hooks
Up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your coding agent's context.
1 MCP server
Build powerful, stateful CLI interfaces for any GUI application using the cli-anything harness methodology.
5 commands
Automates browser interactions for web testing, form filling, screenshots, and data extraction
12 skills
Use Alibaba Open Code Review from local Codex.
2 skills
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.