Plugins

Lính gác (sentinel) đọc PDF văn bản hành chính Việt Nam: chạy ngay khi nhận PDF văn bản nhà nước để trích chính xác số văn bản, ngày ban hành, cơ quan, người ký, trích yếu, nơi nhận bằng scripts/extract_metadata.py. Khắc phục lỗi kinh điển: PDF layout 2 cột có text-box độc lập cho số và ngày, khi nạp vào context thường trống hoặc nối sai dẫn tới viện dẫn sai. Script đồng bộ một bản duy nhất với plugin vbhc-vn.

Soạn thảo, rà soát VBHC (.docx) Sở Công Thương Lào Cai theo NĐ 30/2020: công văn, tờ trình, báo cáo, kế hoạch, quyết định, biên bản, giấy phép, GCN ATTP; văn bản cấp UBND tỉnh/VP do Sở dự thảo. 9 template trắng + 23 mẫu thật, Chế độ A (dựng từ template) / B (sửa file gốc), 9 nhóm anti-error A-I, QA một phát qa_all.py (--forbid/--require, audit keepNext), đọc metadata PDF công văn đến bằng extract_metadata.py. Dùng khi soạn/sửa/rà soát/chuyển thể VBHC hoặc sửa lỗi trình bày file Word.

Bug lifecycle for Virto Commerce QA — project setup, bug filing, autonomous fixing, fix verification, online bug monitoring, and self-diagnostics (/vc-self-check). Self-contained plugin (8 agents, 15 skills, 7 commands).

Advises founders through a pre-seed/seed raise: pitch-deck teardowns, investor research, outreach copy, and runnable fundraising playbooks.

Data-readiness + posture on your vCISO Lite data, with risk-intelligence workflows layering on as they ship.

Claude Code skill pack for Veeva (24 skills)

A working novelist's daily tool for Claude Code: one command for the chapter loop, three hard gates, everything else advisory and silent when clean. The muse agent is the primary entry point; the deterministic Python engine (scripts/vellum) absorbs every check no LLM should burn tokens on.

Connect Claude Code to a product running Vendo: guarded host tools, and `vendo_make` for putting a screen in front of the user.

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

Imported from grok

Vercel deployment platform integration. Manage deployments, check build status, access logs, configure domains, and control your frontend infrastructure directly from Claude Code.

Vercel ecosystem dev plugin. Deployment, AI SDK, Edge Functions, storage, routing, performance optimization. CLI deploy troubleshooting for non-Git projects, Hobby plan fixes, standalone output handling, CMS deploy hooks. Based on official vercel-plugin v0.25.0 by Vercel Labs.

Build, develop, deploy, self-host, secure, and troubleshoot durable backend AI agents with Vercel Eve. Use when creating an Eve agent, adding tools, skills, subagents, channels, schedules, sandboxing, durable sessions, observability, or deploying Eve on Vercel or a Node host. Do not use for the separate Vercel AI SDK Agent APIs such as ToolLoopAgent or WorkflowAgent; use an AI SDK-specific skill for those.

Complete Vercel integration skill pack with 30 skills covering deployments, edge functions, preview environments, performance optimization, and production operations. Flagship+ tier vendor pack.

Build and deploy web apps and agents

Curated upstream: Vercel-Labs React/Next.js skills — performance best practices, composition patterns (compound components, render props), and React Native / Expo conventions for mobile.

Evidence-before-claims methodology. Requires fresh execution of verification commands, reading full output, and confirming results before asserting completion.

Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always

Jurisdiction-neutral verification core (7 skills): legal syllogism, citation extraction, clause checklist, adversarial red-team review, single-pass opposing-counsel attack, judicial first impression (cold-reader test), output scoring. No connectors, sends no data out.

Create or audit deterministic verification surfaces.

Verify work against explicit criteria using direct, source-faithful evidence, reproducible checks, and clear verdicts. Use before declaring an artifact, implementation, or claim complete; do not use for exploratory research without pass/fail criteria.

Verification feedback loop: format/typecheck/test on every edit, and block premature Stop until verify.sh passes.

Specification-first development workflow with ATDD, layered verification gates, and two-stage review agents. Enforces TDD, mechanical quality gates (lint, test, coverage, security, dead code), and AI-powered code review. Language-agnostic: runs the repo's own verify command and infers test idioms; Go is the bundled toolchain example; /test-audit spans Go, TypeScript, Python, and Java.

Adversarial review, assumption flagging, citation integrity checking, and cross-document consistency skills — a quality-control pass for a finished draft from any practice area.

Never assert a fact, completion, or reproduction claim without naming and running the specific check that would prove it false, first.

Identify and verify unverified claims in the agent's own responses before presenting them as conclusions.

Integrated content verification skill. Extracts claims, verifies against external sources, and compiles references in a single workflow.