ClaudeMap

Viserys

A self-contained pack of 28 engineering-workflow skills that walks an AI coding agent through DEFINE, PLAN, BUILD, VERIFY, REVIEW and SHIP instead of letting it improvise.

Skills & Commandsskillworkflowlifecyclereviewevals

Viserys is a pack of Markdown workflows, reviewer personas and validation scripts that gives an agent a consistent process across the full development lifecycle. Inside: 28 SKILL.md workflows with steps, exit criteria and anti-rationalization tables across six phases (idea refinement, interview-style requirements, spec-driven and constraint-driven development, schema and task planning, and more), 4 reviewer personas, shared reference checklists loaded on demand, lifecycle command definitions, and its own QA harness — eval cases and fixtures, six validator scripts (skills, commands, artifact paths, reference links, versions) and an eval runner. Skills are standalone Markdown: skill-aware agents (Claude Code, OpenCode, Cursor and others) consume them by pointing at the skills/ directory or copying it into their native skills location, and anyone else can just read them. The polished one-keystroke activation flow — open the repo and pick the viserys primary agent — is OpenCode-specific.

What it does

  • 28 SKILL.md workflows across six lifecycle phases, each with steps, exit criteria and anti-rationalization tables
  • 4 reviewer personas plus shared reference checklists loaded on demand
  • Ships its own QA harness: eval cases and fixtures, six validator scripts and an eval runner
  • Standalone Markdown skills — usable by skill-aware agents (Claude Code, OpenCode, Cursor) or readable as plain context

When to use it

Developers and small teams who want an AI coder to follow one consistent full-lifecycle process — spec-driven starts, PRD-to-tasks planning, review gates — instead of re-negotiating how to work on every task.

Getting started

git clone https://github.com/rizqinrr/viserys-agent.git
# skill-aware agents (Claude Code, OpenCode, Cursor):
#   point the agent at skills/ or copy that directory into
#   the agent's native skills location
# OpenCode one-liner: open the repo folder, press Tab, select `viserys`

# validation:
node scripts/validate-skills.js
node scripts/run-evals.js

Things to know

No LICENSE file in the repository (GitHub API reports none) — all rights reserved by default, so ask the author before redistributing or building on it. The primary-agent activation flow is OpenCode-specific; in Claude Code you consume the skills directory directly. v0-stage project: skills ship with eval fixtures, but there is no stated release version.

Repository

rizqinrr/viserys-agent

Charted

Related on the map

  • Guizang's agent skill turns your repo's recent updates into a finished promo video — real components, code-rendered animation, an original code-written soundtrack — no video editor involved.

    • agent-skill
    • video
    • promo
    • marketing
  • An agent skill that geolocates a photo with nothing readable in it — OSM geometry, elevation skylines and satellite tiles turn “where was this taken?” into a measured answer with an error radius.

    • agent-skill
    • geolocation
    • osint
    • openstreetmap
  • A skill that makes AI coding agents map the architecture and declare the blast radius before they touch a line of code — rendered as one standalone HTML page.

    • skill
    • architecture
    • code-visualization
    • change-scope