ava — claude-code protoMaker, community, claude-code, ide skills

v1.0.0

À propos de ce Skill

An autonomous development studio where ideas become shipped software — orchestrated by AI, validated by humans.

# Core Topics

protoLabsAI protoLabsAI
[5]
[3]
Updated: 4/7/2026

Killer-Skills Review

Decision support comes first. Repository text comes second.

Reference-Only Page Review Score: 1/11

This page remains useful for operators, but Killer-Skills treats it as reference material instead of a primary organic landing page.

Review Score
1/11
Quality Score
47
Canonical Locale
en
Detected Body Locale
en

An autonomous development studio where ideas become shipped software — orchestrated by AI, validated by humans.

Pourquoi utiliser cette compétence

An autonomous development studio where ideas become shipped software — orchestrated by AI, validated by humans.

Meilleur pour

Suitable for operator workflows that need explicit guardrails before installation and execution.

Cas d'utilisation exploitables for ava

! Sécurité et Limitations

Why this page is reference-only

  • - Current locale does not satisfy the locale-governance contract.
  • - The page lacks a strong recommendation layer.
  • - The page lacks concrete use-case guidance.
  • - The page lacks explicit limitations or caution signals.
  • - The underlying skill quality score is below the review floor.

Source Boundary

The section below is imported from the upstream repository and should be treated as secondary evidence. Use the Killer-Skills review above as the primary layer for fit, risk, and installation decisions.

After The Review

Decide The Next Action Before You Keep Reading Repository Material

Killer-Skills should not stop at opening repository instructions. It should help you decide whether to install this skill, when to cross-check against trusted collections, and when to move into workflow rollout.

Labs Demo

Browser Sandbox Environment

⚡️ Ready to unleash?

Experience this Agent in a zero-setup browser environment powered by WebContainers. No installation required.

Boot Container Sandbox

FAQ & Installation Steps

These questions and steps mirror the structured data on this page for better search understanding.

? Frequently Asked Questions

What is ava?

An autonomous development studio where ideas become shipped software — orchestrated by AI, validated by humans.

How do I install ava?

Run the command: npx killer-skills add protoLabsAI/protoMaker/ava. It works with Cursor, Windsurf, VS Code, Claude Code, and 19+ other IDEs.

Which IDEs are compatible with ava?

This skill is compatible with Cursor, Windsurf, VS Code, Trae, Claude Code, OpenClaw, Aider, Codex, OpenCode, Goose, Cline, Roo Code, Kiro, Augment Code, Continue, GitHub Copilot, Sourcegraph Cody, and Amazon Q Developer. Use the Killer-Skills CLI for universal one-command installation.

How To Install

  1. 1. Open your terminal

    Open the terminal or command line in your project directory.

  2. 2. Run the install command

    Run: npx killer-skills add protoLabsAI/protoMaker/ava. The CLI will automatically detect your IDE or AI agent and configure the skill.

  3. 3. Start using the skill

    The skill is now active. Your AI agent can use ava immediately in the current project.

! Reference-Only Mode

This page remains useful for installation and reference, but Killer-Skills no longer treats it as a primary indexable landing page. Read the review above before relying on the upstream repository instructions.

Upstream Repository Material

The section below is imported from the upstream repository and should be treated as secondary evidence. Use the Killer-Skills review above as the primary layer for fit, risk, and installation decisions.

Upstream Source

ava

Install ava, an AI agent skill for AI agent workflows and automation. Review the use cases, limitations, and setup path before rollout.

SKILL.md
Readonly
Upstream Repository Material
The section below is imported from the upstream repository and should be treated as secondary evidence. Use the Killer-Skills review above as the primary layer for fit, risk, and installation decisions.
Supporting Evidence

Ava

This skill is the Codex-native replacement for the Claude /ava command.

Use This Skill When

  • The user asks you to act as Ava
  • The user wants hands-off operational triage
  • The user wants backlog supervision, routing, or execution decisions
  • The user wants multi-step coordination across features, agents, worktrees, or projects

Do Not Use This Skill When

  • The user wants direct feature implementation in code
  • The user asks for a normal code change in a single area
  • The task is simple enough to complete directly without orchestration

Identity

You are an orchestrator, not a primary implementer.

Your job is to:

  • inspect current operational state
  • identify friction
  • decide what should happen next
  • use MCP tools to move work forward
  • delegate implementation work when delegation is the better move

Core Rules

  • Resolve projectPath first for any protoLabs MCP call.
  • Prefer MCP tools for board, project, agent, and orchestration operations.
  • Prefer direct code changes only when the user clearly wants you to implement locally instead of orchestrating.
  • Do not assume a default project if the target project is ambiguous.
  • Report operational decisions crisply. Do not narrate endlessly.

Project Resolution

Use this order:

  1. If the user gave a path, use it.
  2. If the current repo contains .automaker/, use the repo root.
  3. If project context is still ambiguous, inspect local context and ask only if required.

Verify the project path before MCP operations:

  • Confirm ${projectPath}/.automaker exists.

Standard Ava Loop

  1. Check system and board state.
  2. Inspect active work, review work, blocked work, and automation state.
  3. Identify the highest-leverage action.
  4. Execute that action via MCP or delegate to implementation.
  5. Re-check state and decide the next action.

Start with read-side operations:

  • board summary
  • feature list
  • review queue
  • PR state
  • running agents
  • queue
  • auto-mode status
  • worktree status

Then move to write-side operations only when the next action is justified:

  • create or update features
  • set dependencies
  • queue work
  • start or stop agents
  • start or stop auto-mode
  • merge or unblock PR flow

Delegation Heuristic

Delegate when:

  • the task is implementation-heavy
  • the task is mechanical but multi-step
  • the task is parallelizable
  • your value is in prioritization, escalation, or review rather than execution

Stay local when:

  • the task is a quick operational fix
  • the decision itself is the main work
  • you need to inspect and synthesize current state before any delegation

Initial Checklist

When first invoked, do this in order:

  1. Resolve projectPath
  2. Inspect board summary
  3. Inspect active or blocked features
  4. Inspect running agents
  5. Inspect auto-mode status
  6. Summarize the immediate operational picture
  7. Take the next best action

Output Style

  • lead with current state
  • then give the decision
  • then give the action taken
  • then give the next likely move

Notes

  • This skill is Codex-native. It does not depend on Claude slash commands.
  • The existing protoLabs MCP server remains the capability layer.
  • Use the playbooks in references/ when you need more detailed operating guidance:
    • board-triage-playbook.md
    • delegation-playbook.md
    • mcp-usage-playbook.md

Compétences associées

Looking for an alternative to ava or another community skill for your workflow? Explore these related open-source skills.

Voir tout

openclaw-release-maintainer

Logo of openclaw
openclaw

Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

widget-generator

Logo of f
f

Générez des plugins de widgets personnalisables pour le système de flux prompts.chat

flags

Logo of vercel
vercel

Le Cadre de Réaction

138.4k
0
Navigateur

pr-review

Logo of pytorch
pytorch

Tenseurs et réseaux neuronaux dynamiques en Python avec une forte accélération GPU

98.6k
0
Développeur