verify — verify install verify, agent-orchestrator, community, verify install, ide skills, ai agent orchestration, llm provider routing, cloud and local model mixing, Claude Code, Cursor, Windsurf

v1.0.0
GitHub

About this Skill

Perfect for AI Agents needing comprehensive content analysis and verification capabilities for efficient model deployment. Verify is a provider-agnostic AI agent orchestration framework that adapts the verification-loop pattern for comprehensive testing and deployment.

Features

Build and import check using `docker compose run --rm app python -c "import agent_orchestrator; print('OK')"`
Linting using `docker compose run --rm lint` to report errors
Format check using `docker compose run --rm format` for code consistency
Testing in Phase 4 for thorough verification

# Core Topics

verify install ai agent orchestration llm provider routing cloud and local model mixing
pjcau pjcau
[0]
[0]
Updated: 3/7/2026

Agent Capability Analysis

The verify skill by pjcau is an open-source community AI agent skill for Claude Code and other IDE workflows, helping agents execute tasks with better context, repeatability, and domain-specific guidance. Optimized for verify install, ai agent orchestration, llm provider routing.

Ideal Agent Persona

Perfect for AI Agents needing comprehensive content analysis and verification capabilities for efficient model deployment.

Core Value

Empowers agents to orchestrate LLM providers, route by cost, and mix cloud and local models using docker compose, ensuring flexibility and efficiency in AI model deployment with Python and agent_orchestrator.

↓ Capabilities Granted for verify

Automating model deployment verification
Debugging LLM integration issues
Optimizing model routing by cost

! Prerequisites & Limits

  • Requires docker compose setup
  • Python environment needed
  • Limited to LLM providers supported by agent_orchestrator
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

verify

Install verify, an AI agent skill for AI agent workflows and automation. Works with Claude Code, Cursor, and Windsurf with one-command setup.

SKILL.md
Readonly

Verify — Pre-PR Quality Gate

Comprehensive verification loop adapted from flatrick/everything-claude-code verification-loop pattern.

Phase 1: Build / Import Check

bash
1docker compose run --rm app python -c "import agent_orchestrator; print('OK')"

If this fails, STOP and fix before continuing.

Phase 2: Lint

bash
1docker compose run --rm lint

Report all lint errors. Fix before continuing.

Phase 3: Format Check

bash
1docker compose run --rm format

Phase 4: Test Suite

bash
1docker compose run --rm test

Report:

  • Total tests
  • Passed / Failed
  • Any warnings

Phase 5: Security Scan

bash
1# Check for secrets in tracked files
2grep -rn "sk-\|api_key\s*=\s*['\"]" --include="*.py" src/ tests/ 2>/dev/null | head -10
3# Check for hardcoded passwords
4grep -rn "password\s*=\s*['\"]" --include="*.py" src/ 2>/dev/null | grep -v "test\|example\|orchestrator" | head -10

Phase 6: Diff Review

bash
1git diff --stat
2git diff HEAD --name-only

Review each changed file for:

  • Unintended changes
  • Missing error handling
  • Potential security issues

Output Format

After running all phases, produce a verification report:

VERIFICATION REPORT
==================
Import:    [PASS/FAIL]
Lint:      [PASS/FAIL] (details)
Format:    [PASS/FAIL]
Tests:     [PASS/FAIL] (X passed, Y warnings)
Security:  [PASS/FAIL] (X issues)
Diff:      [X files changed]

Overall:   [READY/NOT READY] for PR

Issues to Fix:
1. ...

When to Run

  • Before every PR
  • After refactoring
  • After adding new dependencies
  • After significant code changes

FAQ & Installation Steps

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

? Frequently Asked Questions

What is verify?

Perfect for AI Agents needing comprehensive content analysis and verification capabilities for efficient model deployment. Verify is a provider-agnostic AI agent orchestration framework that adapts the verification-loop pattern for comprehensive testing and deployment.

How do I install verify?

Run the command: npx killer-skills add pjcau/agent-orchestrator/verify. It works with Cursor, Windsurf, VS Code, Claude Code, and 19+ other IDEs.

What are the use cases for verify?

Key use cases include: Automating model deployment verification, Debugging LLM integration issues, Optimizing model routing by cost.

Which IDEs are compatible with verify?

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.

Are there any limitations for verify?

Requires docker compose setup. Python environment needed. Limited to LLM providers supported by agent_orchestrator.

↓ 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 pjcau/agent-orchestrator/verify. 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 verify immediately in the current project.

Related Skills

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

View All

widget-generator

Logo of f
f

f.k.a. Awesome ChatGPT Prompts. Share, discover, and collect prompts from the community. Free and open source — self-host for your organization with complete privacy.

★ 149.6k
⑂ 0
AI

flags

Logo of vercel
vercel

flags is a Next.js feature management skill that enables developers to efficiently add or modify framework feature flags, streamlining React application development.

★ 138.4k
⑂ 0
Browser

zustand

Logo of lobehub
lobehub

The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, effortless agent team design, and introducing agents as the unit of work interaction.

★ 72.8k
⑂ 0
AI

data-fetching

Logo of lobehub
lobehub

The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, effortless agent team design, and introducing agents as the unit of work interaction.

★ 72.8k
⑂ 0
AI