architect-agent — community architect-agent, agent_rulez, community, ide skills, Claude Code, Cursor, Windsurf

v3.1.0
GitHub

About this Skill

Ideal for Architect Agents requiring coordinated planning, delegation, and evaluation across workspaces. Agent Rulz

SpillwaveSolutions SpillwaveSolutions
[0]
[0]
Updated: 3/5/2026

Agent Capability Analysis

The architect-agent skill by SpillwaveSolutions 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.

Ideal Agent Persona

Ideal for Architect Agents requiring coordinated planning, delegation, and evaluation across workspaces.

Core Value

Empowers agents to orchestrate workspaces using intent classification, decision trees, and resource loading policies, facilitating seamless interactions between architect and code agents through protocols like Critical Protocol: F.

Capabilities Granted for architect-agent

Initializing workspaces for collaborative projects
Delegating tasks to code agents using automated setup
Evaluating work quality through grading and feedback mechanisms

! Prerequisites & Limits

  • Requires comprehensive content analysis
  • Dependent on agent's ability to interpret intent classification and decision trees
  • Limited to architect and code agent workspaces
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

architect-agent

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

SKILL.md
Readonly

Architect Agent Workflow Skill

Coordinate planning, delegation, and evaluation across architect and code agent workspaces.

Quick Start: Say "write instructions for code agent", "initialize workspace", "grade work", or "send instructions". For automated setup, see Quick Setup.

Table of Contents

Intent Classification

Route requests based on user intent:

IntentTrigger PhrasesAction
Create Instructions"write instructions", "create instructions", "delegate to code agent"→ Load guides/workflows/create-instructions.md
Initialize Workspace"set up architect agent", "initialize workspace", "new architect agent"→ Load guides/workflows/initialize-workspace.md
Grade Work"grade the work", "evaluate completed work", "review implementation"→ Load guides/workflows/grade-work.md
Send Instructions"send instructions", "send to code agent"→ Load guides/workflows/send-instructions.md
Add OpenCode Support"migrate to OpenCode", "add OpenCode support"→ Load references/opencode_integration_quickstart.md
Verify Setup"verify setup", "test hooks", "check logging"→ Load references/workspace_verification_protocol.md
Setup Permissions"set up permissions", "fix permission prompts"→ Load references/permissions_setup_protocol.md
Upgrade Workspace"upgrade workspace", "migrate to v3.0"→ Load references/upgrade.md

Decision Tree

User IntentPre-conditionAction
"write/create instructions", "delegate"instructions/ existsLoad guides/workflows/create-instructions.md
"write/create instructions", "delegate"instructions/ missingSuggest workspace initialization first
"set up/initialize" workspaceDirectories don't existLoad guides/workflows/initialize-workspace.md
"set up/initialize" workspaceDirectories existWarn: already initialized
"grade", "evaluate" workgrades/ existsLoad guides/workflows/grade-work.md
"grade", "evaluate" workgrades/ missingSuggest workspace initialization first
"send instructions"Load guides/workflows/send-instructions.md (bash copy, no agents)
"verify", "test hooks"Load references/workspace_verification_protocol.md
"OpenCode", "dual-mode"Load references/opencode_integration_quickstart.md
"permissions"Load references/permissions_setup_protocol.md
"upgrade", "migrate"Load references/upgrade.md

Resource Loading Policy

Load ONLY when needed:

  • Workflow guides: When intent is classified
  • Reference docs: When user needs detailed protocol
  • Templates: When creating workspace or files
  • Never load all references "just in case"

Core Resources by Intent:

IntentPrimary ResourceSupporting Resources
Create Instructionsguides/workflows/create-instructions.mdreferences/instruction_structure.md, references/human_instruction_structure.md, references/file_naming.md
Initialize Workspaceguides/workflows/initialize-workspace.mdreferences/workspace_setup_complete.md
Grade Workguides/workflows/grade-work.mdreferences/grading_rubrics.md, references/decision_types.md
Send Instructionsguides/workflows/send-instructions.md(none - simple bash copy)
Verify Setupreferences/workspace_verification_protocol.mdreferences/pre_work_checklist.md
Setup Permissionsreferences/permissions_setup_protocol.md-
OpenCode Supportreferences/opencode_integration_quickstart.mdreferences/opencode_setup_guide.md

Critical Protocol: File Locations

The architect agent operates in its own workspace, NOT the code agent workspace.

ArtifactArchitect Writes ToCode Agent Location
Instructions[ARCHITECT]/instructions/Reads from debugging/instructions/
Human Instructions[ARCHITECT]/human/N/A (for manual execution)
Grades[ARCHITECT]/grades/N/A
LogsN/AWrites to [CODE_AGENT]/debugging/logs/

Human Instructions = Executable Documentation (not summaries!)

Human instructions must enable manual execution when code agents are unavailable. Include copy-pasteable commands, expected output, and troubleshooting. See references/human_instruction_structure.md.

Guard Rail: If about to write to the code agent's workspace, stop and verify the operation.

Quick Setup (Template-Based)

For fastest setup, use templates:

bash
1cd ~/.claude/skills/architect-agent/templates/ 2 3# Create code agent workspace 4./setup-workspace.sh code-agent ~/projects/my-code-agent 5 6# Create architect workspace 7./setup-workspace.sh architect ~/projects/my-architect \ 8 --code-agent-path ~/projects/my-code-agent

Time: <5 minutes See: templates/README.md

DO NOT Trigger For

  • General architecture discussions
  • Brainstorming or exploration
  • Reading/analyzing existing code
  • Research tasks
  • Any work that isn't explicit instruction creation, grading, or setup

Reference Directory

All detailed protocols are in references/. Load only what is needed for the current task.

Core References (Instruction & Grading)

ReferencePurpose
instruction_structure.mdCode agent instruction template
human_instruction_structure.mdHuman-executable instruction template
grading_rubrics.md6-category grading criteria
instruction_grading_workflow.mdFull grading workflow
decision_types.mddecision, rationale, investigation, verification, deviation, milestone
file_naming.mdTimestamp and naming conventions

Setup & Configuration

ReferencePurpose
installation.mdSkill installation guide
quick_start.mdFast-track setup
workspace_setup_complete.mdFull workspace initialization
workspace_verification_protocol.mdVerify setup is correct
permissions_setup_protocol.mdCross-workspace permissions
upgrade.mdUpgrade to latest version

Logging & Debugging

ReferencePurpose
logging_protocol.mdHybrid logging v2.0
hybrid_logging_protocol.mdDetailed hybrid logging spec
hook_configuration_critical.mdHook setup requirements
hook_logger_enhancements.mdHook logger improvements
pre_work_checklist.mdCode agent pre-work verification
get_unstuck_protocol.mdRecovery from blockers
resilience_protocol.mdError recovery patterns
testing_protocol.mdProgressive testing requirements

OpenCode Integration

ReferencePurpose
opencode_integration_quickstart.mdDual-mode quick start
opencode_setup_guide.mdFull OpenCode setup
opencode_migration_guide.mdMigrate to OpenCode
opencode_logging_protocol.mdOpenCode-specific logging
opencode_wrapper_setup.mdWrapper script setup
claude_vs_opencode_comparison.mdFeature comparison

Agent Configuration

ReferencePurpose
agent_specialization.mdAgent role configuration
code_agent_claude_template.mdCLAUDE.md template for code agents
code_agent_agents_template.mdAGENTS.md template for code agents

Project Management

ReferencePurpose
git_pr_management.mdGit and PR workflow
ticket_tracking_pr_management.mdTicket and PR tracking

Guides Directory

Step-by-step workflows in guides/workflows/:

GuideTrigger
create-instructions.md"write instructions for code agent"
grade-work.md"grade the code agent's work"
send-instructions.md"send instructions to code agent"
initialize-workspace.md"set up architect agent workspace"

Templates

Ready-to-use workspace templates in templates/:

TemplatePurpose
setup-workspace.shAutomated workspace creation script
architect-workspace/Complete architect agent workspace template
code-agent-workspace/Complete code agent workspace template

See: templates/README.md for usage instructions.


FAQ & Installation Steps

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

? Frequently Asked Questions

What is architect-agent?

Ideal for Architect Agents requiring coordinated planning, delegation, and evaluation across workspaces. Agent Rulz

How do I install architect-agent?

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

What are the use cases for architect-agent?

Key use cases include: Initializing workspaces for collaborative projects, Delegating tasks to code agents using automated setup, Evaluating work quality through grading and feedback mechanisms.

Which IDEs are compatible with architect-agent?

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 architect-agent?

Requires comprehensive content analysis. Dependent on agent's ability to interpret intent classification and decision trees. Limited to architect and code agent workspaces.

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 SpillwaveSolutions/agent_rulez/architect-agent. 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 architect-agent immediately in the current project.

Related Skills

Looking for an alternative to architect-agent 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