google-agents-cli-scaffold
Project scaffolding, deployment configuration, and CI/CD setup for Google ADK agents.
coord-tooling
Invoke COORD_TOOLING for tools and skills development
Full skill instructions
Purpose: Invoke COORD_TOOLING for development tools and agent skills coordination Created: 2026-01-06 Trigger:
/coord-toolingor/toolingor/toolsModel Tier: Sonnet (Domain Coordination)
Invoke COORD_TOOLING for tools and skills development:
Do NOT use for:
COORD_TOOLING is a Coordinator reporting to ARCHITECT:
ARCHITECT
↓
COORD_TOOLING (You are here)
├── TOOLSMITH → Skill/command creation, MCP tool development
├── TOOL_QA → Skill validation, testing, edge cases
├── TOOL_REVIEWER → Skill quality review, standards enforcement
└── AGENT_FACTORY → New agent creation following patterns
/coord-tooling [task description]
Example:
/coord-tooling Create skills for Deputies and Coordinators
The COORD_TOOLING.identity.md file is automatically loaded, providing:
For Skill Creation:
Task(
subagent_type="general-purpose",
description="TOOLSMITH: Skill Development",
prompt="""
## Agent: TOOLSMITH
[Identity loaded from TOOLSMITH.identity.md]
## Mission from COORD_TOOLING
{specific_tooling_task}
## Your Task
- Create skill file following skill-factory patterns
- Write YAML frontmatter with proper metadata
- Document purpose, usage, and examples
- Include activation protocol
- Add related skills section
Report results to COORD_TOOLING when complete.
"""
)
For Tool Quality Assurance:
Task(
subagent_type="general-purpose",
description="TOOL_QA: Tool Validation and Testing",
prompt="""
## Agent: TOOL_QA
[Identity loaded from TOOL_QA.identity.md]
## Mission from COORD_TOOLING
{specific_qa_task}
## Your Task
- Validate skill specifications
- Test skill invocation
- Check for edge cases
- Verify documentation completeness
- Test integration with existing skills
Report results to COORD_TOOLING when complete.
"""
)
For Tool Review:
Task(
subagent_type="general-purpose",
description="TOOL_REVIEWER: Tool Quality Review",
prompt="""
## Agent: TOOL_REVIEWER
[Identity loaded from TOOL_REVIEWER.identity.md]
## Mission from COORD_TOOLING
{specific_review_task}
## Your Task
- Review skill quality and consistency
- Ensure standards compliance
- Check for duplication
- Validate against CONSTITUTION.md
- Provide improvement suggestions
Report results to COORD_TOOLING when complete.
"""
)
For Agent Creation:
Task(
subagent_type="general-purpose",
description="AGENT_FACTORY: New Agent Creation",
prompt="""
## Agent: AGENT_FACTORY
[Identity loaded from AGENT_FACTORY.identity.md]
## Mission from COORD_TOOLING
{specific_agent_task}
## Your Task
- Select agent archetype (Researcher, Validator, etc.)
- Create identity card
- Validate against CONSTITUTION.md
- Generate agent specification
- Document spawn patterns
Report results to COORD_TOOLING when complete.
"""
)
COORD_TOOLING can execute these without asking:
Non-negotiable rules:
User: /coord-tooling Create skills for Deputies and Coordinators
COORD_TOOLING Response:
User: /coord-tooling Add MCP tool for burnout monitoring
COORD_TOOLING Response:
User: /coord-tooling Update /schedule-optimization skill with new patterns
COORD_TOOLING Response:
## COORD_TOOLING Report: [Task Name]
**Mission:** [Task description]
**Date:** [Timestamp]
### Approach
[High-level coordination approach]
### Specialists Deployed
**TOOLSMITH:**
- [Specific creation tasks completed]
**TOOL_QA:**
- [Specific testing tasks completed]
**TOOL_REVIEWER:**
- [Specific review tasks completed]
**AGENT_FACTORY:**
- [Specific agent creation tasks completed]
### Skills/Tools Created
1. **[Skill/Tool Name]:**
- Purpose: [Brief description]
- Location: [File path]
- Aliases: [Command aliases]
- Integration: [How it integrates with existing tools]
2. **[Skill/Tool Name]:**
- Purpose: [Brief description]
- Location: [File path]
- Aliases: [Command aliases]
- Integration: [How it integrates with existing tools]
### Quality Checks
- [x] YAML frontmatter valid
- [x] Documentation complete
- [x] Examples provided
- [x] No duplication with existing tools
- [x] CONSTITUTION.md compliance validated
- [x] Integration tested
### Documentation Updates
- [x] AGENT_MCP_MATRIX.md updated (if MCP tools)
- [x] Armory/ documentation updated
- [x] INDEX.md updated (if needed)
- [x] Related skills cross-referenced
### Handoff
**To ARCHITECT:** [Any architectural concerns or approvals needed]
**To Users:** [How to invoke new skills/tools]
---
*COORD_TOOLING coordination complete. Build tools and skills that empower agents to work effectively and autonomously.*
| Skill | Integration Point |
|---|---|
/architect | Parent deputy - escalate architectural decisions |
/skill-factory | Specialist skill for skill creation patterns |
/agent-factory | Specialist skill for agent creation |
/code-review | Review tool implementations |
/coord-tooling (primary)/tooling (short form)/tools (alternative)COORD_TOOLING: Build tools and skills that empower agents to work effectively and autonomously.
Project scaffolding, deployment configuration, and CI/CD setup for Google ADK agents.
Set up tracing, logging, and monitoring for deployed ADK agents across Cloud Trace, BigQuery, and third-party platforms.
Enterprise Azure infrastructure architect generating Bicep or Terraform from workload descriptions.
Plan and configure production-ready Azure Kubernetes Service clusters with Day-0 and Day-1 best practices.
Raw mechanical interfaces fusing Swiss typographic print with military terminal aesthetics. Rigid grids, extreme type scale contrast, utilitarian color, analog degradation effects. For data-heavy dashboards, portfolios, or editorial sites that need to feel like declassified blueprints.
Web search, scraping, extraction, crawling, and monitoring via ScrapeGraph AI CLI.
Skill for working with Firebase Hosting (Classic). Use this when you want to deploy static web apps, Single Page Apps (SPAs), or simple microservices. Do NOT use for Firebase App Hosting.
Deploy and manage web apps with Firebase App Hosting. Use this skill when deploying Next.js/Angular apps with backends.
Deploy applications and websites to Vercel. Use when the user requests deployment actions like "deploy my app", "deploy and give me the link", "push this live", or "create a preview deployment".
Build SEO-optimized pages at scale using templates, data, and proven playbook patterns.
Design and build isolated, reusable Convex backend components with clear boundaries and app-facing wrappers.
Deploy and manage projects on Vercel using token-based authentication. Use when working with Vercel CLI using access tokens rather than interactive login — e.g. "deploy to vercel", "set up vercel", "add environment variables to vercel".
Opus.ai: Revolutionize Your Web Experience
Build a no-code AI app in minutes.
An IDE for code migration from legacy to modern frameworks through coding agents.
Automate CGI animation in live-action scenes
Branded artistic QR-code concepts
Launch a website in seconds with AI.
Streamline Your Coding Experience with AI Code Helper
Convert any screenshot or design to clean code.