coord-tooling
About
The COORD_TOOLING skill coordinates development tools and agent skills creation, specifically for building and updating MCP server tools. It requires git context and uses Sonnet-tier models for domain coordination tasks. Key features include parallel execution capabilities and escalation triggers for breaking changes or security-related tooling.
Quick Install
Claude Code
Recommended/plugin add https://github.com/majiayu000/claude-skill-registrygit clone https://github.com/majiayu000/claude-skill-registry.git ~/.claude/skills/coord-toolingCopy and paste this command in Claude Code to install this skill
Documentation
COORD_TOOLING Skill
Purpose: Invoke COORD_TOOLING for development tools and agent skills coordination Created: 2026-01-06 Trigger:
/coord-toolingor/toolingor/toolsModel Tier: Sonnet (Domain Coordination)
When to Use
Invoke COORD_TOOLING for tools and skills development:
MCP Tools Development
- Create new MCP server tools
- Update existing tool specifications
- Test tool correctness and performance
- Document tool capabilities
- Maintain AGENT_MCP_MATRIX.md
Agent Skills Development
- Create new agent skills following skill-factory patterns
- Update existing skill specifications
- Validate skills against CONSTITUTION.md
- Test skill invocation and behavior
- Maintain skill documentation
Tool Quality and Review
- Review tool/skill PRs
- Validate tool specifications
- Test edge cases
- Ensure no duplication
Do NOT use for:
- Backend infrastructure (use /coord-platform)
- Scheduling logic (use /coord-engine)
- Frontend components (use /coord-frontend)
- Release management (use /coord-ops)
Authority Model
COORD_TOOLING is a Coordinator reporting to ARCHITECT:
Can Decide Autonomously
- Tool implementation approaches
- Skill structure and format
- Testing strategies
- Documentation format
- Tool naming conventions
Must Escalate to ARCHITECT
- Breaking changes to existing MCP tools affecting agents
- New tool capabilities requiring architectural approval
- Agent specification conflicts with hierarchy
- Security implications in tool implementations
- Cross-tool dependencies requiring coordination
Coordination Model
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
Activation Protocol
1. User or ARCHITECT Invokes COORD_TOOLING
/coord-tooling [task description]
Example:
/coord-tooling Create skills for Deputies and Coordinators
2. COORD_TOOLING Loads Identity
The COORD_TOOLING.identity.md file is automatically loaded, providing:
- Standing Orders (execute without asking)
- Escalation Triggers (when to ask ARCHITECT)
- Key Constraints (non-negotiable rules)
- Specialist spawn authority
3. COORD_TOOLING Analyzes Task
- Determine if skill creation needed (spawn TOOLSMITH)
- Assess if testing needed (spawn TOOL_QA)
- Identify review requirements (spawn TOOL_REVIEWER)
- Check if new agent creation needed (spawn AGENT_FACTORY)
4. COORD_TOOLING Spawns Specialists
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.
"""
)
5. COORD_TOOLING Integrates Results
- Review all created skills/tools
- Ensure consistency across implementations
- Verify no duplication
- Update documentation
- Report completion to ARCHITECT
Standing Orders (From Identity)
COORD_TOOLING can execute these without asking:
- Create and maintain MCP tools for agent workflows
- Develop new agent skills following skill-factory patterns
- Validate tool specifications against CONSTITUTION.md
- Test tools for correctness, performance, and edge cases
- Review and approve tool/skill PRs
- Update AGENT_MCP_MATRIX.md when tools change
- Maintain tool documentation in Armory/
Key Constraints (From Identity)
Non-negotiable rules:
- Do NOT break existing tool contracts without migration plan
- Do NOT create tools that bypass security controls
- Do NOT skip validation against agent constitution
- Do NOT duplicate functionality of existing tools
- Do NOT deploy tools without comprehensive tests
Example Missions
Create Agent Skills
User: /coord-tooling Create skills for Deputies and Coordinators
COORD_TOOLING Response:
- Spawn TOOLSMITH to create skill files
- Follow skill-factory patterns for structure
- Include proper YAML frontmatter
- Document activation protocols
- Spawn TOOL_QA for validation
- Spawn TOOL_REVIEWER for quality review
- Report completion to ARCHITECT
Create New MCP Tool
User: /coord-tooling Add MCP tool for burnout monitoring
COORD_TOOLING Response:
- Spawn TOOLSMITH for tool specification
- Design tool interface and parameters
- Implement tool logic
- Spawn TOOL_QA for testing
- Update AGENT_MCP_MATRIX.md
- Document tool in Armory/
- Report completion to ARCHITECT
Review and Update Existing Skill
User: /coord-tooling Update /schedule-optimization skill with new patterns
COORD_TOOLING Response:
- Spawn TOOL_REVIEWER to analyze current skill
- Identify improvements needed
- Spawn TOOLSMITH for updates
- Spawn TOOL_QA for validation
- Ensure backward compatibility
- Report completion to ARCHITECT
Output Format
Tooling Coordination Report
## 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.*
Related Skills
| 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 |
Aliases
/coord-tooling(primary)/tooling(short form)/tools(alternative)
COORD_TOOLING: Build tools and skills that empower agents to work effectively and autonomously.
GitHub Repository
Related Skills
algorithmic-art
MetaThis Claude Skill creates original algorithmic art using p5.js with seeded randomness and interactive parameters. It generates .md files for algorithmic philosophies, plus .html and .js files for interactive generative art implementations. Use it when developers need to create flow fields, particle systems, or other computational art while avoiding copyright issues.
subagent-driven-development
DevelopmentThis skill executes implementation plans by dispatching a fresh subagent for each independent task, with code review between tasks. It enables fast iteration while maintaining quality gates through this review process. Use it when working on mostly independent tasks within the same session to ensure continuous progress with built-in quality checks.
executing-plans
DesignUse the executing-plans skill when you have a complete implementation plan to execute in controlled batches with review checkpoints. It loads and critically reviews the plan, then executes tasks in small batches (default 3 tasks) while reporting progress between each batch for architect review. This ensures systematic implementation with built-in quality control checkpoints.
cost-optimization
OtherThis Claude Skill helps developers optimize cloud costs through resource rightsizing, tagging strategies, and spending analysis. It provides a framework for reducing cloud expenses and implementing cost governance across AWS, Azure, and GCP. Use it when you need to analyze infrastructure costs, right-size resources, or meet budget constraints.
