a5c-ai/babysitter / library/methodologies/metaswarm/skills/external-tool-coordination
external-tool-coordination
VerifiedCoordinate external AI tool integration (OpenAI Codex, Google Gemini) for cross-model adversarial review and delegated implementation.
SKILL.md
View on GitHub---
name: external-tool-coordination
description: Coordinate external AI tool integration (OpenAI Codex, Google Gemini) for cross-model adversarial review and delegated implementation.
allowed-tools: Read, Write, Edit, Bash, Grep, Glob, WebFetch, WebSearch, Agent, AskUserQuestion
graph:
domains: [domain:software-engineering]
skillAreas: [skill-area:agentic-loops, skill-area:orchestration-loop]
workflows: [workflow:feature-development]
topics: [topic:developer-experience]
roles: [role:tech-lead, role:backend-engineer]
---
- For cross-model adversarial review (writer reviewed by different model)
- When delegating implementation to cheaper external models
- For escalation chains across tools
## Capabilities
- **Delegated Implementation** - Send work units to external AI tools for implementation
- **Cross-Model Review** - Implementation by Model A, adversarial review by Model B
- **Escalation Chains** - Tool A -> Tool B -> Claude -> human
- **Cost Optimization** - Route simpler tasks to cheaper models
## Configuration
Requires `.metaswarm/external-tools.yaml`:
```yaml
tools:
- name: codex
type: openai
capabilities: [implement, review]
- name: gemini
type: google
capabilities: [implement, review]
escalation:
chain: [codex, gemini, claude, human]
```
## Agents Used
- `agents/swarm-coordinator/` - Multi-tool orchestration
## Tool Use
Invoke as part of: `methodologies/metaswarm/metaswarm-swarm-coordinator`
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |