Skip to content
All Skills

Local Vco Roles

Codex-local role pack for dialectic multi-agent reviews, designed to be compatible with the local vibe skill.

Agent Orchestration|v1|Updated 7/14/2026|GitHub source
MCP get_skill({ skillId: "local-vco-roles-080b102c" })

Use this skill with your agent

Create a free account and connect via MCP

Get Started Free
# local-vco-roles

Codex-local role pack for dialectic multi-agent reviews, designed to be compatible with the local `vibe` skill.

## When to Use

Use this skill when:
1. You run `/vibe` and need a stable role set for dialectic review.
2. You want reproducible multi-role analysis using TeamCreate-style orchestration.
3. You need standardized outputs across team-lead / bug / architecture / integration / usability roles.

## Vibe Compatibility Contract (Must Follow)

1. Grade handshake:
- M/L: do NOT force TeamCreate orchestration.
- XL: TeamCreate workflow is allowed.

2. Rule-1 boundary:
- Never mix multiple agent systems for the same task.
- Follow `vibe` conflict rules first.

3. Command priority:
- User explicit command > `vibe` routing > this role pack defaults.

4. Output severity:
- Always use `CRITICAL > HIGH > MEDIUM > LOW`.

5. Staged confirmation:
- Keep major confirmation points aligned with `vibe` team protocol.

6. Memory behavior:
- Default state tracking via TodoWrite-style task state.
- Optional enhancements (if available) must not become hard dependencies.

## Role Prompt Library

- Team lead: `references/role-prompts/team-lead.md`
- Bug analyst: `references/role-prompts/bug-analyst.md`
- Architecture critic: `references/role-prompts/arch-critic.md`
- Integration analyst: `references/role-prompts/integration-analyst.md`
- Usability analyst: `references/role-prompts/usability-analyst.md`

## Recommended XL Workflow

1. Read `references/vibe-compatibility.md`.
2. Create 5 tasks (lead + 4 analysts).
3. Assign each role using the prompt files above.
4. Collect results and aggregate by severity.
5. Produce one merged decision set (`keep / simplify / remove`).

## Optional Utility

- Run scaffold helper: `scripts/new-run.ps1 -Topic <name>`
#broad-capability#creative#multi#agent#architecture

Related Skills

More skills in Agent Orchestration

1. Product type search — what design patterns fit this product?

Design UI/UX systems with style guides, palettes, typography, and component specs for new interfaces

#github#broad-capabilityMIT

Acp Router

Route plain-language requests for Claude Code, Cursor, Copilot, OpenClaw ACP, OpenCode, Gemini CLI, Qwen, Kiro, Kimi, iFlow, Factory Droid, Kilocode, or explicit ACP harness work into either OpenClaw ACP runtime sessions or direct acpx-driven sessions ("telephone game" flow). For coding-agent thread requests, read this skill first, then use only `sessions_spawn` for thread creation. Codex chat binding defaults to the native Codex app-server plugin unless ACP is explicit or background spawn needs ACP.

#broad-capability#browserMIT

Add New Safe Output Type

Adding a New Safe Output Type to GitHub Agentic Workflows

#github#broad-capabilityMIT

Agent Governance

Patterns and techniques for adding governance, safety, and trust controls to AI agent systems. Use this skill when: - Building AI agents that call external tools (APIs, databases, file systems) - Implementing policy-based access controls for agent tool usage - Adding semantic intent classification to detect dangerous prompts - Creating trust scoring systems for multi-agent workflows - Building audit trails for agent actions and decisions - Enforcing rate limits, content filters, or tool restrictions on agents - Working with any agent framework (PydanticAI, CrewAI, OpenAI Agents, LangChain, AutoGen)

#github-copilot#agentMIT

Agentic Development

Build AI agents with Pydantic AI (Python) and Claude SDK (Node.js)

#claude-bootstrap#bootstrapMIT

Agentic Workflows

Route gh-aw workflow design/create/debug/upgrade requests to the right prompts.

#broad-capability#agentic-workflowsMIT