Menu
Select the best bundled developer agent for automated expansion leaves and document fallback decisions.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Instructions for using gcode CLI for code search and retrieval. Loaded on demand when project has a code index.
Pre-transition checklist for closing or reviewing tasks. Covers fresh verification evidence, commits, and memory gates.
Use when processing CodeRabbit review comments, CodeRabbit CLI reports, or `$gobby coderabbit [findings]` requests.
Use when creating, editing, or validating Gobby skills, especially when a skill must change agent behavior or become discoverable through gobby-skills.
Use when coordinating a full gobby build run for an epic or task, especially when the user assigns the current session as coordinator, asks for a coordination epic, wants build agents/worktrees monitored, or wants gobby build bugs fixed so future runs work unattended.
Router contract for provider-aware Gobby help and installed skill dispatch.
| name | expansion-agent-selection |
| description | Select the best bundled developer agent for automated expansion leaves and document fallback decisions. |
| version | 1.0.0 |
| category | core |
| internal | true |
| triggers | expansion agent selection, assigned agent, automated leaves |
| metadata | {"gobby":{"audience":"all","depth":0}} |
Use this skill during the expander's Agent Selection step after leaf generation and before the compiled spec is returned or applied.
Assign an agent for every automated leaf in these categories:
codeconfigdocsrefactortestReject category: manual, category: planning, and category: research
leaves. Those categories are valid for direct task creation, but automated
expansion manifests must compile to deterministic development-forward leaf work.
Use labels and task text as weak signals. They should guide the decision, not override clear file paths or task descriptions.
Prefer frontend-developer for work involving UI components, CSS, browser
behavior, accessibility, routing, client state, React, Vue, Svelte, Vite,
Webpack, Storybook, Playwright UI flows, Lighthouse, or frontend linting such as
ESLint.
Prefer backend-developer for APIs, CLIs, storage, migrations, schedulers,
workers, servers, daemon code, Python modules, pytest, mypy, Ruff, SQL,
psql, MCP tools, workflow engines, and infrastructure tests.
Mixed-stack tasks that touch both UI and backend should be split when the plan permits. If splitting would violate the plan's atomic task shape, pick the primary agent for the riskiest surface and document the cross-concern surface in the leaf description.
list_agent_definitions.additional_skills empty unless the leaf needs a skill beyond the
agent's baseline competence.A confident match requires a clear category or content signal and an available agent whose name or description matches the surface. If the signal is weak, mixed, or no available agent crosses the threshold, use the fallback.
Default to backend-developer when no agent matches above the confidence
threshold. Append a ## Agent Selection marker to the leaf description that
explains the default, including the leaf category and the ambiguous signals.
Example marker:
## Agent Selection
No specialized agent matched this docs leaf above the confidence threshold.
Defaulting to `backend-developer` for auditability.
The fallback is intentional audit data, not an error path. Repeated fallback markers are the signal to add a more specialized agent later.