From agents
Analyze a task and recommend agent decomposition level. Routes to single-agent, fan-out, or planner-generator-reviewer pipeline.
How this skill is triggered — by the user, by Claude, or both
Slash command
/agents:dispatchThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Analyze the task against these criteria:
Analyze the task against these criteria:
| Signal | Single Agent | Fan-Out | Pipeline (P/G/R) |
|---|---|---|---|
| Files touched | 1-3 | 4-15 (similar ops) | 4-15 (different ops) |
| Task type | Bug fix, small feature | Batch migration, bulk refactor | New feature, architecture change |
| Interdependence | High (changes depend on each other) | Low (same operation, different files) | Medium (phases depend on prior phase) |
| Risk | Low | Low-Medium | Medium-High |
/fan-out to dispatch parallel subagentsDISPATCH RECOMMENDATION:
Route: [Single Agent | Fan-Out | Pipeline]
Reason: <one sentence>
Agent(s): <which agents to use>
Estimated scope: <files/operations count>
Risk level: <low/medium/high>
Guides collaborative design exploration before implementation: explores context, asks clarifying questions, proposes approaches, and writes a design doc for user approval.
Creates structured, bite-sized implementation plans from specs or requirements before writing code. Useful for breaking down multi-step tasks into testable steps with file structure and task boundaries.
Synthesizes the current conversation into a structured spec (PRD) and publishes it to the project issue tracker with a ready-for-agent label, without interviewing the user.
npx claudepluginhub artmin96/forge-studio --plugin agents