Agent skill
route
Analyze project state and route user to the appropriate agent based on current context.
Install this agent skill to your Project
npx add-skill https://github.com/fabriqaai/specs.md/tree/main/src/flows/fire/agents/orchestrator/skills/route
SKILL.md
<file_system_scan critical="true">
Use these EXACT glob patterns:
<pattern purpose="Find intent briefs">
.specs-fire/intents/*/brief.md
</pattern>
<pattern purpose="Find work items">
.specs-fire/intents/*/work-items/*.md
</pattern>
Work items are {work-item-id}.md files directly in work-items/ folder.
</file_system_scan>
<action>Reconcile: add discovered items to state as pending</action>
<action>Parse current project state</action>
Plan run scope and start execution? [Y/n]
</output>
<check if="response == y">
<route_to>builder-agent (run-plan)</route_to>
</check>
<stop/>
</check>
Work items delivered:
{list completed work items}
Ready for next intent? [Y/n]
</output>
</check>
What do you want to build?
</output>
<route_to>planner-agent (intent-capture)</route_to>
<routing_decision_tree>
state.yaml + file system scan
│
├── runs.active? ─────────────> Builder (run-execute, resume)
│
├── pending work items? ──────> Builder (run-plan, then execute)
│
├── intent without work items? > Planner (work-item-decompose)
│
└── no active intents ────────> Planner (intent-capture)
</routing_decision_tree>
<context_passed_to_agents> To Planner:
context:
action: intent-capture | work-item-decompose
intent_id: {if decomposing}
To Builder:
context:
action: run-plan | run-execute | resume
pending_items: [{list of pending work items}] # for run-plan
run_id: {if resuming}
</context_passed_to_agents>
<success_criteria> File system scanned for untracked intents/work-items State reconciled with file system Correct agent selected based on state Context passed to target agent </success_criteria>
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
frontend-design
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics.
run-status
Display current run status and progress. Shows work item, mode, duration, and files changed.
run-plan
Plan the scope of a run by discovering available work items and suggesting groupings. Invoked before run-execute.
walkthrough-generate
Generate implementation walkthrough for human review after run completion. Documents decisions, changes, and verification steps.
code-review
Review code written during a run, auto-fix no-brainer issues, and suggest improvements requiring confirmation. Invoked after tests pass.
run-execute
Execute work items based on their assigned mode (autopilot, confirm, validate). Supports single-item and multi-item (batch/wide) runs.
Didn't find tool you were looking for?