Agent Workflow Designer
SkillAI & modelsWhen a task needs several AI agents working together, this skill helps your AI design the workflow that coordinates them. It picks the right structure for the job, sets rules for how work passes between agents, and generates config skeletons you can build on. Pipelines come with failure handling and cost controls built in.
Available today. Use it from your connected AI after setup.
No other account needed.
After adding the skill, describe the job you want split across agents, or an existing pipeline you want to refactor, and your AI will propose a pattern and generate a config skeleton to start from.
Then ask your AI: use the Agent Workflow Designer skill
What your AI can do with it
- Design multi-step agent pipelines using sequential, parallel, or hierarchical patterns
- Decide whether a task is better handled by a single agent or multiple agents
- Write handoff contracts that define how work passes between agents
- Add failure handling so pipelines can recover when a step breaks
- Set cost and context controls to keep long workflows manageable
- Generate workflow config skeletons ready to fill in
What this skill tells your AI
The instructions your AI receives, as published by alirezarezvani/claude-skills in .gemini/skills/agent-workflow-designer/SKILL.md and read by ahel’s review.
Tier: POWERFUL Category: Engineering Domain: Multi-Agent Systems / AI Orchestration
Overview
Design production-grade multi-agent workflows with clear pattern choice, handoff contracts, failure handling, and cost/context controls.
Core Capabilities
- Workflow pattern selection for multi-step agent systems
- Skeleton config generation for fast workflow bootstrapping
- Context and cost discipline across long-running flows
- Error recovery and retry strategy scaffolding
- Documentation pointers for operational pattern tradeoffs
When to Use
- A single prompt is insufficient for task complexity
- You need specialist agents with explicit boundaries
- You want deterministic workflow structure before implementation
- You need validation loops for quality or safety gates
Quick Start
# Generate a sequential workflow skeleton
python3 scripts/workflow_scaffolder.py sequential --name content-pipeline
# Generate an orchestrator workflow and save it
python3 scripts/workflow_scaffolder.py orchestrator --name incident-triage --output workflows/incident-triage.json
Pattern Map
sequential: strict step-by-step dependency chainparallel: fan-out/fan-in for independent subtasksrouter: dispatch by intent/type with fallbackorchestrator: planner coordinates specialists with dependenciesevaluator: generator + quality gate loop
Detailed templates: references/workflow-patterns.md
Recommended Workflow
- Select pattern based on dependency shape and risk profile.
- Scaffold config via
scripts/workflow_scaffolder.py. - Define handoff contract fields for every edge.
- Add retry/timeouts and output validation gates.
- Dry-run with small context budgets before scaling.
Common Pitfalls
- Over-orchestrating tasks solvable by one well-structured prompt
- Missing timeout/retry policies for external-model calls
- Passing full upstream context instead of targeted artifacts
- Ignoring per-step cost accumulation
Best Practices
- Start with the smallest pattern that can satisfy requirements.
- Keep handoff payloads explicit and bounded.
- Validate intermediate outputs before fan-in synthesis.
- Enforce budget and timeout limits in every step.
Signals
- GitHub stars
- 26k
- Forks
- 4k
- Last commit
- Aug 2026
Advanced
- Catalog kind
- skill
- Gateway key
agent-workflow-designer- Source
- github.com/alirezarezvani/claude-skills