Skip to content
Agentmart
Submit a tool

agent-workflow-designer

pick the right multi-agent/multi-step pattern (sequential, parallel, router, orchestrator, evaluator) and scaffold it before building — use when designing one…

Skill by Hugofsco

IndexedMIT
Write a review

Chalk Labs

Need help deploying agent-workflow-designer?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/hugofsco-agent-workflow-designer

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

pick the right multi-agent/multi-step pattern (sequential, parallel, router, orchestrator, evaluator) and scaffold it before building — use when designing one of Oceano's own visual Workflows, or a spawn_agent pipeline with more than one stage

Use cases: data, productivity, agent-building

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found
Runs as
Python package

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/agent-workflow-designer

What's inside

Skill name
agent-workflow-designer
Description
pick the right multi-agent/multi-step pattern (sequential, parallel, router, orchestrator, evaluator) and scaffold it before building — use when designing one of Oceano's own visual Workflows, or a spawn_agent pipeline with more than one stage
License
MIT
Instructions
20 lines in SKILL.md · view on GitHub

Before installing

  • Ships executable scripts

Files (2)

  • SKILL.md
  • workflow_scaffolder.py · scripts/

SKILL.md (first lines)

# Agent workflow designer

Directly applicable to Oceano's own node-canvas Workflows and to multi-stage
`spawn_agent` pipelines — pick the pattern before wiring nodes/agents together.

Patterns: **sequential** (strict step-by-step chain) · **parallel** (fan-out/fan-in,
independent subtasks — same shape as multiple `spawn_agent` calls joined at the end) ·
**router** (dispatch by intent, with a fallback) · **orchestrator** (a planner
coordinates specialist steps with dependencies) · **evaluator** (generate → quality
gate → loop, e.g. pairs well with [[self-eval]]).

Scaffold a skeleton before building: `python3 skills/agent-workflow-designer/scripts/workflow_scaffolder.py <pattern> --name <name>` (add `--output <path>.json` to save it).

Rules: start with the smallest pattern that satisfies the requirement — don't
orchestrate what one well-structured prompt or a single agent call can do. Keep
handoff payloads explicit and bounded (pass the specific artifact needed, not the
full upstream context/transcript). Put a timeout on every external-model step. Validate
each stage's output before fanning back in — don't let a bad intermediate result poison
the synthesis step.

From Hugofsco/oceano, MIT.

More from Hugofsco/oceano

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Jul 5, 2026 (4 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
Repository
github.com/Hugofsco/oceano
First seen
Oct 24, 2026
Last checked
Oct 24, 2026
Source
GitHubgithub-graphql

More from Hugofsco

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get agent-workflow-designer running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying agent-workflow-designer?

CallGet help
Cite this page

agent-workflow-designer skill. Agent Mart. https://agentmart.dev/skills/hugofsco-agent-workflow-designer (last updated 2026-10-24)