agentleFS
Sign inStart free
Arcanea-LabsArcanea-Labs/Starlight-Intelligence-System/skills/orchestration/workflow-design/SKILL.md

orchestration/workflow-design

Skill10 starsChanged 2 months agoMITView on GitHub

Use when creating multi-step execution plans or processes — designs reusable, efficient workflows that coordinate agents, skills, tools, and external systems into reliable execution pipelines. Default skill for Starlight Orchestrator.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 5 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Default for: Starlight Orchestrator

    line 15
  2. Distinctive:

    Add error handling for each step

    line 29
  3. Distinctive:

    Add checkpoints for user verification (if needed)

    line 30
  4. Distinctive:

    Document the template with clear parameter descriptions

    line 47
  5. Distinctive:

    Add to Orchestration Engine workflow templates

    line 49

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Workflow Design

"A workflow is a promise: do these steps, get this result."

When This Skill Activates

  • Creating multi-step execution plans or processes
  • Keywords: "workflow", "process", "pipeline", "steps", "sequence", "automate"
  • Default for: Starlight Orchestrator

What This Skill Does

Designs reusable, efficient workflows that coordinate agents, skills, tools, and external systems into reliable execution pipelines.

Procedures

Procedure 1: Workflow Creation

  1. Define the workflow's purpose and expected outcome
  2. Identify all steps required
  3. For each step: define input, action, output, owner
  4. Identify dependencies between steps
  5. Add error handling for each step
  6. Add checkpoints for user verification (if needed)
  7. Define success criteria for the workflow

Procedure 2: Workflow Optimization

  1. Map the current workflow
  2. Identify bottlenecks (slowest steps)
  3. Find parallelization opportunities
  4. Remove unnecessary steps
  5. Consolidate similar steps
  6. Measure estimated vs actual execution time
  7. Store optimization as pattern in Operational Vault

Procedure 3: Workflow Template Creation

  1. Identify a recurring workflow pattern
  2. Abstract specific details into parameters
  3. Document the template with clear parameter descriptions
  4. Store in Operational Vault for reuse
  5. Add to Orchestration Engine workflow templates

Integration Points

  • Vault: Operational Vault (workflow templates and patterns)
  • Agents: Orchestrator (primary), all agents (as workflow participants)
  • Engine: Orchestration Engine (execution)

Quality Criteria

  • Does each step have clear input, action, and output?
  • Are dependencies explicit?
  • Is error handling included?
  • Is the workflow reusable?

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free