mcpField
W
workflow-automator

workflow-automator

github.com/onewave-aiProductivity393268 installsUpdated 1w ago
Repository

About workflow-automator

A skill that maps a manual business process and designs an automated replacement, producing an implementation-oriented workflow document. It covers process analysis, tool selection, error handling, and estimated time savings and ROI.

Key features

  1. 01Current-state process mapping
  2. 02Pain-point and automation scoring
  3. 03Triggers, branching, and error handling
  4. 04Platform recommendations
  5. 05Mermaid diagrams and ROI estimates

Use cases

  1. 01Documenting a manual business process
  2. 02Designing an automated workflow with human checkpoints
  3. 03Estimating time savings and automation costs

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/onewave-ai/claude-skills --skill workflow-automator

After installing, type/workflow-automatorin Claude Code to confirm it loaded.

Bundled files

References and scripts installed along with SKILL.md.

references/
analysis-framework.md
automation-design.md
diagram-and-estimation-standards.md
intake.md
output-template.md
tool-recommendations.md

Details

From the project README

Workflow Automator

Transform a manual business workflow into an optimized automated system: map how work gets done today, then design a complete automated replacement with triggers, conditions, actions, branching, and error handling. Deliver a comprehensive workflow-automation.md.

Contents

  • references/intake.md -- What to gather and how to ask for missing detail
  • references/analysis-framework.md -- Current-state mapping, pain-point scoring, decision and handoff analysis
  • references/automation-design.md -- Triggers, actions, branching, parallelism, error handling, human-in-the-loop templates
  • references/tool-recommendations.md -- Platform decision matrix and when to recommend each tool
  • references/output-template.md -- Full workflow-automation.md structure to fill in
  • references/diagram-and-estimation-standards.md -- Mermaid conventions and time/ROI estimation rules

Workflow

  1. Intake. Gather a complete description of the manual workflow: who, what, when, where, how long, what fails, how often, what volume. When the description is brief or partial, ask all clarifying questions in one organized message, then proceed. See references/intake.md.
  2. Map the current state. Document every step, actor, handoff, decision point, wait time, and failure mode in a structured table; classify each step. See references/analysis-framework.md.
  3. Identify pain points. Score each step on automation potential, impact, and risk. Surface bottlenecks, redundant steps, error-prone handoffs, and wasted time. See references/analysis-framework.md.
  4. Design the automated flow. Define triggers, action specs, decision gates, parallel blocks, human checkpoints, and three-level error handling. See references/automation-design.md.
  5. Recommend tools. Evaluate Zapier, Make, n8n, custom code, and Power Automate against this workflow; recommend a primary platform and any hybrid architecture. See references/tool-recommendations.md.
  6. Estimate impact. Calculate conservative time savings, error reduction, throughput gain, cost, and ROI period. See references/diagram-and-estimation-standards.md.
  7. Deliver. Generate the full workflow-automation.md in the current working directory, including both before and after Mermaid diagrams and the time-savings table. See references/output-template.md and references/diagram-and-estimation-standards.md.

Output Rules

  • Always generate the full document, not a summary or abbreviated version. Make it self-contained enough to implement from alone.
  • Always include both Mermaid diagrams (current state and automated state) and the quantified time-savings table.
  • Use no emojis anywhere in the output.

Quality Checklist

Before delivering, verify:

  • Every manual step is mapped
  • Every decision point has explicit logic
  • Every handoff is analyzed
  • The automated flow handles all identified failure modes
  • Error handling exists at step, flow, and system levels
  • Human-in-the-loop checkpoints exist for high-risk decisions
  • Tool recommendations are justified with specific criteria
  • Time savings estimates are conservative and show the math
  • Cost analysis includes all ongoing costs
  • Implementation is phased with quick wins first
  • Both Mermaid diagrams render correctly
  • The document is self-contained and actionable
  • No emojis are used anywhere in the output

Comments

Markdown supported