agentleFS
full-stack-skillsfull-stack-skills/agent-skills/skills/skill-sop-creator/SKILL.md

skill-sop-creator

Skill2 starsChanged 54 days agoApache-2.0View on GitHub

Guide for creating Standard Operating Procedures and SOPs and composite workflows by combining atomic Agent Skills. Use when users want to design, structure, or implement multi-step workflows that orchestrate multiple skills for complex business goals. Transforms loose tool collections into reliable, repeatable business processes.

The file

Files
SKILL.md

skill-sop-creator

Guide for creating Standard Operating Procedures (SOPs) and composite workflows by combining atomic Agent Skills. Use this skill when users want to design, structure, or implement multi-step workflows (SOPs) that orchestrate multiple skills to achieve complex business goals. This skill transforms loose collections of tools into reliable, repeatable business processes.

Parameters

NameTypeRequiredDescription
actionstringtrueThe action to perform. One of search_skills, draft_sop, validate_sop.
contextstringfalseContext for the action (e.g. business goal for drafting, search query for searching).

Actions

1. Search Atomic Skills

Finds available atomic skills to include in your SOP.

  • Command: skill-sop-creator(action="search_skills", context="pdf processing")
  • Output: List of relevant atomic skills (e.g., pdf-split, pdf-merge, ocr-extract) that can be steps in your SOP.

2. Draft SOP Structure

Generates a draft SKILL.md for a composite skill (SOP) based on a business goal.

  • Command: skill-sop-creator(action="draft_sop", context="Daily Competitor Analysis Report")
  • Output: A structured markdown template defining the workflow steps, required atomic skills, and decision logic.

3. Validate SOP

Checks if a proposed SOP structure is valid and if referenced skills exist.

  • Command: skill-sop-creator(action="validate_sop", context="<sop_content>")
  • Behavior: Verifies that steps are logical and dependencies are met.

SOP Design Principles

  1. Atomic Foundation: SOPs should rely on small, single-purpose skills (e.g., pencil-draw-rect not draw-entire-ui).
  2. Deterministic Flow: Define clear steps: Step 1 -> Step 2 -> Decision -> Step 3.
  3. Human-in-the-loop: Include checkpoints where the Agent should ask for user confirmation.

Example SOP Structure

# Daily Competitor Analysis SOP

## 1. Information Gathering
- **Skill**: `web-search`
- **Action**: Search for "competitor name" + "news"
- **Output**: List of URLs

## 2. Content Extraction
- **Skill**: `web-scraper`
- **Input**: URLs from Step 1
- **Output**: Raw text

## 3. Analysis
- **Skill**: `llm-summarize`
- **Input**: Raw text
- **Prompt**: "Identify key pricing changes and feature launches."

## 4. Reporting
- **Skill**: `pdf-generator`
- **Input**: Summary
- **Output**: PDF Report

Notes

  • An SOP is essentially a "Composite Skill" that acts as a conductor for other "Atomic Skills".
  • This skill helps you design that conductor.

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.