agentleFS
mikeyobrienmikeyobrien/rho/skills/create-sop/SKILL.md

create-sop

Skill372 starsChanged 8 months agoMITView on GitHub

Create a new SOP-style skill as skills/<name>/SKILL.md with kind: sop frontmatter and structured Parameters/Steps sections.

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    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:

    Create a new workflow skill where SOPs are implemented as skills.

    line 11

≈ “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

Create SOP Skill

Overview

Create a new workflow skill where SOPs are implemented as skills.

Canonical artifact:

  • skills/<skill-name>/SKILL.md

A valid SOP skill must include:

  • YAML frontmatter with name, description, and kind: sop
  • ## Parameters
  • ## Steps

Parameters

  • sop_topic (required): What the SOP skill should do
  • skill_name (optional): Kebab-case skill name. If omitted, generate from topic.
  • output_dir (optional, default: skills): Parent directory for the skill
  • include_examples (optional, default: true): Include ## Examples
  • include_troubleshooting (optional, default: true): Include ## Troubleshooting

Steps

1. Gather requirements

Constraints:

  • You MUST ask for all required inputs up front.
  • You MUST clarify intended outcomes, required tools, and failure boundaries.
  • You MUST identify what must be interactive vs autonomous.

2. Define the skill contract

Constraints:

  • You MUST create/confirm a kebab-case skill_name.
  • You MUST define parameters in a machine-readable bullet format.
  • You MUST separate required vs optional params and defaults.

3. Draft SOP skill content

Constraints:

  • You MUST generate frontmatter:
---
name: <skill_name>
description: <one-line purpose>
kind: sop
---
  • You MUST include these sections in order:
    1. # <Title>
    2. ## Overview
    3. ## Parameters
    4. ## Steps
  • You MUST use RFC-2119 constraints (MUST, SHOULD, MAY).
  • You MUST include explicit negative constraints with reasons when relevant.

4. Write the artifact

Constraints:

  • You MUST write to: {output_dir}/{skill_name}/SKILL.md
  • You MUST create parent directories when missing.
  • You MUST use the skill artifact convention only: skills/<skill_name>/SKILL.md.

5. Validate

Constraints:

  • You MUST verify frontmatter includes kind: sop.
  • You MUST verify ## Parameters and ## Steps are present.
  • You SHOULD suggest running via: /skill run {skill_name}.

Output

When done, report:

  • Created path
  • Parameter list
  • Short execution example

Example

Input:

  • sop_topic: "Automated code review with lint/test gates"
  • skill_name: code-review

Output path:

  • skills/code-review/SKILL.md

Run with:

  • /skill run code-review

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.