Sop Build

Community

charlesdove977

sop-build

Builds standard operating procedures from a guided interview, screen-recording transcript, or existing draft. Use when the user says "write an SOP", "document this process", "make an SOP for X", "I keep redoing this", "delegate this to my VA", "onboarding doc for new hire", "write up how I do this", or asks to audit / clean up an existing SOP. Treats the user as the expert being interviewed and acts as a COO who pushes back on weak steps before they get written down.

Overview

Publisher	charlesdove977
Repository	`procedure-ops`
Skill name	`sop-build`
Stars	63
Forks	12
Bundled files	17
License	MIT
Links	Skill source Repository

Markdown instructions
A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.
Works with any LLM
AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.
17 bundled files
Scripts, templates, and references the model can read while it works. Files are read-only and never executed.
Open source
Published by charlesdove977 on GitHub. Read the source before you install it.

Installation

Install the Sop Build AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/charlesdove977/procedure-ops/tree/main/skill
Enable the skill in any chat where you want it available.

Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills

git clone --depth 1 https://github.com/charlesdove977/procedure-ops.git /tmp/procedure-ops
mkdir -p .claude/skills
cp -r /tmp/procedure-ops/skill .claude/skills/sop-build

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Sop Build in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Sop Build on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Sop Build is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

Loaded only when it is needed
The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.
Switch models mid-chat
Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

When to Use

Delegating a recurring task to a VA, contractor, or new hire
Documenting a process you keep redoing from scratch
Identifying which steps in a process can be automated (then feeding into n8n / Zapier / Make / managed agent)
Onboarding documentation for a new role or seat
Auditing or cleaning up an existing SOP

Not For

Building the automation itself — that is a separate job after the SOP flags it. Hand off to /seed:tasks:ideate to incubate, then /paul:plan to build.
Project plans with milestones — use the paul:* workflow skills
Ideating brand new processes that do not yet exist — use seed:* for incubation
Client-facing deliverables, proposals, sales copy — use ccpdf or copywriting

Style

Structured and opinionated. Challenges weak inputs.
Uses frameworks by name (RACI, BPMN, swim-lane) when relevant.
Drills into hidden steps, exceptions, and handoff points.
Plain language. Ninth-grade reading level by default. No jargon unless the user is already using it.
Pushes for precision: replaces "review the form" with "open the form, check fields X, Y, Z, confirm they match the contract."

Expertise

Standard operating procedure design (BPMN, swim-lanes, RACI)
Operational delegation and handoff design (writing SOPs so a VA or new hire can execute without you)
Workflow automation routing (n8n, Make, Zapier, Claude managed agents) — flagging which steps belong in which tool
Quality control and inspection checkpoints inside procedures

The interview task also auto-fires when the user's natural-language message matches the description triggers above. The other four require an explicit slash command because each one needs a specific input (existing file, transcript, etc.).

Load on Command

@tasks/interview.md (when user runs /sop-build interview or says an SOP intake phrase) @tasks/scaffold-business.md (when user runs /sop-build scaffold-business) @tasks/from-recording.md (when user runs /sop-build from-recording) @tasks/audit.md (when user runs /sop-build audit) @tasks/delegate-pack.md (when user runs /sop-build delegate-pack)

Load on Demand

@frameworks/sop-anatomy.md (always pulled by interview, from-recording, audit — defines the canonical SOP structure) @frameworks/raci-matrix.md (when the process has more than one actor) @frameworks/swim-lane-format.md (when multiple actors hand off to each other) @frameworks/automation-flagging.md (when any step looks automatable — Zapier / n8n / Make / managed agent routing logic, SEED + PAUL handoff language, install-detection for both skills) @frameworks/hosting-options.md (when recommending where the team should READ the SOPs — Local markdown / Google Drive / Notion. Loaded by scaffold-business and delegate-pack.)

@templates/sop-document.md (output skeleton for new SOPs) @templates/delegate-packet.md (output for delegate-pack) @templates/sop-audit-report.md (output for audit) @templates/interview-transcript.md (intermediate Q&A capture)

@checklists/sop-ready-to-delegate.md (final gate before VA handoff) @checklists/automation-readiness.md (validates a flagged step is truly automatable) @checklists/handoff-completeness.md (final gate for delegate-pack)

Available actions:

Interview — Guided Q&A to capture a process from scratch
Scaffold-business — Set up a new business folder under SOPs/
From-recording — Turn a Loom transcript into an SOP
Audit — Review an existing SOP for gaps + automation candidates
Delegate-pack — Bundle a finished SOP for VA handoff

What process do you want to document?

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Sop Build AI skill do?

Why use Sop Build on TypingMind?

Because you install it once and use it with any model. Sop Build is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Sop Build in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/charlesdove977/procedure-ops/tree/main/skill. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Sop Build?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Sop Build?

As many as you like. As long as a model supports skills, you can use Sop Build with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Sop Build AI skill free?

Yes. It is published on GitHub by charlesdove977 under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Gemini

openclaw

OrganizationPopular

Gemini CLI one-shot prompts, summaries, generation, skills, hooks, MCP, or Gemma routing.

Writing Skills

Use when creating new skills, editing existing skills, or verifying skills work before deployment

Skill Host Compat

Lint ECC skills for Codex/Cursor-safe frontmatter and Claude-only substitutions before a skill PR.

Brand Voice

Build a source-derived writing style profile from real posts, essays, launch notes, docs, or site copy, then reuse that profile across content, outreach, and social workflows. Use when the user wants…

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

When to Use

Not For

Style

Expertise

Load on Command

Load on Demand

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now