These are working tools, not reading. Each one is a single file that installs into your own AI assistant and runs the somai method on your company - in your environment, on your facts, with nobody watching. Nothing is collected here and nothing reaches somai unless you choose to send the output.

They run in any order, but they compound in this one: check the shopfront, audit the context, map the spend, design one loop, then plan the brain.

Using the skills

Each skill is one markdown file, and that is the whole trick: any assistant that can read a file can run one.

  • Claude Code. Run the install line under the skill, then ask for it by name, or just describe the problem - a skill offers itself when it matches.
  • Claude on the web or desktop. Add the file as a skill in your settings if your plan supports it, or simply attach the file to a conversation or project and say "run this on my company". Attaching works everywhere.
  • ChatGPT, Gemini, Copilot, Cursor, anything else. Download the file, attach or paste it, and say "run this". The file carries the method and the rules; your assistant supplies the conversation.

They work best in an assistant that can also reach what they audit - a shell for the website checks, your own notes for the context audit - but every one of them runs fine as a pure conversation.

somai-agent-ready

Can the assistants your buyers use actually read your website?

Twelve objective pass-or-fail checks on any site: AI crawler access, llms.txt, markdown for agents, structured data, canonical hygiene, social cards, an honest 404. No scores, no judgement - status codes and evidence, with what each miss costs and what to fix first.

Worth running when: Rethinking the website, planning content, or wondering why AI assistants never mention you.

You get: A verdict, the evidence table, and the three fixes that pay best.

Claude Code - one line:

mkdir -p ~/.claude/skills/somai-agent-ready && curl -fsSL https://somai.studio/skills/agent-ready/SKILL.md -o ~/.claude/skills/somai-agent-ready/SKILL.md

Any other assistant: the file is the skill - read or download it.

somai-context-audit

How much of what your company knows could a model actually read?

The new-hire test, run properly: ten probe questions across the five systems every company runs on, each answer classified by where it lives - a system, a document, a head, or nowhere. The audit behind the company brain argument, applied to your business in one sitting.

Worth running when: Before any serious AI initiative, after a disappointing pilot, or when the same questions keep being re-answered from scratch.

You get: A legibility map, the single most expensive gap, and the first move.

Claude Code - one line:

mkdir -p ~/.claude/skills/somai-context-audit && curl -fsSL https://somai.studio/skills/context-audit/SKILL.md -o ~/.claude/skills/somai-context-audit/SKILL.md

Any other assistant: the file is the skill - read or download it.

somai-spend-map

Why does the AI spend keep missing the P&L?

Maps every AI initiative you run - licences, copilots, pilots, agents - and shows the structure: which are retrofits, which can see each other, and how many times the same plumbing has been re-solved from scratch. The verdict is structural, so it needs no invented numbers.

Worth running when: At budget time, when the board asks what the AI spend returned, or when the tool count keeps rising and nothing compounds.

You get: The initiative map, the counts, and the one question that decides the next tranche of budget.

Claude Code - one line:

mkdir -p ~/.claude/skills/somai-spend-map && curl -fsSL https://somai.studio/skills/spend-map/SKILL.md -o ~/.claude/skills/somai-spend-map/SKILL.md

Any other assistant: the file is the skill - read or download it.

somai-decision-loop

What does one decision look like, rebuilt properly?

Takes one recurring decision - intake, a pricing exception, a hiring shortlist - and designs the loop: the model as a standing participant that drafts, checks and argues the other side, a named human keeping the call, dissent and the evidence rule built in.

Worth running when: Moving past copilots, putting AI into real decisions without losing control of them, or choosing the first serious use case.

You get: A one-page loop design, ending in the exact context the loop needs and where that context lives today.

Claude Code - one line:

mkdir -p ~/.claude/skills/somai-decision-loop && curl -fsSL https://somai.studio/skills/decision-loop/SKILL.md -o ~/.claude/skills/somai-decision-loop/SKILL.md

Any other assistant: the file is the skill - read or download it.

somai-brain-plan

Who does what, in what order, to install a company brain?

Turns your actual shape - teams, systems, the people everyone asks, the contested ground - into a first block plan: a four-phase build sequence with exit tests, the named roles that make it survive, the subtraction list, and what the plan refuses to settle without scoping.

Worth running when: Leadership agrees something structural is needed, and the next question is who does what, in what order.

You get: A structured plan of what, who and in what order - honest about what it cannot promise.

Claude Code - one line:

mkdir -p ~/.claude/skills/somai-brain-plan && curl -fsSL https://somai.studio/skills/brain-plan/SKILL.md -o ~/.claude/skills/somai-brain-plan/SKILL.md

Any other assistant: the file is the skill - read or download it.

Offered as examples

These skills are published as examples of the somai method, for learning and for finding out where you stand. They are not consultancy in a file: the readouts are produced by your own assistant from what you tell it, and they deserve the same scrutiny you would give any first draft. Treat what comes back as a starting point for your judgement, not a substitute for it - and when a decision carries real weight, put a person on it. Yours, or ours.

After the skills

The skills are structural: they show the shape of the gap and the shape of the fix, and they never invent a number. The measured version is the AI-Native Diagnostic (opens in a new tab) - 25 questions, 10 minutes, banded inputs only, ending in a one-page brief with the value modelled from public benchmarks. And the scoping conversation is hello@somai.studio.