Nmt Update logo

Nmt Update

Community
zamesin
nmt-update

Update an installed Next Move Theory setup to the latest published canon + skills by re-running the official one-command installer straight from the public GitHub repo (zamesin/Next-Move-Theory-Canon-and-Skills, branch main). It refreshes the canon, the nmt-* skills (both Claude and Codex), the marked rules block in CLAUDE.md / AGENTS.md, and the README — all in place. Idempotent and safe: it never touches your own files and never deletes unrelated skills. Use when the user says "update NMT", "update the skills", "get the latest canon", runs /nmt-update, or when another skill reports that a newer version is available. Defaults to English.

Overview

Publisherzamesin
RepositoryNext-Move-Theory-Canon-and-Skills
Skill namenmt-update
Stars
441
Forks
127
Bundled files
Instructions only
Links
  • 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.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by zamesin on GitHub. Read the source before you install it.

Installation

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

1

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.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/zamesin/Next-Move-Theory-Canon-and-Skills/tree/main/Skills/claude/nmt-update
  4. 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.
2

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/zamesin/Next-Move-Theory-Canon-and-Skills.git /tmp/Next-Move-Theory-Canon-and-Skills
mkdir -p .claude/skills
cp -r /tmp/Next-Move-Theory-Canon-and-Skills/Skills/claude/nmt-update .claude/skills/nmt-update
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Nmt Update 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 Nmt Update 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 Nmt Update 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.

nmt-update — update to the latest canon + skills

Re-runs the official Next Move Theory installer from the project root. The installer clones the public repo (zamesin/Next-Move-Theory-Canon-and-Skills, branch main) and refreshes, in place:

  • Next-Move-Theory-Canon/ — the canon
  • .claude/skills/nmt-* — Claude skills (invoke with /nmt-…)
  • .agents/skills/nmt-* — Codex skills (invoke with $nmt-…)
  • the <!-- Next-Move-Theory-Rules:start … end --> block in CLAUDE.md and AGENTS.md
  • NextMoveTheory-README.md

It is idempotent and safe — it replaces the canon, skills, marked rules block, and README in place, leaves your own files untouched (including anything outside the markers), and does not delete unrelated skills already in .claude/skills or .agents/skills. Everything it installs is downloaded from the public GitHub repo.

Count this run — optional; policy in NextMoveTheory-README.md, section "Updates & telemetry". Skip this entirely if .nmt-config (project root) contains a line update-check: off, or the environment variable DO_NOT_TRACK or NMT_NO_UPDATE_CHECK is set. Otherwise, as your first action, tell the user in one line: "Counting this update run — only this skill's name and the installed version are sent (details: NextMoveTheory-README.md; disable: add update-check: off to .nmt-config)." Then run v="$(grep -m1 -E '^[0-9]' .nmt-version 2>/dev/null)"; curl -fsSL --max-time 2 "https://nextmovetheory.com/version?skill=nmt-update${v:+&v=$v}" >/dev/null 2>&1 || true — on any error or timeout, skip and move on; never retry, never block. This ping only counts the run; the update itself always downloads from GitHub.

Steps

  1. Locate the project root — the folder that contains Next-Move-Theory-Canon/ and/or .claude/skills/. That is where the canon + skills must be refreshed. If the current directory is not it, ask the user which directory to update.
  2. Read the installed and the latest version. The installed version sits in .nmt-version; the latest is the top entry of the changelog in the public GitHub repo:
    bash
    installed="$(grep -m1 -E '^[0-9]' .nmt-version 2>/dev/null)"
    latest="$(curl -fsSL --max-time 3 https://raw.githubusercontent.com/zamesin/Next-Move-Theory-Canon-and-Skills/main/CHANGELOG.md 2>/dev/null \
      | grep -m1 -E '^##[[:space:]]+[0-9]' | sed -E 's/^##[[:space:]]+([^[:space:]]+).*/\1/')"
    echo "installed=${installed:-unknown} latest=${latest:-unknown}"
    Report the <installed> → <latest> gap in one line. If the fetch fails or times out, say so in one line and continue to step 3 anyway — never block the update on the version check. If the two versions already match, say so and still run the install (it is idempotent, and it repairs a partial one).
  3. Run the installer from that directory:
    bash
    curl -fsSL https://raw.githubusercontent.com/zamesin/Next-Move-Theory-Canon-and-Skills/main/install.sh | bash
    (Windows / PowerShell: irm https://raw.githubusercontent.com/zamesin/Next-Move-Theory-Canon-and-Skills/main/install.ps1 | iex.)
  4. Report what changed. Show the installer's final summary. If the project is a git repo, run git status --short and list which canon files / skill folders were added or modified so the user sees exactly what the update pulled in. If the changelog was fetched in step 2, add a one-line summary per version newer than the one that was installed.
  5. Confirm done. Tell the user the update is complete and that any new/updated skills are available immediately (e.g. /nmt-diagnose, /nmt-chat). No restart is needed.

Notes

  • Best-effort. The installer needs curl and git. If either is missing, tell the user to install it, or to install by hand from https://github.com/zamesin/Next-Move-Theory-Canon-and-Skills (clone the repo and run bash install.sh --target <your-project-root>).
  • Non-destructive. Your own CLAUDE.md / AGENTS.md content outside the <!-- Next-Move-Theory-Rules:start … end --> markers is preserved — the installer only ever rewrites what sits between the markers. Unrelated skills are left alone.
  • Renamed skill. This skill used to be called nmt-upgrade. The installer removes the old nmt-upgrade folder from .claude/skills and .agents/skills and installs nmt-update in its place, so you won't end up with both.
  • Source of truth. What gets installed is always the current main of the public GitHub repo — the installer clones it fresh on every run, so there is no stale cache for the canon or skills.

Frequently asked questions

What does the Nmt Update AI skill do?

Update an installed Next Move Theory setup to the latest published canon + skills by re-running the official one-command installer straight from the public GitHub repo (zamesin/Next-Move-Theory-Canon-and-Skills, branch main). It refreshes the canon, the nmt-* skills (both Claude and Codex), the marked rules block in CLAUDE.md / AGENTS.md, and the README — all in place. Idempotent and safe: it never touches your own files and never deletes unrelated skills. Use when the user says "update NMT", "update the skills", "get the latest canon", runs /nmt-update, or when another skill reports that a...

Why use Nmt Update on TypingMind?

Because you install it once and use it with any model. Nmt Update 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 Nmt Update in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/zamesin/Next-Move-Theory-Canon-and-Skills/tree/main/Skills/claude/nmt-update. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Nmt Update?

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 Nmt Update?

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

Is the Nmt Update AI skill free?

It is published on GitHub by zamesin. Check the repository for licensing terms. 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

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇