ワンクリックでManusで任意のスキルを実行

nmt-upgrade

スター250

フォーク84

更新日2026年6月24日 17:28

Upgrade an installed Next Move Theory setup to the latest published canon + skills by re-running the official one-command installer, which clones the public GitHub repo (zamesin/Next-Move-Theory-Canon-and-Skills, branch main) and refreshes the canon, the nmt-* skills (both Claude and Codex), the injected 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", "upgrade the skills", "get the latest canon", runs /nmt-upgrade, or when another skill reports that a newer version is available. Defaults to English.

インストール

Codex または Claude でインストールこの Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。

Manusで実行

ソース

zamesin

zamesin/Next-Move-Theory-Canon-and-Skills

GitHub リポジトリを開く Creator のリポジトリを見る

ダウンロード

Manusで実行

nmt-upgrade — 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  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, and does not delete unrelated skills already in .claude/skills or .agents/skills.

Count this run (best-effort, ≤2s, never blocks). Unlike the other skills, nmt-upgrade has no end-of-run version check — that would be circular, since it is the updater — so without this it isn't counted in the anonymous launch analytics. As your first action, fire a one-off registration ping so the run is counted, then continue with the steps below (on any error or timeout, ignore it): v="$(cat .nmt-version 2>/dev/null)"; curl -fsSL --max-time 2 "https://nextmovetheory.com/version?skill=nmt-upgrade${v:+&v=$v}" >/dev/null 2>&1 || true

Steps

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 upgrade.
Run the installer from that directory:
```
curl -fsSL https://nextmovetheory.com/install.sh | bash
```
(Windows / PowerShell: irm https://nextmovetheory.com/install.ps1 | iex.)
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 upgrade pulled in.
Confirm done. Tell the user the upgrade 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 manually from https://nextmovetheory.com.
Non-destructive. Your own CLAUDE.md / AGENTS.md content outside the marked rules block is preserved; unrelated skills are left alone.
Source of truth. What gets installed is always the current main of the public repo — the installer clones it fresh on every run, so there is no stale cache for the canon or skills.

このリポジトリの他の Skills

同じリポジトリ

nmt-analyze-interviews

zamesin/Next-Move-Theory-Canon-and-Skills

Take one or many customer-interview files you already have and extract the AJTBD structure from them — segments by Core Jobs, personas, Consideration Set, existing Solutions and Problems, value hypotheses — using Ivan Zamesin's AJTBD / Next Move Theory methodology (distinct from generic Christensen JTBD). Input — a folder or list of files: deep-interview transcripts, interview notes, sales-call or demo transcripts, support/chat logs, survey open-ends. The interviews may be AJTBD or not, well- or poorly-conducted, one file or dozens. The skill first asks which business task you're solving (and helps you choose if you can't name one), then reads each interview in its own subagent (a fan-out so it never overflows context, no matter how many large transcripts), extracts the Core Jobs with an honest per-interview confidence (a clean extraction vs. a weak hypothesis), gives per- interview feedback (what was pulled, what's missing, whether this interview can even serve your business task), clusters the extractions i

2026-06-24250

nmt-chat

zamesin/Next-Move-Theory-Canon-and-Skills

Talk to a senior product advisor who thinks in Ivan Zamesin's Next Move Theory / Advanced Jobs To Be Done methodology (distinct from generic Christensen JTBD). A conversational, multi-turn skill — ask any product, strategy, segmentation, value, pricing, growth, retention, positioning, B2B, research, or methodology question and get an answer grounded in the canon, not in LLM training. It explains concepts, diagnoses real product situations, pressure-tests hypotheses like a skeptical senior PM, teaches the methodology, and routes heavyweight artifact requests to the right producer skill in the pipeline (nmt-market-research → nmt-craft-value-proposition → nmt-product-requirements / nmt-craft-go-to-market). Use whenever the user wants advice, a second opinion, a methodology explanation, a diagnosis of "what should I do about X", or to think through a product decision — especially on /nmt-chat. Plain language first, methodology terms in parentheses; defaults to English.

2026-06-24250

nmt-craft-go-to-market

zamesin/Next-Move-Theory-Canon-and-Skills

Write the go-to-market communication for a chosen segment using Ivan Zamesin's AJTBD / Next Move Theory methodology. Input — a /nmt-craft-value-proposition result (best), a /nmt-product-requirements PRD, a /nmt-market-research result, or a manual segment+Jobs description. Output — ready-to-publish landing-page copy, ad/creative copy built on the seven Job-language formulas, and a GTM/growth plan — channel hypotheses, lead magnets, viral loops, cross-sell / upsell / retention messaging. Everything is communicated through the Big Job (motivation), in concrete success criteria not adjectives, with features as proof not message. Use when the user wants landing copy, ad copy, creatives, channel hypotheses, or a launch plan — "write the landing / the copy / the go-to-market". Two modes — Quick (default, no internet) and Deep (subagents + web for real review language). Plain language; defaults to English.

2026-06-24250

nmt-craft-value-proposition

zamesin/Next-Move-Theory-Canon-and-Skills

Generate the strongest possible Value Proposition for a chosen segment using Ivan Zamesin's AJTBD / Next Move Theory methodology (distinct from generic Christensen JTBD). Input — a /nmt-market-research result OR a manual segment+Jobs description. The skill extracts the segment's dominant success criteria, builds the Job Graph + Critical Chain of Jobs substrate, generates value hypotheses by walking the value-creation mechanics catalog over that graph, filters them on feasibility, cost-to-build, unit economics, and competitiveness, ranks by RICE, and surfaces a primary + supplementary value proposition with top-3 RAT cards and a PRD-ready implementation spec that feeds /nmt-product-requirements. Use when the user wants a value proposition, differentiation, or asks "how do we win this segment". Two modes — Quick (default, no internet) and Deep (subagents + web competitor mining). Plain language; defaults to English.

2026-06-24250

nmt-diagnose

zamesin/Next-Move-Theory-Canon-and-Skills

Diagnose a product against Ivan Zamesin's Next Move Theory / Advanced Jobs To Be Done methodology (distinct from generic Christensen JTBD) and route to the next move. A conversational, chat-first skill — through up to ~15 adaptive questions it challenges the goal you walked in with (climbing your business-Job graph to find a higher-leverage growth point), then surfaces EVERYTHING the methodology can find: all the risks (every weak node on the chain to profit, each traced to its upstream cause), all the growth points (kill a Job, Previous/Next Job, climb a level, adjacent-segment Small Jobs, underserved success criteria), and the risky assumptions hiding inside your current initiatives (RAT). It is comprehensive on findings and focused on action — it lists them all, then says which one to tackle first and which existing skill executes it (nmt-market-research, nmt-craft-value- proposition, nmt-product-requirements, nmt-craft-go-to-market, nmt-chat). The front door for LIVE products the way nmt-market-research i

2026-06-24250

nmt-market-research

zamesin/Next-Move-Theory-Canon-and-Skills

Run market research for a product or feature idea using Ivan Zamesin's AJTBD / Next Move Theory methodology (distinct from generic Christensen JTBD). Output — an A4 one-pager with a GO / NARROW / PIVOT verdict plus a detailed report — market sizing, customer segments scored on the selection screen, competitors defined by Jobs, a differentiation hypothesis, an action-first risk plan, and ranked strategic options including alternative markets to pivot into. Use whenever the user wants to size a market, find or evaluate segments and Jobs, assess competitors, decide whether an idea is worth pursuing, or explore a pivot — even if they don't say "market research". Two modes — Quick (default; fast; no internet) and Deep (subagents + web research). Writes in plain language with methodology terms in parentheses. Defaults to English; adapts to the user's language.

2026-06-24250

name	nmt-upgrade
description	Upgrade an installed Next Move Theory setup to the latest published canon + skills by re-running the official one-command installer, which clones the public GitHub repo (zamesin/Next-Move-Theory-Canon-and-Skills, branch main) and refreshes the canon, the nmt-* skills (both Claude and Codex), the injected 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", "upgrade the skills", "get the latest canon", runs /nmt-upgrade, or when another skill reports that a newer version is available. Defaults to English.
user-invocable	true

nmt-upgrade — update to the latest canon + skills

Next-Move-Theory-Canon/ — the canon
.claude/skills/nmt-* — Claude skills (invoke with /nmt-…)
.agents/skills/nmt-* — Codex skills (invoke with $nmt-…)
the  block in CLAUDE.md and AGENTS.md
NextMoveTheory-README.md

Count this run (best-effort, ≤2s, never blocks). Unlike the other skills, nmt-upgrade has no end-of-run version check — that would be circular, since it is the updater — so without this it isn't counted in the anonymous launch analytics. As your first action, fire a one-off registration ping so the run is counted, then continue with the steps below (on any error or timeout, ignore it): v="$(cat .nmt-version 2>/dev/null)"; curl -fsSL --max-time 2 "https://nextmovetheory.com/version?skill=nmt-upgrade${v:+&v=$v}" >/dev/null 2>&1 || true

Steps

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 upgrade.
Run the installer from that directory:
```
curl -fsSL https://nextmovetheory.com/install.sh | bash
```
(Windows / PowerShell: irm https://nextmovetheory.com/install.ps1 | iex.)
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 upgrade pulled in.
Confirm done. Tell the user the upgrade 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 manually from https://nextmovetheory.com.
Non-destructive. Your own CLAUDE.md / AGENTS.md content outside the marked rules block is preserved; unrelated skills are left alone.
Source of truth. What gets installed is always the current main of the public repo — the installer clones it fresh on every run, so there is no stale cache for the canon or skills.