* docs(installation): add an AI-assistant setup prompt
Adds a provider-neutral "Install with your AI assistant" section to
docs/installation.md with one copyable prompt that detects the runtime and
package manager, installs the CLI, runs `openspec init --tools <id>`, and
verifies the result. Surfaced from the README Quick Start and the docs map.
The manual package-manager instructions stay the source of truth.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
* docs(installation): harden the AI-assistant prompt and link it from the install paths
Adversarial review found the first draft's verify step false-failing on healthy
installs and its guardrails unenforceable. The prompt now reports what init
actually printed instead of asserting config.yaml and command files (config.yml
is equally valid; six tools and delivery=skills correctly generate zero
commands), warns that --tools auto-cleans legacy files including opsx-*.md
prompts under $HOME, picks the package manager by what's on PATH rather than by
lockfile, scopes yarn to 1.x, and stops cleanly on EACCES, a missing pnpm global
bin dir, or a version-manager shim.
Also links the flow from getting-started, the docs map, troubleshooting, and the
website CTA; notes Berry dropped `yarn global`; replaces `npm bin -g` (removed in
npm 9) with `npm prefix -g`.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
* docs(installation): close the gaps two trial runs found in the setup prompt
Two assistants (different models) ran the prompt end to end in sandboxes, one
on Cursor and one on Codex with deliberately messy legacy files. Both finished
with a working, verified setup. Their findings:
- Cursor's commands are `/opsx-propose`, not `/opsx:propose`. The prompt named
the colon form and init's summary agrees with it, so the assistant would have
handed back a command the tool doesn't match. It now takes the spelling from
the files init created.
- "List whatever you find and wait for my go-ahead" was undefined when the list
is empty, i.e. on every fresh project. It now says to carry on.
- `openspec --version` succeeding doesn't prove it's the copy just installed;
an older one earlier on PATH shadows it. Step 3 now compares the two.
- The request asked for confirmation before privileged/global changes; the
prompt only stopped reactively on failure. It now shows the global install
command and waits.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
* docs: correct the core profile to six workflows and the tool count to 30+
Two long-standing inaccuracies, found while verifying the install docs.
`CORE_WORKFLOWS` (src/core/profiles.ts:14) is six — propose, explore, apply,
update, sync, archive — and a real `openspec init` generates six skills and six
commands. Eleven pages listed five, omitting `update`; migration-guide listed
four and filed `sync` under the expanded set. supported-tools also dropped
`update` from the full workflow-ID list. docs/commands.md was already right and
is untouched, as are flow diagrams that show a typical path rather than a
profile roster.
The tool count was written as both "25+" and "30+" against 34 supported tools.
Now consistently "30+".
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
* docs: address CodeRabbit review on the AI-assisted install flow
- Windows puts global npm binaries directly in the prefix directory, not in a
`bin/` subdirectory; the troubleshooting fix I added said otherwise.
- Tell the assistant to stop rather than improvise when none of npm/pnpm/yarn/bun
is available, and point Nix users at the Nix section.
- Drop the blockquote on the getting-started pointer so it isn't a second `>`
block adjacent to the explore callout (markdownlint MD028).
Two other comments were already fixed in 1bf0706 (stop on a PATH problem; map
the user's answer to an exact tool id).
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
7.3 KiB
OpenSpec Documentation
Welcome. This is the home for everything OpenSpec.
OpenSpec helps you and your AI coding assistant agree on what to build before any code is written. You describe the change, the AI drafts a short spec and a task list, you both look at the same plan, and then the work happens. No more discovering halfway through that the AI built the wrong thing.
If you read nothing else, read these two pages:
- Getting Started: install, initialize, and ship your first change.
- How Commands Work: where you actually type
/opsx:propose(hint: in your AI chat, not the terminal). This trips up almost everyone once.
That second one matters more than it looks. OpenSpec has two halves: a command line tool you run in your terminal, and slash commands you give to your AI assistant. Knowing which is which saves you the most common moment of confusion.
The best habit to build first: when you're not sure what to build, start with
/opsx:explore. It's a no-stakes thinking partner that reads your code, weighs options, and sharpens a fuzzy idea into a concrete plan before any artifact or code exists. The Explore First guide makes the case.
Pick your path
I'm brand new. Start with Getting Started, then skim the Core Concepts at a Glance. When something feels mysterious, the FAQ and Glossary are nearby.
I have a problem but not a plan. This is the common case, and it has a dedicated answer: Explore First. Use /opsx:explore to think it through with the AI before committing to anything.
I have a big existing codebase. You don't document all of it. Using OpenSpec in an Existing Project shows how to start on real, brownfield code without boiling the ocean.
I just want to get it working. Install, run openspec init, then read How Commands Work so your first slash command lands in the right place. Or hand the setup to your assistant with the AI-assisted install prompt.
I learn by example. The Examples & Recipes page walks through real changes start to finish: a small feature, a bug fix, a refactor, an exploration.
The AI just drafted a plan — now what? Read it. Reviewing a Change shows the two-minute pass that catches a wrong turn while it's still cheap, and Writing Good Specs covers what a plan worth approving is made of.
I work on a team. OpenSpec on a Team shows how a change maps onto a branch and a pull request, and how teammates review a plan before the code.
I'm coming from the old workflow. The Migration Guide explains what changed and why, and promises your existing work is safe.
I want to bend it to my team's process. Customization covers project config, custom schemas, and shared context.
Something's broken. Troubleshooting collects the failures people actually hit, with fixes.
The whole map
Start here
| Doc | What it gives you |
|---|---|
| Getting Started | Install, initialize, and run your first change end to end |
| Explore First | Use /opsx:explore to think through an idea before you commit |
| How Commands Work | Where slash commands run, what "interactive mode" means, terminal vs chat |
| Core Concepts at a Glance | The whole mental model on one page: specs, changes, deltas, archive |
| Installation | npm, pnpm, yarn, bun, Nix, a prompt that hands setup to your AI assistant, and how to verify it worked |
Use it day to day
| Doc | What it gives you |
|---|---|
| Workflows | Common patterns and when to reach for each command |
| Examples & Recipes | Full walkthroughs of real changes, copy-pasteable |
| Writing Good Specs | What a strong requirement and scenario look like, and how to right-size a change |
| Reviewing a Change | The two-minute pass on a drafted plan before any code is written |
| OpenSpec on a Team | How changes fit branches, pull requests, and review |
| Using OpenSpec in an Existing Project | Adopting OpenSpec on a large brownfield codebase |
| Editing & Iterating on a Change | Update artifacts, go back, reconcile manual edits |
| Commands | Reference for every /opsx:* slash command |
| CLI | Reference for every openspec terminal command |
Understand it deeply
| Doc | What it gives you |
|---|---|
| Concepts | The long-form explanation of specs, changes, artifacts, schemas, and archive |
| OPSX Workflow | Why the workflow is fluid instead of phase-locked, plus an architecture deep dive |
| Glossary | Every term defined in one place |
Make it yours
| Doc | What it gives you |
|---|---|
| Customization | Project config, custom schemas, shared context |
| Multi-Language | Generate artifacts in languages other than English |
| Supported Tools | The 30+ AI tools OpenSpec integrates with, and where files land |
When you need help
| Doc | What it gives you |
|---|---|
| FAQ | Quick answers to the questions people ask most |
| Troubleshooting | Concrete fixes for concrete failures |
| Migration Guide | Moving from the legacy workflow to OPSX |
Coordinate across repos (beta)
| Doc | What it gives you |
|---|---|
| Stores: User Guide | Plan in its own repo when your work spans repos or teams |
| Agent Contract | The machine-readable CLI surfaces agents drive |
The thirty-second version
1. Install npm install -g @fission-ai/openspec@latest
2. Initialize cd your-project && openspec init
3. Explore (in your AI chat) /opsx:explore ← optional, but a great habit
4. Propose (in your AI chat) /opsx:propose add-dark-mode
5. Build (in your AI chat) /opsx:apply
6. Archive (in your AI chat) /opsx:archive
Steps 1 and 2 happen in your terminal. The rest happen in your AI assistant's chat. That split is the one thing worth memorizing, and How Commands Work explains exactly why. Step 3 is optional, but starting with /opsx:explore when you're unsure is the habit most worth forming.
Where else to get help
- Discord: discord.gg/YctCnvvshC for questions, ideas, and help.
- GitHub Issues: github.com/Fission-AI/OpenSpec/issues for bugs and feature requests.
openspec feedback "your message"sends feedback straight from your terminal (it opens a GitHub issue).
Found something in these docs that's wrong, stale, or confusing? That's a bug. Open an issue or a PR. Documentation improvements are some of the most valuable contributions you can make.