Installs into a Spec Kit project · works with Claude, kiro-cli & more · public catalog, no token needed
Before you start
Spectra builds on Spec Kit and installs into a Spec Kit project — a folder containing .specify/.
Run everything below from inside that project. Don’t have one yet? The installer offers to run specify init for you.
After Spectra installs, restart your agent so it picks up the new commands.
Installation
Two ways to set up Spectra: the installer does everything for you, or
manual setup is a copy-paste path. The catalog is public — no GitHub
login or token needed.
Spectra Installer
The recommended path. Download the single installer script and run it from inside your
Spec Kit project — it installs Spec Kit if needed, offers to initialize the project, registers the
Spectra catalog, and installs the extension.
Always fetches the latest release — or browse the
releases page.
python3 spectra-setup.py
Run it inside a Spec Kit project (a folder containing .specify/).
Not in one yet? The installer offers to run specify init first. When it finishes, Spectra is
installed — restart your agent, then see Agents below. You can delete the
installer script afterward.
Manual setup
Prefer copy-paste? Register the public catalog once per project (this marks it
install-allowed, so installs resolve by name with no “untrusted source” prompt), then install the
extension and restart your agent.
Spectra ships as a single extension under the unified
speckit.spectra.* namespace — install once and get every command. Examples use
Claude’s trigger form — a leading slash with dashes, like /speckit-spectra-adr.
Other agents differ (kiro-cli uses /speckit.spectra.adr); your agent’s own command/skill
list shows the exact trigger.
Spectra
spectrav1.2.0
Spectra’s agentic SDLC commands for Spec Kit, bundled as a single extension: structured BRD authoring, context-aware Architecture Decision Records, business-domain guardrail analysis, and correctly-targeted GitHub PR delivery.
speckit.spectra.adrCreate a context-aware Architecture Decision Record grounded in your codebase, prior ADRs, and constitution — it asks a few clarifying questions, then writes the ADR under Docs/ADR/. Use it when making a significant architecture or technology choice.Arguments: a short description of the decision. If omitted, you’ll be asked for one before drafting.Example (Claude)
/speckit-spectra-adr We should standardize on PostgreSQL for all primary data stores
speckit.spectra.domain-analyzerScan the existing codebase, docs, and ADRs to infer the project's domain, then write an opt-in proposal of candidate guardrails for SME review and handoff to the constitution. It never edits the constitution or source — you choose what to adopt.Arguments: none required — runs on the whole project (ideal for brownfield). Optionally pass a domain hint to steer it.Example (Claude)
/speckit-spectra-domain-analyzer
/speckit-spectra-domain-analyzer this is a banking system
speckit.spectra.create-prOpen a correctly-targeted GitHub PR for the current spec branch, deriving the base from your promotion strategy and returning the PR URL. Confirms before any push, and is also offered automatically after implement.Arguments: none opens a ready-for-review PR (default); --draft opens a draft; --base <branch> overrides the derived base branch (confirmed first).Example (Claude)
speckit.spectra.brdTurn a raw business requirement — typed text or a .docx/.pdf/.md/.txt document — into a structured, specify-ready BRD written under /brds. Reads project context, asks a few clarifying questions only when the requirement has gaps, and never invents requirements — then hand the result to the specify command.Arguments: the requirement as text, or a path to a requirement document. With no input it asks for one.Example (Claude)
/speckit-spectra-brd Support agents need to merge duplicate customer tickets while preserving history