Command
sw-eval
Run Specwright eval suite. Spawns subagents to run skills in fixture workdirs, then grades results.
@obsidian-owlView CommandDevelopment
Command
/sw-audit
Periodic codebase health check for systemic technical debt.
Install
$ npx -y skills add Obsidian-Owl/specwright --agent claude-codeHow it fires
How this command gets triggered: by you, by Claude, or both.
- Fires itselfClaude auto-loads it when your prompt matches the work.
- You can call itInvoke it directly when you want it.
- Slash command
/sw-audit
Context preview
What this command does when you run it.
Periodic codebase health check for systemic technical debt.
Command definition
sw-audit.mddescription: Periodic codebase health check for systemic technical debt.
Use the installed `specwright:sw-audit` skill for this request.
$ARGUMENTS
Ships withspecwright
Craft quality software with AI discipline. Spec-driven development plugin for Claude Code and Opencode — quality gates, adversarial testing, and evidence capture.
Get the whole plugin
Stats
9
Stars
0
Forks
Maintained
Maintenance
Python
Language
MIT
License
4mo ago
Last commit
7mo ago
Created
Repo: Obsidian-Owl/specwright
Other commands on specwright.
@obsidian-owlView CommandCommand
Command
sw-build
TDD implementation of one work unit. If branch-head freshness blocks and policy is rebase or merge, recover in-stage; manual is the fallback.
@obsidian-owlView CommandCommand
sw-debug
Investigation-first debugging. Scope, investigate, diagnose, then fix/log/defer.
@obsidian-owlView CommandCommand
sw-design
Interactive solution architecture with adversarial critique and assumption surfacing.
@obsidian-owlView CommandCommand