plugins/spectre-codex/skills/spectre-evaluate/SKILL.md
👻 | Architecture review + knowledge capture
npx skillsauth add codename-inc/spectre spectre-evaluateInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Treat the current command arguments as this workflow's input. When invoked from a slash command, use the forwarded $ARGUMENTS value.
This command runs two activities in parallel:
Skill(spectre-architecture_review) (Claude slash route: spectre-architecture_review)spectre-learn skillAction — DispatchReview: Launch architecture review as a background subagent
subagent_type="general-purpose", model="opus", run_in_background=trueOutput: Inform the user that the architecture review is running in the background and they'll be notified when it completes.
Skill(spectre-learn)When the learn flow completes:
testing
👻 | Independent multi-lens review of plan.md and/or tasks.md — finds overengineering, missing verification, hallucinated deps, weak references
data-ai
👻 | Unified planning entry point - researches, assesses complexity, routes to workflow - primary agent
data-ai
👻 | Transform requirements into executable tasks - primary agent
testing
👻 | Independent multi-lens review of plan.md and/or tasks.md — finds overengineering, missing verification, hallucinated deps, weak references