plugins/spectre/skills/ux_spec/SKILL.md
Define the User Flows and generate a UX Spec - primary agent
npx skillsauth add codename-inc/spectre ux_specInstall 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.
Transform product requirements into a definitive behavioral specification. Two stages: align on user flows, then generate detailed spec. Output: ux.md ready for implementation.
<ARGUMENTS> $ARGUMENTS </ARGUMENTS>
Goal: Align on HOW the feature works before specifying details.
docs/tasks/{branch}/task_summary.md and docs/tasks/{branch}/specs/prd.mdWrite each flow as a narrative walkthrough:
Per flow include: Goal, Entry point, Journey steps (User sees → User does → System responds), Decision points with branches, Success state, Questions where ambiguity exists
After writing all flows, prompt:
User Flows for Review
I've mapped {N} flows: {list with one-line summaries}
Please review: Are these the right flows? Any missing? Do journeys feel right? Answer flagged questions.
Reply with feedback, or "Flows approved" to proceed.
Wait for approval. If feedback → revise and re-present. If approved → Stage 2.
Gate: Only proceed after explicit flow approval.
Review approved flows for gaps: component behaviors, edge cases, state definitions.
If significant gaps, ask 3-5 targeted questions (empty states, error handling, loading, limits). Save to clarifications/ux_clarifications_{timestamp}.md, prompt user to read, incorporate answers.
Generate complete spec with these sections:
Save to docs/tasks/{branch}/ux.md
Prompt:
UX Specification Complete
Written to
{path}. Please review: Any behaviors wrong or missing? Edge cases not covered?Reply with feedback, or "Approved" to finalize.
Wait for approval.
Confirm completion with summary: screens specified, flows documented, components with states, edge cases and accessibility covered.
Read .spectre/next_steps_guide.md and render Next Steps footer:
Next Steps | Phase: Scope | Status: UX Complete
Recommendation: {contextual next action}
Options: /create_plan, /create_tasks, /tdd
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