skills/team/qrspi-spec/SKILL.md
QRSPI Spec phase -- a Design Brain-Dump the human redirects ("brain surgery"), followed by a vertically-sliced Structure Outline. Use for "/qrspi-spec <feature>", "design discussion for X", "structure outline for X", "spec out X from the research". Do NOT use for an open-ended design chat (use spec-coach); this phase consumes research.md and produces an approved spec.md.
npx skillsauth add michaelalber/ai-toolkit qrspi-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.
"Plans are worthless, but planning is everything." -- Adapted from Dwight D. Eisenhower
The Spec phase turns objective research into an agreed design BEFORE any plan or code exists. It
runs two movements: a Design Brain-Dump the human performs "brain surgery" on, then a
Structure Outline of signatures and vertical slices. The hard human gate between them is the
point -- catching a wrong approach here costs minutes; catching it in code costs hours. Spec maps
the source workflow's stages 3 (Design Discussion) and 4 (Structure Outline); see
references/stage-mapping.md.
Non-Negotiable Constraints:
research.md on disk; never design from memorydesign_approved: true)spec.md with progress and tell the
user to start a fresh session.PRE-FLIGHT
[ ] Locate the feature folder thoughts/shared/qrspi/YYYY-MM-DD-{slug}/
[ ] Read research.md (status: complete). If absent -> STOP; route the user to /qrspi-research
[ ] Read the answered questions.md for design intent
BRAIN-DUMP (source stage 3 -- Design Discussion)
Write ~200 lines: current state (from research) · desired end state · design decisions & tradeoffs
Write spec.md with the Brain-Dump only, status: draft, design_approved: false
STOP & LOOP (the "brain surgery" gate)
Present the Brain-Dump. WAIT. The human redirects architecture -> revise the Brain-Dump ->
re-present. Repeat until the human approves. Do NOT write the Structure Outline before approval.
STRUCTURE OUTLINE (source stage 4 -- only after design_approved: true)
Add: new/changed type signatures, public function signatures, and high-level phases sliced
VERTICALLY (mock-API -> front-end -> database), each with a verification checkpoint. No bodies.
Set status: ready-for-review
REPORT
Artifact path · slice list · "Review, then start a NEW session and run /qrspi-plan"
Exit criteria: spec.md holds an approved Brain-Dump plus a vertically-sliced Structure
Outline; status: ready-for-review; design_approved: true; user told to review before /qrspi-plan.
<qrspi-spec-state>
phase: PRE-FLIGHT | BRAIN-DUMP | STOP-LOOP | STRUCTURE-OUTLINE | REPORT | COMPLETE
feature_folder: thoughts/shared/qrspi/YYYY-MM-DD-{slug}/
research_present: true | false # MUST be true to proceed
design_approved: true | false # MUST be true before the Structure Outline
brain_dump_revisions: [count]
slices_outlined: [count]
context_budget: under-40 | approaching-60 | checkpoint-now
status: draft | ready-for-review | approved
</qrspi-spec-state>
See references/spec-template.md for the full spec.md structure and frontmatter, and
references/stage-mapping.md for the 8-stage source -> 5-phase QRSPI mapping.
| Skill | Relationship |
|-------|-------------|
| qrspi-research | Prior phase. Its objective research.md is the factual ground for the Brain-Dump. |
| qrspi-plan | Next phase. Consumes the approved spec.md; refuses to plan without it. |
| dotnet-vertical-slice / python-feature-slice / rust-feature-slice | Stack scaffolders for the vertical slices the Structure Outline defines. |
| spec-coach | Use instead for an open-ended interactive design chat; qrspi-spec is a gated brain-dump -> outline. |
development
Interviews the user relentlessly about a plan, decision, or idea — one question at a time, each with a recommended answer. Shared engine behind "grill-me" and "grill-with-docs". Use on any "grill" trigger phrase or to stress-test thinking. Do NOT use to build the plan; it ends at shared understanding, not implementation.
testing
Runs a relentless interview to sharpen a plan or design, capturing the decisions as ADRs and a glossary along the way. Use when the user wants to be grilled AND wants the session to leave durable domain documentation behind. Do NOT use for a throwaway stress-test with no artifacts; use grill-me instead.
tools
OWASP-based security review of Vue/TypeScript front-ends. Detects framework (Vite/Vue CLI/Nuxt), entry points, and data flows; scans the OWASP Top 10 (2025) mapped to Vue client-side risks (raw-HTML XSS via v-html, URL/protocol injection, bundled secrets, insecure token storage, dependency CVEs, missing CSP, open redirects, router guard bypass); emits an exec summary plus graded findings. Use to audit Vue for vulnerabilities. Not for architecture grading (vue-architecture-checklist).
tools
Analyzes legacy Vue codebases and produces actionable modernization plans. Primary migration paths include Options API to Composition API, Vue 2 to Vue 3, Vue CLI to Vite, JavaScript to TypeScript, Vue Test Utils/Karma/Mocha to Vitest + Vue Testing Library, legacy Vuex to Pinia, and removed-in-Vue-3 pattern cleanup (filters, event bus, `$listeners`). Does NOT perform the migration — assesses, quantifies risk, and plans.