specmint-core-htmllisted

Persistent spec management for AI coding workflows, producing canonical SPEC.html files. Use this companion when the user explicitly mentions specs, forging, structured planning, resume/status/pause/switch, implementing a spec, or generating OpenAPI docs. Do NOT trigger on ordinary coding tasks that do not ask for spec management.
ngvoicu/kluris · ★ 4 · AI & Automation · score 77

Install: claude install-skill ngvoicu/kluris

# Spec Mint Core HTML — Kluris Companion Turn ephemeral plans into structured, persistent specs built through deep research and iterative interviews. This HTML variant uses `.specs/<id>/SPEC.html` as the canonical spec document, not a markdown spec plus a separate view. The HTML file carries metadata, lifecycle state, diagrams, code previews, mockups, decision logs, and deviations in one human-openable artifact. When this file is referenced from a Kluris-generated brain skill, read and follow it directly from `~/.kluris/companions/specmint-core-html/SKILL.md`. Do not ask the user to install Specmint separately. Kluris vendors companions as single `SKILL.md` files, so every rule needed for companion mode is below. ## Critical Invariants 1. **Canonical files** - Registry: `.specs/registry.md` (markdown index) - Per-spec document: `.specs/<id>/SPEC.html` - Research notes: `.specs/<id>/research-*.md` - Interview notes: `.specs/<id>/interview-*.md` - Scratch, if needed: `.specs/<id>/artifacts/` 2. **Authority rule**: the JSON inside `<script type="application/json" id="spec-meta">` is authoritative for identity and spec status. `data-status` attributes on phases, tasks, and acceptance criteria are authoritative for progress. 3. **Active-spec rule**: target exactly one active spec at a time. 4. **HTML is the source of truth**: do not create or update a parallel markdown spec for an HTML companion spec. 5. **Progress tracking is sacred**: after completing