chore: bump version and changelog (v0.5.0)

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
Garry Tan 2026-03-16 10:59:19 -05:00
parent 1fdfeb6e6e
commit 1ab1c66fe5
No known key found for this signature in database
GPG Key ID: C1F69E85C74EFE1D
4 changed files with 38 additions and 1 deletions

View File

@ -1,5 +1,20 @@
# Changelog # Changelog
## 0.5.0 — 2026-03-16
- **Your site just got a design review.** `/plan-design-review` opens your site and reviews it like a senior product designer — typography, spacing, hierarchy, color, responsive, interactions, and AI slop detection. Get letter grades (A-F) per category, a dual headline "Design Score" + "AI Slop Score", and a structured first impression that doesn't pull punches.
- **It can fix what it finds, too.** `/qa-design-review` runs the same designer's eye audit, then iteratively fixes design issues in your source code with atomic `style(design):` commits and before/after screenshots. CSS-safe by default, with a stricter self-regulation heuristic tuned for styling changes.
- **Know your actual design system.** Both skills extract your live site's fonts, colors, heading scale, and spacing patterns via JS — then offer to save the inferred system as a `DESIGN.md` baseline. Finally know how many fonts you're actually using.
- **AI Slop detection is a headline metric.** Every report opens with two scores: Design Score and AI Slop Score. The AI slop checklist catches the 10 most recognizable AI-generated patterns — the 3-column feature grid, purple gradients, decorative blobs, emoji bullets, generic hero copy.
- **Design regression tracking.** Reports write a `design-baseline.json`. Next run auto-compares: per-category grade deltas, new findings, resolved findings. Watch your design score improve over time.
- **80-item design audit checklist** across 10 categories: visual hierarchy, typography, color/contrast, spacing/layout, interaction states, responsive, motion, content/microcopy, AI slop, and performance-as-design. Distilled from Vercel's 100+ rules, Anthropic's frontend design skill, and 6 other design frameworks.
### For contributors
- Added `{{DESIGN_METHODOLOGY}}` resolver to `gen-skill-docs.ts` — shared design audit methodology injected into both `/plan-design-review` and `/qa-design-review` templates, following the `{{QA_METHODOLOGY}}` pattern.
- Added `~/.gstack-dev/plans/` as a local plans directory for long-range vision docs (not checked in). CLAUDE.md and TODOS.md updated.
- Added `/setup-design-md` to TODOS.md (P2) for interactive DESIGN.md creation from scratch.
## 0.4.1 — 2026-03-16 ## 0.4.1 — 2026-03-16
- **gstack now notices when it screws up.** Turn on contributor mode (`gstack-config set gstack_contributor true`) and gstack automatically writes up what went wrong — what you were doing, what broke, repro steps. Next time something annoys you, the bug report is already written. Fork gstack and fix it yourself. - **gstack now notices when it screws up.** Turn on contributor mode (`gstack-config set gstack_contributor true`) and gstack automatically writes up what went wrong — what you were doing, what broke, repro steps. Next time something annoys you, the bug report is already written. Fork gstack and fix it yourself.

View File

@ -43,6 +43,8 @@ gstack/
│ ├── skill-llm-eval.test.ts # Tier 3: LLM-as-judge (~$0.15/run) │ ├── skill-llm-eval.test.ts # Tier 3: LLM-as-judge (~$0.15/run)
│ └── skill-e2e.test.ts # Tier 2: E2E via claude -p (~$3.85/run) │ └── skill-e2e.test.ts # Tier 2: E2E via claude -p (~$3.85/run)
├── qa-only/ # /qa-only skill (report-only QA, no fixes) ├── qa-only/ # /qa-only skill (report-only QA, no fixes)
├── plan-design-review/ # /plan-design-review skill (report-only design audit)
├── qa-design-review/ # /qa-design-review skill (design audit + fix loop)
├── ship/ # Ship workflow skill ├── ship/ # Ship workflow skill
├── review/ # PR review skill ├── review/ # PR review skill
├── plan-ceo-review/ # /plan-ceo-review skill ├── plan-ceo-review/ # /plan-ceo-review skill
@ -101,6 +103,12 @@ CHANGELOG.md is **for users**, not contributors. Write it like product release n
- No jargon: say "every question now tells you which project and branch you're in" not - No jargon: say "every question now tells you which project and branch you're in" not
"AskUserQuestion format standardized across skill templates via preamble resolver." "AskUserQuestion format standardized across skill templates via preamble resolver."
## Local plans
Contributors can store long-range vision docs and design documents in `~/.gstack-dev/plans/`.
These are local-only (not checked in). When reviewing TODOS.md, check `plans/` for candidates
that may be ready to promote to TODOs or implement.
## Deploying to the active skill ## Deploying to the active skill
The active skill lives at `~/.claude/skills/gstack/`. After making changes: The active skill lives at `~/.claude/skills/gstack/`. After making changes:

View File

@ -374,6 +374,20 @@
**Priority:** P3 **Priority:** P3
**Depends on:** Ref staleness Parts 1+2 (shipped) **Depends on:** Ref staleness Parts 1+2 (shipped)
## Design Review
### /setup-design-md interactive skill
**What:** Interactive skill that walks user through creating a DESIGN.md from scratch (aesthetic direction, fonts, colors, spacing, motion).
**Why:** /plan-design-review can infer and export a DESIGN.md from a live site. /setup-design-md is the from-scratch version for new projects — full guided setup with font research, color palette selection, and preview pages.
**Context:** The full flow is spec'd in ~/.gstack-dev/plans/design-ux-master-skill.md (sections 0, 4-8). Covers: project context → aesthetic direction → decoration level → layout approach → color approach → font selection (with research + bun preview page) → spacing/density → motion → write DESIGN.md → update CLAUDE.md.
**Effort:** L
**Priority:** P2
**Depends on:** /plan-design-review (proves the DESIGN.md format)
## Completed ## Completed
### Phase 1: Foundations (v0.2.0) ### Phase 1: Foundations (v0.2.0)

View File

@ -1 +1 @@
0.4.1 0.5.0