Skip to content

feat: add anti-patterns, design philosophies, advisor mode, asset protocol#295

Open
najamali wants to merge 1 commit into
nextlevelbuilder:mainfrom
najamali:feat/anti-patterns-and-advisor-mode
Open

feat: add anti-patterns, design philosophies, advisor mode, asset protocol#295
najamali wants to merge 1 commit into
nextlevelbuilder:mainfrom
najamali:feat/anti-patterns-and-advisor-mode

Conversation

@najamali

@najamali najamali commented May 3, 2026

Copy link
Copy Markdown

Summary

Adds two new search domains and four process docs ported from impeccable (pbakaus), Anthropic frontend-design, and jiji262/claude-design-skill. Closes the gap where ui-ux-pro-max had a strong data layer but no anti-pattern detection, no advisor mode for vague briefs, and no asset protocol for branded work.

New search domains

  • antipattern — 30 deterministic rules for generic AI aesthetics (purple gradients, default shadcn, Inter everywhere, stock photos, nested cards). Columns: Why It's Bad, How to Detect, Better Alternative, Severity, Mode (brand/product/both).
  • philosophy — 10 design directions × 5 schools (Swiss, Brutalist, Editorial, Kenya Hara, Bold Maximalism, Refined Minimalism, Aurora/Glass, Y2K/Retro-Futuristic, Organic, Anti-Design). Each has flagship examples, signature moves, risk level, and an AI prompt seed.

New process docs

  • data/asset-protocol.md — 5-step Core Asset Protocol for branded work (fact-check → logo → product shots → reference → tokens → brand-spec.md)
  • data/advisor-mode.md — 3-direction protocol for when the brief is vague
  • templates/base/DESIGN.md — per-project design memory (mode, locked direction, tokens, hard rules)
  • templates/base/PRODUCT.md — per-project product memory (audience, voice rules, decision log)

Code changes

  • src/ui-ux-pro-max/scripts/core.py — adds antipattern and philosophy to CSV_CONFIG and detect_domain keyword sets
  • src/ui-ux-pro-max/templates/base/skill-content.md — adds Advisor Mode, Anti-Pattern Check, Asset Protocol, and project-memory sections
  • CLAUDE.md — documents new domains and process files
  • cli/assets/ — synced per CLAUDE.md sync rules

Test plan

  • python3 src/ui-ux-pro-max/scripts/search.py "purple gradient" --domain antipattern → returns Color anti-pattern row
  • python3 src/ui-ux-pro-max/scripts/search.py "swiss editorial" --domain philosophy → returns Swiss Editorial row
  • python3 src/ui-ux-pro-max/scripts/search.py "default shadcn" -n 3 → auto-detects antipattern domain
  • python3 src/ui-ux-pro-max/scripts/search.py "minimalism" -n 1 → existing style domain unchanged (no regression)
  • CLI assets diff matches src/ data + scripts + templates

Inspiration / credit

…et protocol

Adds two new search domains and four process docs ported from impeccable
(pbakaus), Anthropic frontend-design, and jiji262/claude-design-skill.

New data:
- data/anti-patterns.csv: 30 deterministic anti-pattern rules covering
  generic AI aesthetics (purple gradients, default shadcn, Inter
  everywhere, stock photos, nested cards) with severity, mode, and
  better-alternative columns
- data/design-philosophies.csv: 10 philosophies x 5 schools (Swiss,
  Brutalist, Editorial, Hara, Maximalism, Aurora, Y2K, Organic, Anti-
  Design) with flagship examples, signature moves, and AI prompt seeds
- data/asset-protocol.md: 5-step Core Asset Protocol for branded work
- data/advisor-mode.md: 3-direction protocol for vague briefs

New templates:
- templates/base/DESIGN.md: per-project design memory (mode, locked
  direction, tokens, hard rules, anti-pattern checklist)
- templates/base/PRODUCT.md: per-project product memory (audience, voice
  rules, constraints, decision log)

Search engine:
- core.py: add 'antipattern' and 'philosophy' domains to CSV_CONFIG and
  detect_domain keyword sets

Docs:
- CLAUDE.md: document new domains and process files
- skill-content.md: add Advisor Mode, Anti-Pattern Check, Asset Protocol,
  and project-memory sections to the skill workflow

CLI assets synced per CLAUDE.md sync rules.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
@mrgoonie

Copy link
Copy Markdown
Contributor

Summary: I’m deferring this PR in the cron-safe maintainer lane because it is over the bounded review budget and currently not mergeable.nnDecision: deferred / needs focused maintainer reviewnnEvidence:n- Scope is 17 changed files with +1,002/-4 lines, which exceeds the cron lane threshold for a safe deep review.n- It adds new data domains, process docs, base templates, script routing, and mirrored CLI assets in one PR, so the source-of-truth and generated-asset sync need to be reviewed together.n- GitHub currently reports mergeStateStatus=DIRTY, so it cannot be merged as-is.nnNext step: please rebase/resolve conflicts and, if possible, split this into narrower lanes: (1) anti-pattern + philosophy data/search support, and (2) advisor/asset protocol + project-memory template docs. Include the exact validation commands and output after syncing cli/assets from src/.

@mrgoonie mrgoonie added agent:github-maintain Processed by github-maintain automation maintain:deferred Deferred by maintain workflow pr:oversized Too large for cron-safe review budget labels Jun 23, 2026
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

agent:github-maintain Processed by github-maintain automation maintain:deferred Deferred by maintain workflow pr:oversized Too large for cron-safe review budget

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants