Florian BRUNIAUX
8c93c31b90
feat(guide): add Product Designer learning path and design-to-code workflow
...
Add comprehensive resources for Product Designers working with Claude Code via Figma MCP:
- New workflow: guide/workflows/design-to-code.md (700 lines)
- Documented metrics: 62% reduction in design inconsistencies, 78% workflow efficiency improvement
- 4 core workflows: Frame→Component, Design System Audit, Token Automation, Visual Iteration
- 3-tier token hierarchy (base/composite/semantic)
- Team adoption patterns for designers, developers, PMs
- Implementation roadmap (Foundation → Scaling → Orchestration)
- Sources: builder.io, parallelhq.com, composio.dev, vladimirsiedykh.com
- New template: examples/claude-md/product-designer.md (400 lines)
- Complete CLAUDE.md configuration for design-to-code projects
- Figma MCP commands reference
- Design handoff checklist
- Token conventions and implementation constraints
- Updated README.md: Added "Product Designer" learning path (5 steps)
- Positioned after DevOps/SRE, before main content
- Links to image analysis, wireframing, Figma MCP, new workflow, cheatsheet
- Updated machine-readable/reference.yaml: Added 4 new entries
- product_designer_workflow, product_designer_claudemd
- design_system_handoff, figma_make_integration
Templates count: 72 → 73 (examples/claude-md/product-designer.md)
Guide workflows: 6 → 7 (guide/workflows/design-to-code.md)
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
2026-01-22 09:15:16 +01:00
Florian BRUNIAUX
fd17414abb
docs: add AI productivity research, trust calibration, and exploration workflow
...
## New Content
### Trust & Verification (ultimate-guide.md)
- Section 1.7 "Trust Calibration: When and How Much to Verify" (~155 lines)
- Research-backed stats (ACM, Veracode, CodeRabbit, Cortex.io)
- Verification spectrum by code type
- Solo vs Team strategies with workflow diagrams
- "Prove It Works" checklist
- New pitfall: "Trust AI output without proportional verification"
- CLAUDE.md size guideline: 4-8KB optimal, >16K degrades coherence
### AI Productivity (learning-with-ai.md)
- Section "The Reality of AI Productivity" (~55 lines)
- Productivity curve phases (Wow Effect → Targeted Gains → Plateau)
- High-gain vs low/negative-gain task categorization
- Team success factors
- Productivity trajectory table by pattern (Dependent/Avoidant/Augmented)
- 5 new sources (GitHub, McKinsey, Stack Overflow, Uplevel, DORA)
### Session Limits (architecture.md)
- "Session Degradation Limits" section
- Turn limits (15-25), token thresholds (80-100K)
- Success rates by scope (1-3 files: ~85%, 8+ files: ~40%)
### Exploration Workflow
- NEW: guide/workflows/exploration-workflow.md
- Anti-anchoring prompts, 3-5 approaches pattern
- iterative-refinement.md: Script Generation Workflow (3-7 iteration pattern)
- anchor-catalog.md: Anti-Anchoring Techniques, Exploration/Iteration Prompts
### Reference Updates
- adoption-approaches.md: Empirical data section
- reference.yaml: New deep_dive entries, updated line numbers
Sources: MetalBear engineering blog, arXiv studies, Addy Osmani (Jan 2026)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-01-19 19:16:33 +01:00
Florian BRUNIAUX
174192f583
feat(seo): add CITATION.cff and improve AI discoverability
...
- Add CITATION.cff for academic citations and GitHub citation button
- Add "For AI Assistants" section in README with llms.txt reference
- Update machine-readable/llms.txt stats (4700+ → 9600+ lines)
- Bump version display to 3.8.0 in README footer
Improves discoverability in GitHub search, Google Scholar, and AI assistants
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-01-17 11:21:58 +01:00
