Florian BRUNIAUX
09eb141976
docs: v3.9.6 - Trust Calibration, Vibe Coding Trap, reference.yaml sync
...
Added:
- ultimate-guide.md: Trust Calibration section (1.7) with research-backed verification strategies
- ultimate-guide.md: Infrastructure as Code Skills (Anton Babenko's terraform-skill)
- learning-with-ai.md: "The Vibe Coding Trap" anti-pattern (Karpathy, Feb 2025)
- learning-with-ai.md: "Reality of AI Productivity" section with research
- learning-with-ai.md: External resource link to leerob.com/ai (AI fundamentals)
- IDEAS.md: "Vibe Coding Discourse" watching entry
Changed:
- reference.yaml: Complete line number synchronization (~55 entries)
Guide grew from ~9900 to 11154 lines; all deep_dive references updated
- Version bump: 3.9.5 → 3.9.6
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-01-20 08:36:35 +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
dab11d260c
feat: reorganize learning commands under /learn namespace
...
- Move quiz.md → learn/quiz.md (/learn:quiz)
- Add learn/teach.md (/learn:teach) for step-by-step concept explanations
- Add learn/alternatives.md (/learn:alternatives) for approach comparisons
- Update all references in guide, README, and reference.yaml
Follows Claude Code namespaced commands convention:
/namespace:command → .claude/commands/namespace/command.md
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-01-19 11:13:54 +01:00
Florian BRUNIAUX
7fd4048d5e
feat: add learning guide & website badge
...
- Add "Visit Website" badge to README.md (prominent, top position)
- Add learning-with-ai.md guide for junior developers (~900 lines)
- UVAL Protocol, dependency patterns, 30-day progression plan
- Add 3 learning templates (55 total):
- examples/claude-md/learning-mode.md
- examples/commands/quiz.md
- examples/hooks/bash/learning-capture.sh
- Fix template count: 52 → 55 (was incorrectly showing 56)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-01-17 18:42:34 +01:00
