crashtestdev

ken/crashtestdev

Fork 0

Commit Graph

Author	SHA1	Message	Date
Ken	84bf9e706b	feat: add inline SVG diagrams to judgment essay Two diagrams in the warm palette (paper bg, terracotta accent): 1. Floor and Ceiling: before/after comparison showing AI raises the floor (what's functional) while the ceiling (excellence, judgment) stays where it is. The gap between them IS the argument. 2. Lagged Failure Timeline: decision → invisible degradation → failure surfaces 12-18 months later → misattributed to market conditions. Makes the delay visible as a four-node flow. Both use SVG primitives (rect, line, text, circle) following the diagram design spec: warm palette, Inter for labels, Source Serif for descriptions, terracotta for accents. 🤖 Generated with Amplifier Co-Authored-By: Amplifier <240397093+microsoft-amplifier@users.noreply.github.com>	2026-05-27 03:53:02 +00:00
Ken	a951c00e35	fix: purge AI slop from judgment essay, add voice linting pipeline - Killed 16 em-dashes (Claude fingerprint, 15.9/1000 words -> 0) - Replaced all clause-dash-elaboration patterns with periods, colons, restructuring - Removed 'The One-Sentence Version' section (restated the intro, voice anti-pattern) - Broke tricolon at lines 56-58 (too-clean parallel structure) - Collapsed 'How to Actually Help' listicle into connective prose - Added receipt link for ~100x inference cost claim - Heading dashes replaced with colons (Tradesman Analogy, Excellence vs Functional) New tooling: - scripts/lint-voice.sh: mechanical anti-slop linter (em-dashes, trigger words, hedging, filler, receipts, sentence uniformity) - .amplifier/skills/voice-check/SKILL.md: LLM-as-judge voice authenticity check (8 dimensions against VOICE.md profile) - .amplifier/AGENTS.md: standing rule requiring both checks before any publish 🤖 Generated with Amplifier Co-Authored-By: Amplifier <240397093+microsoft-amplifier@users.noreply.github.com>	2026-05-27 00:42:18 +00:00

Author

SHA1

Message

Date

Ken

84bf9e706b

feat: add inline SVG diagrams to judgment essay

Two diagrams in the warm palette (paper bg, terracotta accent):

1. Floor and Ceiling: before/after comparison showing AI raises the
   floor (what's functional) while the ceiling (excellence, judgment)
   stays where it is. The gap between them IS the argument.

2. Lagged Failure Timeline: decision → invisible degradation →
   failure surfaces 12-18 months later → misattributed to market
   conditions. Makes the delay visible as a four-node flow.

Both use SVG primitives (rect, line, text, circle) following the
diagram design spec: warm palette, Inter for labels, Source Serif
for descriptions, terracotta for accents.

🤖 Generated with Amplifier

Co-Authored-By: Amplifier <240397093+microsoft-amplifier@users.noreply.github.com>

2026-05-27 03:53:02 +00:00

Ken

a951c00e35

fix: purge AI slop from judgment essay, add voice linting pipeline

- Killed 16 em-dashes (Claude fingerprint, 15.9/1000 words -> 0)
- Replaced all clause-dash-elaboration patterns with periods, colons, restructuring
- Removed 'The One-Sentence Version' section (restated the intro, voice anti-pattern)
- Broke tricolon at lines 56-58 (too-clean parallel structure)
- Collapsed 'How to Actually Help' listicle into connective prose
- Added receipt link for ~100x inference cost claim
- Heading dashes replaced with colons (Tradesman Analogy, Excellence vs Functional)

New tooling:
- scripts/lint-voice.sh: mechanical anti-slop linter (em-dashes, trigger words,
  hedging, filler, receipts, sentence uniformity)
- .amplifier/skills/voice-check/SKILL.md: LLM-as-judge voice authenticity check
  (8 dimensions against VOICE.md profile)
- .amplifier/AGENTS.md: standing rule requiring both checks before any publish

🤖 Generated with Amplifier

Co-Authored-By: Amplifier <240397093+microsoft-amplifier@users.noreply.github.com>

2026-05-27 00:42:18 +00:00

2 Commits