Fix missing context gathering and AI-slop copy in 3 skills

critique:
- Add MANDATORY PREPARATION block with context gathering and
  {{ask_instruction}} — it was the only skill with a MANDATORY
  PREPARATION section in other skills that lacked one
- Enforce frontend-design skill loading with "Do NOT proceed until..."

onboard:
- Add MANDATORY PREPARATION block — same gap as critique, onboard
  jumped straight to assessment without gathering context first
- Add frontend-design skill loading

delight:
- Replace cliched loading messages ("Herding pixels", "Teaching robots
  to dance", "Consulting the magic 8-ball") with product-specific
  examples — these are exactly the kind of AI-generated copy the
  suite's own anti-slop philosophy warns against
- Add explicit WARNING against these cliched patterns
- Change "Checkboxes that bounce" to "scale pulse" — bounce easing
  contradicts the suite's consistent stance against bounce/elastic
  curves (documented in motion-design reference and every skill
  that mentions easing)

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

source/skills/critique/SKILL.md

@@ -8,9 +8,26 @@ args:
 user-invokable: true
 ---
 
-Conduct a holistic design critique, evaluating whether the interface actually works—not just technically, but as a designed experience. Think like a design director giving feedback.
+## MANDATORY PREPARATION
 
-**First**: Use the frontend-design skill for design principles and anti-patterns.
+### Context Gathering (Do This First)
+
+You cannot do a great job without having necessary context, such as target audience (critical), desired use-cases (critical), brand personality/tone, and what the interface is trying to accomplish.
+
+Attempt to gather these from the current thread or codebase.
+
+1. If you don't find *exact* information and have to infer from existing design and functionality, you MUST STOP and {{ask_instruction}} whether you got it right.
+2. Otherwise, if you can't fully infer or your level of confidence is medium or lower, you MUST {{ask_instruction}} clarifying questions first to complete your context.
+
+Do NOT proceed until you have answers. Critique without context produces generic feedback.
+
+### Use frontend-design skill
+
+Use the frontend-design skill for design principles and anti-patterns. Do NOT proceed until it has executed and you know all DO's and DON'Ts.
+
+---
+
+Conduct a holistic design critique, evaluating whether the interface actually works—not just technically, but as a designed experience. Think like a design director giving feedback.
 
 ## Design Critique
 

source/skills/delight/SKILL.md

@@ -113,7 +113,7 @@ Add personality and joy through these methods:
 
 **Loading delight**:
 - Playful loading animations (not just spinners)
-- Personality in loading messages ("Herding pixels..." "Teaching robots to dance...")
+- Personality in loading messages (write product-specific ones, not generic AI filler)
 - Progress indication with encouraging messages
 - Skeleton screens with subtle animations
 
@@ -203,7 +203,7 @@ Add personality and joy through these methods:
 
 **Form interactions**:
 - Input fields that animate on focus
-- Checkboxes that bounce when checked
+- Checkboxes with a satisfying scale pulse when checked
 - Success state that celebrates valid input
 - Auto-grow textareas
 
@@ -253,13 +253,15 @@ Add personality and joy through these methods:
 - Countdown with encouraging messages
 
 ```
-Loading messages rotation:
-- "Waking up the servers..."
-- "Teaching robots to dance..."
-- "Consulting the magic 8-ball..."
-- "Counting backwards from infinity..."
+Loading messages — write ones specific to your product, not generic AI filler:
+- "Crunching your latest numbers..."
+- "Syncing with your team's changes..."
+- "Preparing your dashboard..."
+- "Checking for updates since yesterday..."
 ```
 
+**WARNING**: Avoid cliched loading messages like "Herding pixels", "Teaching robots to dance", "Consulting the magic 8-ball", "Counting backwards from infinity". These are AI-slop copy — instantly recognizable as machine-generated. Write messages that are specific to what your product actually does.
+
 ### Celebration Moments
 
 **Success celebrations**:

source/skills/onboard/SKILL.md

@@ -8,6 +8,25 @@ args:
 user-invokable: true
 ---
 
+## MANDATORY PREPARATION
+
+### Context Gathering (Do This First)
+
+You cannot do a great job without having necessary context, such as target audience (critical), desired use-cases (critical), the "aha moment" you want users to reach, and what users' experience level and motivation looks like.
+
+Attempt to gather these from the current thread or codebase.
+
+1. If you don't find *exact* information and have to infer from existing design and functionality, you MUST STOP and {{ask_instruction}} whether you got it right.
+2. Otherwise, if you can't fully infer or your level of confidence is medium or lower, you MUST {{ask_instruction}} clarifying questions first to complete your context.
+
+Do NOT proceed until you have answers. Onboarding designed for the wrong audience wastes everyone's time.
+
+### Use frontend-design skill
+
+Use the frontend-design skill for design principles and anti-patterns. Do NOT proceed until it has executed and you know all DO's and DON'Ts.
+
+---
+
 Create or improve onboarding experiences that help users understand, adopt, and succeed with the product quickly.
 
 ## Assess Onboarding Needs