skills/general/generate-philosophy-doc/SKILL.md
create philosophy doc, generate standards, build best practices guide.
npx skillsauth add beam-ai-team/beam-next-skills generate-philosophy-docInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Create comprehensive, research-backed philosophy and standards documents for any domain.
This skill generates high-quality philosophy documents similar to ux-onboarding-philosophy.md for any domain:
Each document includes:
Ask the user to specify:
Domain name: "What domain do you want to document?"
Target audience: "Who will use this document?"
Focus areas (optional): "Any specific areas to emphasize?"
Clarify scope: Ensure domain is specific enough to be actionable but broad enough to be useful.
Use the WebSearch tool or Perplexity API to gather comprehensive research:
Research Strategy:
Foundational Research (principles and theory):
Framework Research (methodologies):
Anti-Pattern Research (common mistakes):
Metrics Research (measurement):
Case Study Research (real examples):
Academic Research (credible sources):
Execute 10-15 targeted searches covering all research areas. Synthesize findings into structured notes organized by section.
Optional: Use scripts/research_topic.py to generate search queries:
uv run python scripts/research_topic.py "Landing Page Design" "principles,frameworks,anti-patterns,metrics"
Use the bundled template to create the document structure:
Option A: Manual Creation
Copy assets/philosophy-template.md and fill in sections with research findings.
Option B: Script-Assisted
uv run python scripts/generate_structure.py "Landing Page Design" > output.md
Then fill in placeholders with researched content.
Work through each section systematically. See references/document-template.md for detailed guidance on each section.
Length: 100-200 words
Create 5-8 principles. Each principle needs:
Format Pattern:
### Principle 1: [Name]
**Definition**: [One sentence]
**Why This Works**: [Research explanation with citation]
**Application**:
- WRONG: [Concrete bad example]
- RIGHT: [Concrete good example]
**Test**: [Verification method]
Quality Check:
Length: 400-800 words total (80-160 per principle)
Create a named framework (e.g., "LIFT Framework", "AIDA Model"):
Example Structure:
### The CLEAR Framework
[ASCII diagram showing 5 phases]
#### Phase 1: Capture Attention
**Purpose**: Hook user in first 3 seconds
**Key Activities**:
- Design hero section with compelling headline
- Use high-contrast CTA button
- Optimize above-fold content
**Quality Checklist**:
- [ ] Headline clearly states value proposition
- [ ] CTA visible without scrolling
- [ ] Hero image supports message
**Time Budget**: 20% of design process
Length: 400-600 words
Document 5-10 common mistakes:
Format:
### Anti-Pattern 1: "The Wall of Text"
**Symptom**: Landing page with 500+ words above fold, no visual breaks
**Example**:
WRONG:
[Paste or describe actual bad example]
**Why It Fails**: Users scan, don't read. Average time on page: 8 seconds.
Wall of text = 90% bounce rate (Source: Nielsen Norman Group)
**Fix**: Break into scannable sections with headers, bullets, and whitespace
**Metrics**: Before: 90% bounce | After: 45% bounce (50% improvement)
Length: 400-600 words total (60-80 per anti-pattern)
Create 3 checklists:
Format:
### Pre-Design Checklist
**Define Success Criteria**:
- [ ] Primary conversion goal defined
- [ ] Target audience identified
- [ ] Success metrics established
**Audience Analysis**:
- [ ] User personas documented
- [ ] Pain points identified
- [ ] Value proposition clear
Quality Standards:
Length: 200-400 words
Include 2-3 real examples:
Example:
### Case Study: Dropbox Homepage Redesign
**Context**: Dropbox needed to improve conversion on homepage (2017)
**Challenge**: 65% bounce rate, unclear value proposition
**Approach**: Applied "Show Don't Tell" principle - replaced feature list
with video demo showing product in action
**Before**:
- Bounce Rate: 65%
- Sign-up Conversion: 2.8%
- Time on Page: 12 seconds
**After**:
- Bounce Rate: 42% (35% improvement)
- Sign-up Conversion: 4.2% (50% improvement)
- Time on Page: 48 seconds (300% improvement)
**Key Insights**:
- Video demo increased engagement 4x
- Visual demonstration beats text explanation
- Clear CTA after video critical for conversion
Length: 300-500 words total (150-250 per case study)
Create tiered metrics structure:
Format:
### Success Metrics Hierarchy
TIER 1: CRITICAL METRICS (Make or Break)
- Conversion Rate: Primary goal completion
Target: >5% | Baseline: 2-3%
- Bounce Rate: User engagement
Target: <40% | Baseline: 50-60%
### Red Flags
CRITICAL RED FLAGS:
1. Conversion Rate < 2%
-> Poor value proposition - Redesign messaging
2. Bounce Rate > 70%
-> No engagement - Rethink content strategy
Length: 300-400 words
Organize sources by category:
Format:
### Academic Sources
1. **Cognitive Psychology**:
- Nielsen, J. (2006). "F-Shaped Pattern For Reading Web Content"
- Kahneman, D. (2011). "Thinking, Fast and Slow"
### Industry Research
1. **ConversionXL**: Landing page optimization studies
2. **Baymard Institute**: UX research and benchmarks
Quality Standards:
Length: 100-200 words
Use references/quality-checklist.md to validate the document:
Critical Checks:
Content Quality:
Formatting Quality:
Target Grade: B (80%+) minimum, A (90%+) recommended
After initial draft:
Common Refinements:
Output Format Options:
[domain]-philosophy.md in appropriate location00-system/documentation/ if system-wideDelivery Includes:
Do:
Don't:
Do:
Don't:
Too Broad: Domain too general to be actionable
Too Shallow: Research insufficient for depth
No Metrics: Principles lack quantified support
Abstract Examples: Examples too generic to be useful
Incomplete Sections: Missing key components
UX & Design:
Marketing:
Technical:
Business:
Skill Resources:
Example Philosophy Document:
Scripts:
scripts/research_topic.py - Generate research queriesscripts/generate_structure.py - Generate document structureA successful philosophy document:
Target: Create documents that become authoritative references for the domain.
testing
Audit registry.yaml against disk, validate SKILL.md frontmatter, find duplicates and orphans. Load when user says 'audit skills registry', 'validate beam-next-skills', 'registry drift', 'skills catalog audit', 'check registry yaml'.
tools
All Workable ATS operations — fetch JDs, search candidates, post assessments/reviews. Load when user says "fetch JD", "search workable", "push to workable", "post review", "rate candidate", "workable", "push assessment", "list jobs", or after interview-coach completes an evaluation. Replaces workable-fetch-jd and workable-push-assessment.
data-ai
Load when user mentions "tavily research", "market intelligence", "competitive research", "GTM research", or needs real-time market data for sales, marketing, or vertical strategy.
development
Shared resource library for Slack integration skills. DO NOT load directly - provides common references (setup, API docs, error handling, authentication) and scripts used by slack-connect and individual Slack skills.