AI Skill Report Card

Creating AI Skills

B72·Apr 2, 2026·Source: Extension-page
12 / 15

Input your expertise description and get a structured skill:

Input: "I'm a UX researcher who conducts user interviews"
Output: Structured skill with identity, process steps, and quality standards
Recommendation
Replace the abstract Quick Start example with actual concrete input/output showing a complete skill transformation
15 / 15

Progress:

  • Analyze Input: Extract core expertise, methodology, and domain
  • Structure Identity: Define the expert role and specialization
  • Map Process: Break down methodology into clear, actionable steps
  • Set Standards: Identify quality benchmarks and best practices
  • Add Examples: Include concrete input/output scenarios
  • Score & Refine: Rate clarity, specificity, and usability (0-100)

Step-by-Step Process

  1. Parse Expertise Description

    • Identify the professional role/domain
    • Extract specific methodologies mentioned
    • Note tools, frameworks, or standards used
  2. Create Structured Identity

    • Write clear role definition
    • Specify areas of specialization
    • Define scope and boundaries
  3. Document Process Flow

    • Break methodology into numbered steps
    • Make each step actionable and specific
    • Include decision points and alternatives
  4. Establish Quality Standards

    • Define what "good" looks like
    • Set measurable criteria
    • Include common success metrics
  5. Generate Examples

    • Create realistic input scenarios
    • Show expected output format
    • Include edge cases if relevant
Recommendation
Provide full structured skill templates instead of abbreviated examples with '...' - show complete methodology
10 / 20

Example 1: Input: "I'm a senior developer who does code reviews focusing on security and performance" Output:

Identity: Expert code reviewer specializing in security vulnerabilities and performance optimization
Process: 1. Scan for security anti-patterns 2. Analyze performance bottlenecks 3. Check architecture decisions...
Quality Standards: Zero security vulnerabilities, sub-100ms response times, maintainable code patterns

Example 2: Input: "I help startups with fundraising pitch decks" Output:

Identity: Startup fundraising advisor specializing in pitch deck optimization for Series A-C rounds
Process: 1. Analyze market positioning 2. Refine value proposition 3. Structure financial projections...
Quality Standards: Clear problem-solution fit, defensible market size, realistic projections
Recommendation
Remove over-explanation of basics like 'Use Action Verbs' and 'Be Specific' - focus on unique methodology for skill creation
  • Be Specific: "Marketing" → "B2B SaaS demand generation"
  • Include Frameworks: MATCH framework, OKR methodology, etc.
  • Set Clear Standards: Measurable quality criteria
  • Use Action Verbs: "Analyzes", "Creates", "Optimizes"
  • Reference Real Tools: Specific software, platforms, methodologies
  • Score Objectively: Rate on clarity, specificity, and usability
  • Too Generic: Avoid broad descriptions like "I help with business"
  • No Process: Don't just describe what, include how
  • Missing Standards: Always define quality criteria
  • Vague Examples: Use concrete, realistic scenarios
  • No Context: Include when and why to use the skill
0
Grade BAI Skill Framework
Scorecard
Criteria Breakdown
Quick Start
12/15
Workflow
15/15
Examples
10/20
Completeness
10/20
Format
15/15
Conciseness
10/15