Andrew Yim
341d5f5a5b
Custom Skills (ourdigital-custom-skills/): - 00-ourdigital-visual-storytelling: Blog featured image prompt generator - 01-ourdigital-research-publisher: Research-to-publication workflow - 02-notion-organizer: Notion workspace management - 03-research-to-presentation: Notion research to PPT/Figma - 04-seo-gateway-strategist: SEO gateway page strategy planning - 05-gateway-page-content-builder: Gateway page content generation - 20-jamie-brand-editor: Jamie Clinic branded content GENERATION - 21-jamie-brand-guardian: Jamie Clinic content REVIEW & evaluation Refinements applied: - All skills converted to SKILL.md format with YAML frontmatter - Added version fields to all skills - Flattened nested folder structures - Removed packaging artifacts (.zip, .skill files) - Reorganized file structures (scripts/, references/, etc.) - Differentiated Jamie skills with clear roles 🤖 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
102 lines
3.9 KiB
Markdown
102 lines
3.9 KiB
Markdown
# Meeting Intelligence Skill Evaluations
|
|
|
|
Evaluation scenarios for testing the Meeting Intelligence skill across different Claude models.
|
|
|
|
## Purpose
|
|
|
|
These evaluations ensure the Meeting Intelligence skill:
|
|
- Gathers context from Notion workspace
|
|
- Enriches with Claude research appropriately
|
|
- Creates both internal pre-reads and external agendas
|
|
- Distinguishes between Notion facts and Claude insights
|
|
- Works consistently across Haiku, Sonnet, and Opus
|
|
|
|
## Evaluation Files
|
|
|
|
### decision-meeting-prep.json
|
|
Tests preparation for a decision-making meeting.
|
|
|
|
**Scenario**: Prep for database migration decision meeting
|
|
**Key Behaviors**:
|
|
- Searches Notion for migration context (specs, discussions, options)
|
|
- Fetches 2-3 relevant pages
|
|
- Enriches with Claude research (decision frameworks, migration best practices)
|
|
- Creates comprehensive internal pre-read with recommendation
|
|
- Creates clean, professional external agenda
|
|
- Clearly distinguishes Notion facts from Claude insights
|
|
- Cross-links both documents
|
|
|
|
### status-meeting-prep.json
|
|
Tests preparation for a status update or review meeting.
|
|
|
|
**Scenario**: Prep for project status review
|
|
**Key Behaviors**:
|
|
- Gathers project metrics and progress from Notion
|
|
- Fetches relevant pages (roadmap, tasks, milestones)
|
|
- Adds Claude context (industry benchmarks, best practices)
|
|
- Creates internal pre-read with honest assessment
|
|
- Creates external agenda with structured flow
|
|
- Includes source citations using mention-page tags
|
|
- Time-boxes agenda items
|
|
|
|
## Running Evaluations
|
|
|
|
1. Enable the `meeting-intelligence` skill
|
|
2. Submit the query from the evaluation file
|
|
3. Verify the skill searches Notion first (not Claude research)
|
|
4. Check that TWO documents are created (internal + external)
|
|
5. Verify Claude enrichment adds value without replacing Notion content
|
|
6. Test with Haiku, Sonnet, and Opus
|
|
|
|
## Expected Skill Behaviors
|
|
|
|
Meeting Intelligence evaluations should verify:
|
|
|
|
### Notion Context Gathering
|
|
- Searches workspace for relevant context first
|
|
- Fetches specific pages (not generic)
|
|
- Extracts key information from Notion content
|
|
- Cites sources using mention-page tags
|
|
|
|
### Claude Research Integration
|
|
- Adds industry context, frameworks, or best practices
|
|
- Enrichment is relevant and valuable (not filler)
|
|
- Clearly distinguishes Notion facts from Claude insights
|
|
- Research complements (doesn't replace) Notion content
|
|
|
|
### Two-Document Creation
|
|
- **Internal Pre-Read**: Comprehensive, includes strategy, recommendations, detailed pros/cons
|
|
- **External Agenda**: Professional, focused on meeting flow, no internal strategy
|
|
- Both documents are clearly labeled
|
|
- Documents are cross-linked
|
|
|
|
### Document Quality
|
|
- Pre-read follows structure: Overview → Background → Current Status → Context & Insights → Discussion Points
|
|
- Agenda follows structure: Details → Objective → Agenda Items (with times) → Decisions → Actions → Resources
|
|
- Titles include date or meeting context
|
|
- Content is actionable and meeting-ready
|
|
|
|
## Creating New Evaluations
|
|
|
|
When adding Meeting Intelligence evaluations:
|
|
|
|
1. **Test different meeting types** - Decision, status, brainstorm, 1:1, sprint planning, retrospective
|
|
2. **Vary complexity** - Simple updates vs. complex strategic decisions
|
|
3. **Test with/without Notion content** - Rich workspace vs. minimal existing pages
|
|
4. **Verify enrichment value** - Is Claude research genuinely helpful?
|
|
5. **Check internal/external distinction** - Is sensitive info kept in pre-read only?
|
|
|
|
## Example Success Criteria
|
|
|
|
**Good** (specific, testable):
|
|
- "Creates TWO documents (internal pre-read + external agenda)"
|
|
- "Internal pre-read marked 'INTERNAL ONLY' or 'For team only'"
|
|
- "Cites at least 2-3 Notion pages using mention-page tags"
|
|
- "Agenda includes time allocations for each section"
|
|
- "Claude enrichment includes decision frameworks or best practices"
|
|
|
|
**Bad** (vague, untestable):
|
|
- "Creates meeting materials"
|
|
- "Gathers context effectively"
|
|
- "Prepares well"
|