Install any skill in seconds. Free to start, no credit card required.
Get Started Free →This skill enables Perplexity AI to conduct comprehensive pre-meeting research and generate structured briefing documents, helping professionals walk into every meeting fully informed and ready to add value.
.claude/skills/vythanhtra-skill-meeting-preparation/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-09 | ✗→✓ | ▲ Improved | 94% | 0% |
| case-15 | ✗→✓ | ▲ Improved | 68% | 0% |
| case-17 | ✗→✓ | ▲ Improved | 95% | 0% |
| case-19 | ✗→✓ | ▲ Improved | 90% | 0% |
| case-04 | ✓→✓ | = Same ✓ | 256% | 0% |
This skill enables Perplexity AI to conduct comprehensive pre-meeting research and generate structured briefing documents, helping professionals walk into every meeting fully informed and ready to add value.
yamlrequired_inputs: - meeting_type: "sales|interview|partnership|team|board|vendor|networking" - participants: "Names and companies of key participants" - meeting_objective: "What you want to achieve" optional_inputs: - agenda_items: "Specific topics to be discussed" - prior_context: "Previous interactions or relevant history" - your_role: "Your position and what you're representing" - meeting_duration: "Length of the meeting" - prep_depth: "quick|standard|deep"
Step 1: Individual Research
For each key participant, research:
- Current title and company
- Career background (last 3-5 years)
- Educational background
- Published content or notable quotes
- Recent activity (posts, articles, speaking engagements)
- Any awards or recognitionStep 2: Identify Conversation Hooks
Look for:
- Shared connections or alma maters
- Common interests or expertise areas
- Recent milestones (promotions, company news)
- Their stated priorities or challenges
- Projects they are publicly excited aboutStep 3: Company Deep-Dive
Research areas:
- Founding story and mission
- Current product/service offerings
- Business model and revenue approach
- Recent funding, M&A, or major announcements
- Key customers and use cases
- Technology stack (if relevant)
- Culture and values signalsStep 4: Industry Context
Gather:
- Current trends affecting their business
- Regulatory or market changes
- Competitor landscape overview
- Analyst reports or expert opinions
- Macroeconomic factors relevant to their sectorStep 5: Objective Alignment
Step 6: Question Preparation
| Question Type | Purpose | Example | |--------------|---------|--------| | Discovery | Understand their situation | "What is your biggest challenge with X?" | | Qualifying | Assess fit/readiness | "How are you currently handling Y?" | | Vision | Explore future state | "Where do you want to be in 12 months?" | | Validation | Confirm understanding | "Did I capture that correctly?" | | Next Steps | Drive action | "What would need to happen for us to move forward?" |
markdown# Meeting Brief: [Meeting Title] **Date & Time:** [Date] at [Time] **Duration:** [X] minutes **Location/Platform:** [In-person/Zoom/Teams] **Prepared by:** [Your Name] **Objective:** [One sentence goal] --- ## Participants ### [Participant Name] - [Title] at [Company] - **Background:** [2-3 sentences on career history] - **Current Focus:** [What they are working on now] - **Notable:** [Interesting fact, recent achievement, or connection point] - **LinkedIn:** [URL] --- ## Company Overview: [Company Name] - **Founded:** [Year] | **Size:** [Employees] | **Stage:** [Startup/Growth/Enterprise] - **What they do:** [One sentence description] - **Recent news:** [Key recent development] - **Key challenge:** [Known pain point or strategic priority] --- ## Agenda & Talking Points ### Topic 1: [Agenda Item] - Background context: [Relevant info] - Your key message: [What to communicate] - Questions to ask: [2-3 questions] ### Topic 2: [Agenda Item] - Background context: [Relevant info] - Your key message: [What to communicate] - Questions to ask: [2-3 questions] --- ## My Key Messages 1. [Most important point to communicate] 2. [Second key message] 3. [Third key message] ## Questions to Ask 1. [High-priority question] 2. [Discovery question] 3. [Future-state question] 4. [Follow-up based on research] ## Potential Objections & Responses | They might say... | I will respond with... | |------------------|----------------------| | [Objection 1] | [Response] | | [Objection 2] | [Response] | ## Success Criteria - [ ] [Primary outcome to achieve] - [ ] [Secondary outcome] - [ ] [Relationship goal] --- ## Notes Template _Use during meeting:_ **Key points discussed:** - **Decisions made:** - **Action items:** | Action | Owner | Due Date | |--------|-------|----------| | | | | **Next meeting:** [Date/Topic]
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 16,531 | 14,833 | -10% | 1 | 1 | 0% | 2,827 | 4,232 | +50% | 0 | 0 | — |
case-02 | fail→fail | 20,790 | 16,045 | -23% | 1 | 1 | 0% | 3,484 | 4,584 | +32% | 0 | 0 | — |
case-03 | fail→fail | 25,109 | 13,599 | -46% | 1 | 1 | 0% | 3,050 | 4,166 | +37% | 0 | 0 | — |
case-04 | pass→pass | 5,080 | 6,480 | +28% | 1 | 1 | 0% | 828 | 2,947 | +256% | 0 | 0 | — |
case-05 | pass→pass | 13,361 | 11,332 | -15% | 1 | 1 | 0% | 2,278 | 4,305 | +89% | 0 | 0 | — |
case-06 | fail→fail | 25,381 | 35,702 | +41% | 1 | 1 | 0% | 4,000 | 5,561 | +39% | 0 | 0 | — |
case-07 | fail→fail | 10,143 | 8,579 | -15% | 1 | 1 | 0% | 1,727 | 3,321 | +92% | 0 | 0 | — |
case-08 | fail→fail | 11,693 | 8,458 | -28% | 1 | 1 | 0% | 1,795 | 3,396 | +89% | 0 | 0 | — |
case-09 | fail→pass | 13,045 | 11,760 | -10% | 1 | 1 | 0% | 1,952 | 3,792 | +94% | 0 | 0 | — |
case-10 | pass→pass | 15,364 | 16,423 | +7% | 1 | 1 | 0% | 2,386 | 4,327 | +81% | 0 | 0 | — |
case-11 | fail→fail | 15,143 | 10,888 | -28% | 1 | 1 | 0% | 2,302 | 3,134 | +36% | 0 | 0 | — |
case-12 | pass→pass | 15,372 | 15,082 | -2% | 1 | 1 | 0% | 2,249 | 4,346 | +93% | 0 | 0 | — |
case-13 | pass→pass | 14,818 | 15,967 | +8% | 1 | 1 | 0% | 2,210 | 4,524 | +105% | 0 | 0 | — |
case-14 | pass→pass | 16,548 | 15,841 | -4% | 1 | 1 | 0% | 2,678 | 4,471 | +67% | 0 | 0 | — |
case-15 | fail→pass | 13,157 | 11,778 | -10% | 1 | 1 | 0% | 1,974 | 3,314 | +68% | 0 | 0 | — |
case-16 | fail→fail | 17,455 | 14,298 | -18% | 1 | 1 | 0% | 2,758 | 4,263 | +55% | 0 | 0 | — |
case-17 | fail→pass | 11,619 | 11,422 | -2% | 1 | 1 | 0% | 1,934 | 3,778 | +95% | 0 | 0 | — |
case-18 | pass→pass | 9,970 | 9,778 | -2% | 1 | 1 | 0% | 1,729 | 3,714 | +115% | 0 | 0 | — |
case-19 | fail→pass | 9,522 | 6,410 | -33% | 1 | 1 | 0% | 1,542 | 2,927 | +90% | 0 | 0 | — |
case-20 | fail→fail | 13,036 | 11,202 | -14% | 1 | 1 | 0% | 2,069 | 3,732 | +80% | 0 | 0 | — |
case-21 | fail→fail | 11,001 | 6,969 | -37% | 1 | 1 | 0% | 1,985 | 3,416 | +72% | 0 | 0 | — |
case-22 | pass→pass | 7,964 | 5,062 | -36% | 1 | 1 | 0% | 1,320 | 2,786 | +111% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted. The headline lift of +18 percentage points is the difference between those two pass rates over the 22 comparable cases.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.