Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Prepare meeting materials with Notion context and Codex research; use when gathering context, drafting agendas/pre-reads, and tailoring materials to attendees.
.claude/skills/davila7-notion-meeting-intelligence/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-25 | ✗→✓ | ▲ Improved | 38% | 0% |
| case-12 | ✓→✗ | ▼ Worse | -52% | 0% |
| case-16 | ✓→✗ | ▼ Worse | -41% | 0% |
| case-04 | ✓→✓ | ＝ Same ✓ | 104% | 0% |
| case-05 | ✓→✓ | ＝ Same ✓ | 72% | 0% |
Prep meetings by pulling Notion context, tailoring agendas/pre-reads, and enriching with Codex research.
1) Confirm meeting goal, attendees, date/time, and decisions needed. 2) Gather context: search with Notion:notion-search, then fetch with Notion:notion-fetch (prior notes, specs, OKRs, decisions). 3) Pick the right template via reference/template-selection-guide.md (status, decision, planning, retro, 1:1, brainstorming). 4) Draft agenda/pre-read in Notion with Notion:notion-create-pages, embedding source links and owner/timeboxes. 5) Enrich with Codex research (industry insights, benchmarks, risks) and update the page with Notion:notion-update-page as plans change.
codex mcp add notion --url https://mcp.notion.com/mcp[features].rmcp_client = true in config.toml or run codex --enable rmcp_clientcodex mcp login notionAfter successful login, the user will have to restart codex. You should finish your answer and tell them so when they try again they can continue with Step 1.
Notion:notion-search), then fetch key pages (Notion:notion-fetch).reference/template-selection-guide.md to confirm.reference/ and adapt sections (context, goals, agenda, owner/time per item, decisions, risks, prep asks).Notion:notion-update-page when details change; keep a brief changelog if multiple edits.reference/ — template picker and meeting templates (e.g., template-selection-guide.md, status-update-template.md, decision-meeting-template.md, sprint-planning-template.md, one-on-one-template.md, retrospective-template.md, brainstorming-template.md).examples/ — end-to-end meeting preps (e.g., executive-review.md, project-decision.md, sprint-planning.md, customer-meeting.md).| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-07 | fail→fail | 6,687 | 4,195 | -37% | 1 | 1 | 0% | 517 | 1,099 | +113% | 0 | 0 | — |
case-01 | fail→fail | 14,158 | 6,866 | -52% | 1 | 1 | 0% | 2,306 | 1,339 | -42% | 0 | 0 | — |
case-02 | fail→fail | 11,460 | 4,905 | -57% | 1 | 1 | 0% | 1,855 | 1,159 | -38% | 0 | 0 | — |
case-03 | fail→fail | 15,054 | 6,516 | -57% | 1 | 1 | 0% | 2,399 | 1,157 | -52% | 0 | 0 | — |
case-04 | pass→pass | 5,130 | 5,357 | +4% | 1 | 1 | 0% | 811 | 1,658 | +104% | 0 | 0 | — |
case-05 | pass→pass | 8,530 | 12,832 | +50% | 1 | 1 | 0% | 1,913 | 3,284 | +72% | 0 | 0 | — |
case-06 | pass→pass | 7,331 | 5,102 | -30% | 1 | 1 | 0% | 1,425 | 1,755 | +23% | 0 | 0 | — |
case-08 | fail→fail | 5,866 | 5,265 | -10% | 1 | 1 | 0% | 305 | 1,182 | +288% | 0 | 0 | — |
case-09 | fail→fail | 12,014 | 4,327 | -64% | 1 | 1 | 0% | 1,778 | 1,058 | -40% | 0 | 0 | — |
case-10 | fail→fail | 4,683 | 5,018 | +7% | 1 | 1 | 0% | 365 | 1,179 | +223% | 0 | 0 | — |
case-11 | fail→fail | 3,933 | 4,434 | +13% | 1 | 1 | 0% | 837 | 1,642 | +96% | 0 | 0 | — |
case-12 | pass→fail | 14,173 | 5,905 | -58% | 1 | 1 | 0% | 2,658 | 1,282 | -52% | 0 | 0 | — |
case-13 | fail→fail | 5,813 | 5,604 | -4% | 1 | 1 | 0% | 533 | 1,320 | +148% | 0 | 0 | — |
case-14 | fail→fail | 4,306 | 7,273 | +69% | 1 | 1 | 0% | 263 | 2,266 | +762% | 0 | 0 | — |
case-15 | fail→fail | 8,152 | 7,032 | -14% | 1 | 1 | 0% | 1,518 | 1,326 | -13% | 0 | 0 | — |
case-16 | pass→fail | 8,824 | 4,433 | -50% | 1 | 1 | 0% | 1,853 | 1,094 | -41% | 0 | 0 | — |
case-17 | fail→fail | 11,680 | 4,551 | -61% | 1 | 1 | 0% | 2,228 | 1,108 | -50% | 0 | 0 | — |
case-18 | fail→fail | 9,138 | 5,228 | -43% | 1 | 1 | 0% | 1,650 | 1,117 | -32% | 0 | 0 | — |
case-19 | fail→fail | 12,161 | 5,643 | -54% | 1 | 1 | 0% | 2,090 | 1,328 | -36% | 0 | 0 | — |
case-20 | fail→fail | 5,152 | 4,390 | -15% | 1 | 1 | 0% | 337 | 998 | +196% | 0 | 0 | — |
case-21 | pass→pass | 10,352 | 3,482 | -66% | 1 | 1 | 0% | 1,392 | 1,436 | +3% | 0 | 0 | — |
case-22 | fail→fail | 6,348 | 7,805 | +23% | 1 | 1 | 0% | 1,579 | 1,726 | +9% | 0 | 0 | — |
case-23 | fail→fail | 12,788 | 4,128 | -68% | 1 | 1 | 0% | 1,869 | 1,100 | -41% | 0 | 0 | — |
case-24 | fail→fail | 2,818 | 5,108 | +81% | 1 | 1 | 0% | 285 | 1,242 | +336% | 0 | 0 | — |
case-25 | fail→pass | 4,581 | 2,026 | -56% | 1 | 1 | 0% | 860 | 1,185 | +38% | 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. 25 cases were attempted, and 6 counted toward the lift figure. The other 19 produced results that are not comparable between the two arms, so they are excluded from the headline rather than averaged into it. The headline lift of -4 percentage points is the difference between those two pass rates over the 6 comparable cases. 11 cases got worse with the skill loaded, and they are included in that figure.
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.