Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Generate one-page meeting briefings from structured input (attendees, prior context, decisions needed). Use before customer calls, board meetings, or 1:1s to prepare a pre-read or briefing.
.claude/skills/borghei-calendar-prep/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-11 | ✗→✓ | ▲ Improved | -36% | 0% |
| case-01 | ✗→✓ | ▲ Improved | -21% | 0% |
| case-02 | ✗→✓ | ▲ Improved | -25% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 4% | 0% |
| case-05 | ✗→✓ | ▲ Improved | -35% | 0% |
Convert structured meeting context into a one-page briefing in seconds.
meeting prep, calendar prep, briefing, pre-read, pre-meeting, talking points, agenda, board meeting, customer call, 1:1
Before generating the briefing, confirm these inputs. If any is unknown or vague, ASK — do not assume:
Stop rule: ask only the 2-3 that most change the output. If the user says "just draft it," proceed and list your assumptions at the top of the artifact.
assets/meeting_input.json with attendees, context, decisions needed, supporting linkspython scripts/meeting_prep_briefer.py meeting_input.jsonTime Estimate: 10-15 minutes per major customer call.
documents/pptx-toolkit/ deck auditTime Estimate: 30-60 minutes per board meeting.
Time Estimate: 5-10 minutes per 1:1.
Reads a structured JSON input describing meeting context and produces a one-page briefing in markdown.
bashpython scripts/meeting_prep_briefer.py meeting_input.json python scripts/meeting_prep_briefer.py meeting_input.json --json
references/briefing_methodology.md — When briefings help and when they don't, format conventionsassets/meeting_input.json — Input file templatepersonal-productivity/meeting-insights/ post-meeting to convert the briefing's questions into the meeting's decisions.| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-11 | fail→pass | 10,953 | 3,088 | -72% | 1 | 1 | 0% | 1,733 | 1,108 | -36% | 0 | 0 | — |
case-01 | fail→pass | 12,257 | 4,611 | -62% | 1 | 1 | 0% | 1,801 | 1,422 | -21% | 0 | 0 | — |
case-02 | fail→pass | 11,729 | 4,144 | -65% | 1 | 1 | 0% | 1,859 | 1,391 | -25% | 0 | 0 | — |
case-03 | fail→pass | 18,333 | 15,121 | -18% | 1 | 1 | 0% | 2,738 | 2,860 | +4% | 0 | 0 | — |
case-04 | pass→pass | 10,210 | 10,387 | +2% | 1 | 1 | 0% | 1,458 | 2,280 | +56% | 0 | 0 | — |
case-05 | fail→pass | 10,262 | 1,991 | -81% | 1 | 1 | 0% | 1,646 | 1,071 | -35% | 0 | 0 | — |
case-06 | fail→pass | 8,773 | 1,943 | -78% | 1 | 1 | 0% | 1,514 | 1,094 | -28% | 0 | 0 | — |
case-07 | fail→pass | 14,620 | 4,318 | -70% | 1 | 1 | 0% | 2,192 | 1,347 | -39% | 0 | 0 | — |
case-08 | fail→pass | 12,097 | 5,326 | -56% | 1 | 1 | 0% | 1,863 | 1,651 | -11% | 0 | 0 | — |
case-09 | fail→pass | 7,621 | 2,934 | -62% | 1 | 1 | 0% | 1,357 | 1,223 | -10% | 0 | 0 | — |
case-10 | pass→pass | 9,923 | 2,332 | -76% | 1 | 1 | 0% | 1,342 | 1,140 | -15% | 0 | 0 | — |
case-12 | pass→pass | 10,437 | 7,308 | -30% | 1 | 1 | 0% | 1,582 | 1,782 | +13% | 0 | 0 | — |
case-13 | pass→pass | 17,722 | 4,558 | -74% | 1 | 1 | 0% | 1,445 | 1,377 | -5% | 0 | 0 | — |
case-14 | fail→pass | 6,835 | 1,800 | -74% | 1 | 1 | 0% | 970 | 972 | +0% | 0 | 0 | — |
case-15 | fail→pass | 15,802 | 2,670 | -83% | 1 | 1 | 0% | 2,339 | 1,157 | -51% | 0 | 0 | — |
case-20 | pass→pass | 7,115 | 7,979 | +12% | 1 | 1 | 0% | 1,152 | 1,854 | +61% | 0 | 0 | — |
case-16 | fail→pass | 15,312 | 1,884 | -88% | 1 | 1 | 0% | 1,760 | 1,012 | -43% | 0 | 0 | — |
case-17 | fail→pass | 9,695 | 2,046 | -79% | 1 | 1 | 0% | 1,451 | 1,004 | -31% | 0 | 0 | — |
case-18 | fail→pass | 8,555 | 2,850 | -67% | 1 | 1 | 0% | 1,322 | 1,137 | -14% | 0 | 0 | — |
case-19 | pass→pass | 11,698 | 3,552 | -70% | 1 | 1 | 0% | 1,826 | 1,349 | -26% | 0 | 0 | — |
case-21 | pass→pass | 4,367 | 4,654 | +7% | 1 | 1 | 0% | 723 | 1,392 | +93% | 0 | 0 | — |
case-22 | pass→pass | 5,402 | 5,110 | -5% | 1 | 1 | 0% | 823 | 1,528 | +86% | 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 +64 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.