Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Structured meeting summarization that captures decisions, action items, and open questions in a consistent format.
.claude/skills/borghei-summarize-meeting/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 395% | 0% |
| case-02 | ✗→✓ | ▲ Improved | 213% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 159% | 0% |
| case-07 | ✗→✓ | ▲ Improved | 367% | 0% |
| case-14 | ✗→✓ | ▲ Improved | 255% | 0% |
Transform meeting notes, transcripts, or recordings into clear, actionable summaries. Every summary follows a consistent structure that makes it easy for attendees and non-attendees alike to understand what was discussed, what was decided, and who is doing what by when.
Before summarizing, 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.
Load the reference that matches the task — keep this file lean and pull detail on demand:
wwas/ to create backlog items with strategic context.../jira-expert/.../confluence-expert/ templates.In Scope: Capturing meeting metadata, extracting key discussion points, documenting decisions with rationale, recording action items with owners and due dates, capturing open questions, distributing summaries, maintaining consistent naming conventions and storage.
Out of Scope: Meeting facilitation and agenda design, real-time transcription (use a transcription tool as input), project status tracking (hand off to ../jira-expert/), strategic decision frameworks (hand off to ../senior-pm/), recording or video management.
Limitations: Summary quality is bounded by the quality of input notes or transcript. Automated transcription tools may introduce errors that the summarizer must catch. The skill does not replace the need for a skilled facilitator -- poorly run meetings produce poor summaries regardless of template quality. Sensitive or confidential meetings may require restricted distribution that the standard workflow does not address.
| Integration | Direction | What Flows | |-------------|-----------|------------| | wwas/ | Meetings -> WWAS | Decisions and commitments from meetings become WWAS backlog items | | job-stories/ | Meetings -> Stories | Discovery discussions surface situations and motivations for job stories | | ../jira-expert/ | Meetings -> Jira | Action items create Jira tickets; decisions update issue comments | | ../confluence-expert/ | Meetings -> Confluence | Summaries stored in Confluence using meeting notes template | | ../senior-pm/ | Meetings -> PM | Steering committee and stakeholder meeting summaries feed portfolio reporting | | ../delivery-manager/ | Meetings -> DM | Release planning and incident review meeting outcomes feed delivery tracking |
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 2,372 | 5,108 | +115% | 1 | 1 | 0% | 368 | 1,821 | +395% | 0 | 0 | — |
case-02 | fail→pass | 3,912 | 6,624 | +69% | 1 | 1 | 0% | 604 | 1,888 | +213% | 0 | 0 | — |
case-03 | fail→pass | 4,327 | 5,598 | +29% | 1 | 1 | 0% | 691 | 1,792 | +159% | 0 | 0 | — |
case-04 | pass→pass | 3,688 | 6,568 | +78% | 1 | 1 | 0% | 539 | 1,992 | +270% | 0 | 0 | — |
case-05 | pass→pass | 2,314 | 4,460 | +93% | 1 | 1 | 0% | 381 | 1,714 | +350% | 0 | 0 | — |
case-06 | pass→pass | 4,289 | 5,422 | +26% | 1 | 1 | 0% | 720 | 1,894 | +163% | 0 | 0 | — |
case-07 | fail→pass | 2,613 | 5,956 | +128% | 1 | 1 | 0% | 427 | 1,992 | +367% | 0 | 0 | — |
case-08 | fail→fail | 2,691 | 5,685 | +111% | 1 | 1 | 0% | 516 | 1,965 | +281% | 0 | 0 | — |
case-09 | pass→pass | 8,838 | 3,614 | -59% | 1 | 1 | 0% | 1,246 | 1,610 | +29% | 0 | 0 | — |
case-10 | pass→pass | 6,470 | 4,840 | -25% | 1 | 1 | 0% | 1,142 | 1,787 | +56% | 0 | 0 | — |
case-11 | fail→fail | 4,122 | 5,378 | +30% | 1 | 1 | 0% | 654 | 1,823 | +179% | 0 | 0 | — |
case-12 | pass→pass | 7,440 | 6,602 | -11% | 1 | 1 | 0% | 1,059 | 1,935 | +83% | 0 | 0 | — |
case-13 | fail→fail | 3,678 | 3,451 | -6% | 1 | 1 | 0% | 543 | 1,532 | +182% | 0 | 0 | — |
case-14 | fail→pass | 4,330 | 8,250 | +91% | 1 | 1 | 0% | 632 | 2,245 | +255% | 0 | 0 | — |
case-15 | fail→pass | 4,153 | 5,974 | +44% | 1 | 1 | 0% | 650 | 1,911 | +194% | 0 | 0 | — |
case-16 | pass→fail | 8,956 | 8,022 | -10% | 1 | 1 | 0% | 1,438 | 2,311 | +61% | 0 | 0 | — |
case-17 | fail→pass | 6,955 | 3,678 | -47% | 1 | 1 | 0% | 1,126 | 1,575 | +40% | 0 | 0 | — |
case-18 | fail→pass | 10,067 | 3,466 | -66% | 1 | 1 | 0% | 1,568 | 1,546 | -1% | 0 | 0 | — |
case-19 | fail→fail | 10,792 | 10,948 | +1% | 1 | 1 | 0% | 1,737 | 2,831 | +63% | 0 | 0 | — |
case-20 | pass→pass | 6,490 | 4,991 | -23% | 1 | 1 | 0% | 906 | 1,786 | +97% | 0 | 0 | — |
case-21 | pass→pass | 7,915 | 6,666 | -16% | 1 | 1 | 0% | 1,625 | 2,028 | +25% | 0 | 0 | — |
case-22 | fail→pass | 15,722 | 7,761 | -51% | 1 | 1 | 0% | 2,466 | 2,133 | -14% | 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 +36 percentage points is the difference between those two pass rates over the 22 comparable cases. 1 case got worse with the skill loaded, and it is 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.