Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Retrieve meeting transcripts and summaries from the Fathom API. Use when fetching meeting data, testing API access, or learning Fathom API response structure. Trigger with phrases like "fathom hello world", "fathom first api call", "get fathom transcript", "fathom meeting data".
.claude/skills/jeremylongshore-fathom-hello-world/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | -38% | 0% |
| case-02 | ✗→✓ | ▲ Improved | -22% | 0% |
| case-03 | ✗→✓ | ▲ Improved | -14% | 0% |
| case-04 | ✗→✓ | ▲ Improved | 10% | 0% |
| case-05 | ✗→✓ | ▲ Improved | -26% | 0% |
First API calls against Fathom: list meetings, get a transcript, retrieve AI-generated summaries and action items.
fathom-install-auth setupbashcurl -s -H "X-Api-Key: ${FATHOM_API_KEY}" \ "https://api.fathom.ai/external/v1/meetings?limit=5" \ | jq '.meetings[] | {id, title, created_at, duration_seconds}'
bashRECORDING_ID="your-recording-id" curl -s -H "X-Api-Key: ${FATHOM_API_KEY}" \ "https://api.fathom.ai/external/v1/recordings/${RECORDING_ID}/transcript" \ | jq '.segments[] | {speaker, text, start_time}'
bash# Get meeting with summary included curl -s -H "X-Api-Key: ${FATHOM_API_KEY}" \ "https://api.fathom.ai/external/v1/meetings?include_summary=true&limit=1" \ | jq '.meetings[0] | {title, summary, action_items}'
bash# Meetings from the last 7 days curl -s -H "X-Api-Key: ${FATHOM_API_KEY}" \ "https://api.fathom.ai/external/v1/meetings?created_after=2026-03-15T00:00:00Z&limit=20" \ | jq '.meetings | length'
| Error | Cause | Solution | |-------|-------|----------| | Empty meetings array | No recordings in account | Record a meeting in Fathom | | 404 on recording ID | Wrong ID or deleted | List meetings to get valid IDs | | No summary available | Meeting still processing | Wait a few minutes after recording | | Transcript empty | Recording too short | Minimum meeting length required |
Proceed to fathom-local-dev-loop for development workflow setup.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 12,386 | 2,935 | -76% | 1 | 1 | 0% | 1,866 | 1,166 | -38% | 0 | 0 | — |
case-02 | fail→pass | 8,524 | 3,139 | -63% | 1 | 1 | 0% | 1,593 | 1,238 | -22% | 0 | 0 | — |
case-03 | fail→pass | 11,210 | 8,215 | -27% | 1 | 1 | 0% | 2,130 | 1,839 | -14% | 0 | 0 | — |
case-04 | fail→pass | 5,454 | 3,284 | -40% | 1 | 1 | 0% | 991 | 1,092 | +10% | 0 | 0 | — |
case-05 | fail→pass | 9,126 | 3,183 | -65% | 1 | 1 | 0% | 1,710 | 1,264 | -26% | 0 | 0 | — |
case-06 | pass→pass | 12,625 | 1,786 | -86% | 1 | 1 | 0% | 1,824 | 901 | -51% | 0 | 0 | — |
case-07 | fail→pass | 7,547 | 9,377 | +24% | 1 | 1 | 0% | 1,194 | 1,667 | +40% | 0 | 0 | — |
case-08 | fail→pass | 7,207 | 3,411 | -53% | 1 | 1 | 0% | 1,074 | 1,132 | +5% | 0 | 0 | — |
case-09 | fail→pass | 12,598 | 7,542 | -40% | 1 | 1 | 0% | 2,138 | 2,008 | -6% | 0 | 0 | — |
case-10 | fail→pass | 11,734 | 9,951 | -15% | 1 | 1 | 0% | 2,007 | 2,016 | +0% | 0 | 0 | — |
case-11 | pass→pass | 10,845 | 4,945 | -54% | 1 | 1 | 0% | 1,487 | 1,367 | -8% | 0 | 0 | — |
case-12 | pass→pass | 15,927 | 11,215 | -30% | 1 | 1 | 0% | 2,105 | 2,157 | +2% | 0 | 0 | — |
case-13 | fail→pass | 11,341 | 2,776 | -76% | 1 | 1 | 0% | 1,780 | 1,001 | -44% | 0 | 0 | — |
case-14 | pass→pass | 10,118 | 2,205 | -78% | 1 | 1 | 0% | 1,425 | 1,040 | -27% | 0 | 0 | — |
case-15 | fail→pass | 12,518 | 1,865 | -85% | 1 | 1 | 0% | 1,717 | 888 | -48% | 0 | 0 | — |
case-16 | fail→pass | 11,154 | 2,652 | -76% | 1 | 1 | 0% | 1,920 | 930 | -52% | 0 | 0 | — |
case-17 | fail→pass | 11,369 | 3,957 | -65% | 1 | 1 | 0% | 1,848 | 1,443 | -22% | 0 | 0 | — |
case-18 | pass→pass | 6,096 | 3,540 | -42% | 1 | 1 | 0% | 1,152 | 1,020 | -11% | 0 | 0 | — |
case-19 | fail→pass | 9,849 | 4,946 | -50% | 1 | 1 | 0% | 1,793 | 1,460 | -19% | 0 | 0 | — |
case-20 | fail→fail | 6,090 | 2,820 | -54% | 1 | 1 | 0% | 1,113 | 1,118 | +0% | 0 | 0 | — |
case-21 | fail→fail | 13,794 | 17,457 | +27% | 1 | 1 | 0% | 2,210 | 3,251 | +47% | 0 | 0 | — |
case-22 | fail→fail | 8,216 | 5,107 | -38% | 1 | 1 | 0% | 1,406 | 1,510 | +7% | 0 | 0 | — |
case-23 | fail→fail | 16,874 | 12,232 | -28% | 1 | 1 | 0% | 2,571 | 2,944 | +15% | 0 | 0 | — |
case-24 | fail→pass | 7,156 | 6,955 | -3% | 1 | 1 | 0% | 1,087 | 1,608 | +48% | 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. 24 cases were attempted. The headline lift of +63 percentage points is the difference between those two pass rates over the 24 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.