{
  "schema_version": 2,
  "kind": "shortening-method",
  "format": "agent-skill",
  "id": "transcript-gist",
  "name": "Transcript gist",
  "category": "Writing",
  "summary": "Extract the editorial substance of a transcript and keep useful source timestamps.",
  "use_cases": [
    "Video transcripts",
    "Podcast transcripts",
    "Recorded talks"
  ],
  "word_count": 122,
  "url": "https://sho.rten.it/methods/transcript-gist/",
  "instructions_url": "https://sho.rten.it/methods/transcript-gist/SKILL.md",
  "skill_url": "https://sho.rten.it/methods/transcript-gist/SKILL.md",
  "json_url": "https://sho.rten.it/methods/transcript-gist/llms.txt",
  "plain_text_url": "https://sho.rten.it/methods/transcript-gist/prompt.txt",
  "license": "MIT",
  "sources_url": "https://sho.rten.it/sources/#transcript-gist",
  "skill_name": "transcript-gist",
  "skill_description": "Extract the editorial substance of a transcript and keep useful source timestamps. Use for Video transcripts, Podcast transcripts, Recorded talks.",
  "agents_md_url": "https://sho.rten.it/methods/transcript-gist/AGENTS.md",
  "sources": [
    {
      "title": "steipete/summarize · Transcript gist",
      "url": "https://github.com/steipete/summarize/blob/41375359bd55da4bdc2e3a861dfd0a0695c1c6af/packages/core/src/prompts/link-summary.ts",
      "repository": "https://github.com/steipete/summarize",
      "revision": "41375359bd55da4bdc2e3a861dfd0a0695c1c6af",
      "path": "packages/core/src/prompts/link-summary.ts",
      "license": "MIT",
      "license_url": "https://github.com/steipete/summarize/blob/41375359bd55da4bdc2e3a861dfd0a0695c1c6af/LICENSE",
      "license_file": "licenses/steipete--summarize.txt",
      "copyright": "Copyright (c) 2026 Peter Steinberger",
      "repository_stars": 6613,
      "checked_at": "2026-09-10",
      "license_scope": "Source is in the repository or package covered by the linked MIT license; no source-file license override was present.",
      "adaptation": "Adapted the transcript audience, source-grounding, structure, sponsor omission, and timestamp rules. Removed CLI configuration, slide markers, social-share ingestion, and hard-coded length presets. Relaxed the source's blanket exclusion of brand names so relevant editorial facts remain; user-directed ad analysis is permitted. Omitted optional quotation requirements to avoid adding excerpts that do not help a short summary."
    }
  ],
  "instructions": "Summarize the supplied transcript for someone deciding whether to watch or listen. Lead with the central point, then group supporting ideas by theme or chronology. Keep concrete findings, qualifications, and disagreements. Use only the available transcript; do not infer missing sections.\n\nOmit sponsor reads, promotions, repeated introductions, and calls to subscribe, unless the user specifically asks to analyze them. Do not spend summary space announcing those omissions. Keep editorial discussion about a company or product when it matters to the topic.\n\nUse short paragraphs or a small set of bullets. If timestamps are supplied, add a brief Key moments list using exact timestamps from the source. Never invent timestamps, reactions, or quotes. Follow the requested length without padding. Return only the summary.",
  "example": {
    "before": "[00:00] Welcome back to the Community Workshop podcast. Please subscribe and tell a friend about the show.\n[00:25] Today we compare the two ways our repair café booked visitors during June: reserved slots and walk-ins. We tried each on one Saturday, with four volunteer repairers at both events.\n[01:40] Reserved slots had a median wait of 12 minutes. Walk-ins had a median wait of 28 minutes. We counted waiting time from arrival until a repairer began.\n[03:10] Six people with reservations did not attend. The walk-in event had no appointments to miss, but three people left before a repairer was free.\n[04:20] Our sponsor has a special offer this week. Use the code in the description.\n[05:05] The weather differed between the Saturdays, and we did not record how difficult the repairs were. We cannot attribute the waiting-time difference to booking format alone.\n[06:15] Next month we plan a mixed format, but the volunteer coordinator has not approved the schedule.",
    "after": "In June, a repair café tested reserved slots and walk-ins on one Saturday each, with four repairers per event. Median arrival-to-repair waits were 12 and 28 minutes respectively. Six reservation holders did not attend; three walk-in visitors left before service. Weather differed and repair difficulty was unrecorded, so the wait difference cannot be attributed to booking format alone. A mixed-format trial is planned for next month; its schedule is unapproved.\n\nKey moments\n- [00:25] Test setup\n- [01:40] Waiting times\n- [03:10] Missed reservations and walk-outs\n- [05:05] Comparison limits\n- [06:15] Proposed next trial",
    "context": "Fictional repair-café podcast transcript",
    "must_preserve": [
      "June comparison: one Saturday per format, four repairers at each event",
      "Median arrival-to-repair waits: 12 minutes reserved, 28 minutes walk-in",
      "Six reservation no-shows; three walk-in departures before service",
      "Different weather and unmeasured repair difficulty prevent attributing the difference to format alone",
      "Next month’s mixed-format plan has no approved schedule",
      "Exact supplied timestamps in the Key moments list"
    ],
    "omitted": [
      "Subscription request and sponsor promotion"
    ],
    "kind": "illustrative"
  }
}