agentsclimarketplace

Transcribe

Skill yigityildiz0/universal-ai-skill-library/skills/common/transcribe

531 searchable AI Agent Skills for Claude Code, OpenAI Codex, and OpenCode — EN/TR catalog, platform and risk notes, direct ZIPs, and curated bundles.

Install
npx -y skills add yigityildiz0/universal-ai-skill-library --skill transcribe

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

3 things to look at

  • 19 days oldThe repository was created 19 days ago. New is not bad, but a brand new repository carrying a familiar-sounding name is the shape a typosquat arrives in, and there has been no time for anyone else to find a problem with it.
  • no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
  • 1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Transcribe audio or video with an already configured local or approved speech-to-text capability, selecting current supported options from evidence at run.

The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.

SKILL.md

2.0 KB, 352 tokens by cl100k_base, as published. Nobody here has run it

Transcription

Inspect and scope

Record file type, duration, channels, sample rate, language(s), speaker count, noise/music, privacy, desired timestamps, diarization, speaker names, verbatim versus cleaned style, and output format. Preserve the original.

Choose an available path

Use an installed local engine or an already approved/configured API. Verify current supported model IDs, size/duration limits, diarization, prompting, timestamp, and language behavior from installed/current official documentation. Do not hard-code a model, silently upload audio, install dependencies, or spend credits.

For sensitive recordings, prefer local processing. Named-speaker references require consent and must be stored/removed intentionally. Do not infer speaker identity from voice alone.

Process

  • Normalize/convert audio losslessly enough for speech recognition and keep channel information when it helps speaker separation.
  • Chunk long files on silence/overlap boundaries and retain source offsets.
  • Preserve uncertainty with markers rather than inventing words.
  • Use a glossary for verified names/terms; do not let a prompt override the audio.
  • Keep raw, timestamped, and cleaned transcripts separate. Cleaning may fix punctuation/fillers but must not alter facts.

Validate

Spot-check the start, middle, end, speaker transitions, low-confidence segments, names, numbers, dates, negations, and domain terms against audio. Check caption timing/line length when producing SRT/VTT. For important work, report word/error uncertainty or a reviewed-segment list.

Deliverable

Return output paths, engine/provider and configuration source, language, timestamps/diarization choices, coverage, low-confidence markers, whether audio left the device, and deletion/retention status of temporary files.

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Gives 0 of the 12 instructions most video audio skills give in 352 tokens

Counted across 622 of the 795 authors here whose files we hold, read 2026-08-07

  • Read individual rule files for detailed explanationsin 21 of 622, across 10 files
  • Render final videoin 13 of 622, across 6 files
  • Use WAV PCM 16kHz mono audio formatin 12 of 622, across 3 files
  • Use this skill when dealing with Remotion codein 11 of 622, across 4 files
  • Save generated audio to a WAV filein 11 of 622, across 4 files
  • Handle conversion errors gracefullyin 10 of 622, across 6 files
  • Add captions to videos alwaysin 10 of 622, across 4 files
  • Generate music from text descriptions using MusicGenin 9 of 622, across 2 files
  • Do not skip pipeline layersin 9 of 622, across 3 files
  • Do not make one tool do everythingin 9 of 622, across 3 files
  • Use Azure Document Intelligence for complex PDFsin 9 of 622, across 4 files
  • Never ask the user to paste their full API keyin 9 of 622, across 3 files

Said here and by no other author read

  • use an installed local engine or approved API
  • verify supported model IDs and limits from current documentation
  • do not hard-code a model
  • do not install dependencies
  • prefer local processing for sensitive recordings
  • chunk long files on silence or overlap boundaries

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.