Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add johnqtcg/awesome-skills --skill local-transcriptgit clone --depth 1 https://github.com/johnqtcg/awesome-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/johnqtcg/awesome-skills/local-transcript)<a href="https://agentmods.dev/skills/johnqtcg/awesome-skills/local-transcript"><img src="https://agentmods.dev/badge/skills/johnqtcg/awesome-skills/local-transcript/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/johnqtcg/awesome-skills/local-transcript"><img src="https://agentmods.dev/badge/skills/johnqtcg/awesome-skills/local-transcript.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00139 | $0.04161 |
| Opus 5.5 | $0.00056 | $0.01664 |
| Sonnet 5.5 | $0.00028 | $0.00832 |
| Haiku 4.5 | $0.00014 | $0.00416 |
Grade A, and why
local-transcript scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 312 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Local Transcript
Overview
Use this skill to turn a local media file into cleaned final transcript files in .txt, .pdf, or .docx format. Extract audio with ffmpeg, transcribe with mlx-whisper (Apple Silicon GPU) or faster-whisper (CPU fallback), then clean the transcript with deterministic replacements for known ASR bugs. LLM contextual proofreading is an opt-in second layer (--llm-backend local|claude) — see §LLM Proofreading Is Opt-In for why it is not the default.
Workflow
- Validate the input path.
- Confirm the requested output format.
- Check dependencies.
- Resolve the ASR mode:
fast,balanced, oraccurate. - Reuse cached audio/raw transcript/clean transcript layers when available.
- Extract or reuse 16 kHz mono WAV audio.
- Transcribe with the selected ASR backend (language auto-detected or user-specified via
--language). - Clean the transcript: simplified Chinese → deterministic replacements → (opt-in) LLM proofreading → post-LLM safety replacements.
- Paragraphize and write the requested final file(s).
Format Resolution Gate
- If the user explicitly requests
txt,pdf, orword/docx, use that format directly. - If the user requests multiple formats, generate all requested formats from the same cleaned transcript.
- If the user asks to transcribe a file but does not specify an output format, ask a short follow-up question before execution:
Which output format do you want: txt, pdf, or docx? - Do not guess the output format from context alone when the user did not say.
Dependency Gate
Before running, verify:
ffmpeg- local Python execution for
scripts/local_transcript.pyThis is an Apple-Silicon-first tool. Say so rather than presenting the fallbacks as an equivalent path — they are usable, not seamless.
| Platform | ASR | LLM proofreading | Chinese PDF |
|---|---|---|---|
| Apple Silicon | mlx-whisper (GPU/ANE), default |
mlx-lm + Qwen2.5, opt-in, no API key |
macOS system CJK fonts found automatically |
| Intel Mac / Linux / Windows | --backend faster-whisper (CPU, markedly slower) |
only --llm-backend claude (needs the claude CLI); local requires MLX |
must install a CJK font; the built-in candidates are macOS paths |
What ships with it
7 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- scripts/local_transcript.py 63 KB runs code
- scripts/make_reference_corpus.py 7.2 KB runs code
- scripts/run_quality_eval.py 18 KB runs code
- scripts/run_regression.sh 255 B runs code
- scripts/tests/stub_transcriber.py 1.4 KB runs code
- scripts/tests/test_local_transcript.py 50 KB runs code
- scripts/zh_replacements.json 605 B
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 312 lines · 139 tokens per session scan A afe15596e24c
local-transcript is a skill published in the GitHub repository johnqtcg/awesome-skills (30 stars, last pushed 18d ago), licensed MIT. It adds 139 tokens to every session and 4,161 once invoked, about $0.0006 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
pptx-translator
This skill should be used when the user needs to translate PowerPoint presentations (.pptx) between languages, preserving formatting and layout. Supports parallel slide-by-slide translation with per-slide validation and retry. Default languages are Portuguese and English but any language pair is supported.
document-converter
This skill should be used when the user needs to convert documents between formats (Office to PDF, PDF to images, image to PDF), perform PDF operations (merge, split, rotate, encrypt, decrypt), or run OCR on scanned documents. Uses local free tools — LibreOffice, ghostscript, pdftk, tesseract, and imagemagick — with…
summarize
Summarize or extract text/transcripts from URLs, podcasts, and local files (great fallback for “transcribe this YouTube/video”).
contract-generator
Draft professional legal contracts — NDAs, service agreements, employment contracts, and SaaS terms with customizable clauses.
docx
Create, read, edit, and manipulate Word .docx files with full formatting — tables of contents, headings, page numbers, letterheads, tracked changes.
epub-creator
Package text and images into valid ePub 3 e-books — chapters, TOC, cover images, and metadata for Kindle and Apple Books.