vietnamese-transcript-cleaner SKILL.md skillA
vietnamese-transcript-cleaner from ducdg88/ducpt-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add ducdg88/ducpt-skills/vietnamese-transcript-cleaner@v1.0.0Pins v1.0.0 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- ducdg88/ducpt-skills
- Path
skills/vietnamese-transcript-cleaner/SKILL.md- Versions recorded
- 1
- Latest version
- v1.0.0, committed Sep 26, 2026
- Size
- 3,529 bytes
- Repository stars
- 8
- License
- MIT
Clean raw Vietnamese speech-to-text output (Whisper, YouTube auto captions, Zoom, Google Meet, SRT or VTT files) into readable text. Restores missing diacritics and punctuation, merges broken caption lines into paragraphs, labels speakers, keeps timestamps, then writes a summary, key decisions and action items. Use when the user shares a transcript, subtitle file, meeting recording notes, "bản ghi", "phụ đề", "bóc băng", "gỡ băng", "chép lời", "tóm tắt cuộc họp", or asks to fix Vietnamese text…
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Vietnamese Transcript Cleaner Raw Vietnamese captions are hard to read: lines break mid sentence, diacritics are missing, names are misheard and there is no punctuation. This skill turns them into a clean document plus a useful summary. ## Step 1. Normalize the file If the input is an `.srt` or `.vtt` file, run the bundled script first. It strips numbering and cue timing, merges short cues into paragraphs and keeps one timestamp per paragraph: ```bash python scripts/clean_subs.py input.srt > merged.txt python scripts/clean_subs.py input.vtt --gap 2.5 --max-chars 600 > merged.txt ``` `--gap` starts a new paragraph when the silence between cues is longer than N seconds (default 2.0). If the input is plain text, skip this step. ## Step 2. Clean the language (work paragraph by paragraph) 1. Restore diacritics only when the intended word is unambiguous from context. If two readings are plausible (for example "ban" could be "bạn", "bán" or "bàn"), pick the one that fits the sentence and mark truly unclear spots with `[?]`. 2. Add punctuation and capitalization. Vietnamese sentences in speech are long; split at natural pauses. …
Read the whole file at its exact version.
How to install
mdr add ducdg88/ducpt-skills/vietnamese-transcript-cleaner@sha256:02ff425004559ed9The line at the top of this page pins the label v1.0.0, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_v6yy3vweb7gm5hsk)
3 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 1 version of this file, committed on Sep 26, 2026.
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (3529 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
ducdg88/ducpt-skills · 8 stars · license MIT · pushed 2026-10-23 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_v6yy3vweb7gm5hsk GET https://markdownregistry.com/api/v1/resolve?ref=ducdg88/ducpt-skills/vietnamese-transcript-cleaner GET https://markdownregistry.com/api/v1/blob/02ff425004559ed9039824f0b9effea47c44c9b1b68efd43b3c3e80507d628ed
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.