clean-transcript

A transcript-cleaning skill that turns timestamped, fragmented speech into readable Markdown while keeping the spoken words unchanged.

In plain words
What is it for?
Use it on raw video transcripts to create readable prose, optionally adding chapter headings and formatting existing speaker labels.
Why use it?
It removes caption timestamps and noise markers and repairs paragraph structure without manually rewriting the transcript.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/mayank-io/mstack/clean-transcript
Any agent
npx skills add mayank-io/mstack --skill clean-transcript
Clone the repo
git clone --depth 1 https://github.com/mayank-io/mstack

Made for: Claude Code, Codex.

Per session 70 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 996 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00070 $0.00996
Opus 5 $0.00035 $0.00498
Sonnet 5 $0.00014 $0.00199
Haiku 4.5 $0.00007 $0.00100

Measured yesterday against content hash 78a5d9a8ee6f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

clean-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 yesterday.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/clean.py, tests/test_clean.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

plugins/notes/skills/clean-transcript/SKILL.md · 59 lines

How it starts

The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Clean Transcript

Raw transcripts arrive as timestamped fragments — auto-captions split sentences across timed segments and sprinkle [Music] markers through them. This skill merges them into readable prose without changing a single word.

Run the script. Do not clean by hand.

python3 "${CLAUDE_PLUGIN_ROOT}/skills/clean-transcript/scripts/clean.py" \
  RAW.txt OUT.md [META.json] [--speakers "David Puell,Yassine Elmandjra"]
Argument Meaning
RAW.txt raw transcript text — the transcript field from fetch:youtube-transcript, written to a file
OUT.md where the cleaned Markdown goes
META.json (optional) JSON with a chapters array; each entry needs start_time (or seconds) and title
--speakers (optional) comma-separated names whose already-present labels get bolded

It prints segments:, chapters inserted:, chars out: and any corruption warnings to stderr, then OUTPUT_FILE:<path> as the final stdout line. Chain on that line.

Why a script and not instructions: verbatim is a property you can either guarantee or merely request. This script only deletes timestamps and noise markers and inserts whitespace, headings and bold markers — so the output is provably the input's token stream minus deliberate deletions, and tests/test_clean.py::test_verbatim_invariant checks exactly that over a 50k-character fixture. An LLM asked to "clean but stay verbatim" silently fixes grammar, drops filler, and tightens sentences. That has produced bad captures before.

What it does and does not do

Deletes: leading timestamps (mm:ss and hh:mm:ss), and the noise markers [Music] [Applause] [Laughter] [Snorts] [Inaudible] [Silence] [Crosstalk] [Side conversation], case-insensitively.

Inserts: paragraph breaks (at ≥700 characters and a sentence terminator — both required, so a long unpunctuated run stays whole rather than being cut mid-sentence), ## Chapter Title headings, and **Name:** bolding for labels already in the text.

Read the full file on GitHub · 59 lines

Files

What ships with it

2 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.

Changes

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.

  1. yesterday First seen · 59 lines · 70 tokens per session scan A 78a5d9a8ee6f

Subscribe to this mod's changes

clean-transcript is a skill published in the GitHub repository mayank-io/mstack (5 stars, last pushed 7d ago), licensed MIT. It adds 70 tokens to every session and 996 once invoked, about $0.0003 per session on Opus 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 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens