Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

YouTube to Markdown · nicepkg | DecimalAI

documentationby nicepkg

YouTube to Markdown

nicepkg/youtube-to-markdown

Source nicepkg/ai-workflow ↗License MIT

Use when user asks YouTube video extraction, get, fetch, transcripts, subtitles, or captions. Writes video details and transcription into structured markdown file.

SkillScore27Maintained

Automatic

Knowledge Management pack

Last verified 8/24/2026

What it changes

Passed 4 of 13 test cases with the skill, and 2 of 13 without it.

Without skill14%

With skill27%

Checks it passed that the model alone missed

Classifies the content type as TIPS
Enforces a byte budget limit of less than 10 percent of transcript bytes
Uses chapter timestamps from chapters.json as primary break points when present

and 2 more in the full report

3 fixed3 passed either way16 still failing0 broke

Pass-rate lift: +14 pp
Tokens: +34%
Agent turns: 0%
Response time: -59%

Model gemini-3.6-flashMeasured 8/24/2026v16 of 22 cases passed with skill · 13 comparable

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/nicepkg-youtube-to-markdown/SKILL.md https://app.decimal.ai/s/nicepkg-youtube-to-markdown/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add nicepkg-youtube-to-markdown, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/nicepkg-youtube-to-markdown/ and pins it in .decimal/skills.lock

decimalai skills add nicepkg-youtube-to-markdown

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/nicepkg-youtube-to-markdown/SKILL.md https://app.decimal.ai/s/nicepkg-youtube-to-markdown/SKILL.md

Raw file: /s/nicepkg-youtube-to-markdown/SKILL.md ↗ · machine-readable summary at /s/nicepkg-youtube-to-markdown.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 3 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 3

Prompt

I have downloaded `youtube_abc123_transcript.vtt` into `./out_dir` during video processing and need to strip repeating line timestamps into raw text files.

What was checked, without and with the skill
Checked	Without skill	With skill
Executes deduplicate_vtt.py passing the original vtt file, dedup markdown file, and no-timestamp text file paths	Missed	Passed

case-07 · gemini-3.6-flash · 8/24/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md203 linessingle file

YouTube to Markdown

Multiple videos: Process one video at a time, sequentially. Do not run parallel extractions. Execute all steps sequentially without asking for user approval. Use TodoWrite to track progress.

Step 0: Check extracted before

python3 ./check_existing.py "<YOUTUBE_URL>" "<output_directory>"

Integrity check:

If summary_valid: false: Show issues to user, ask "Tiedosto epätäydellinen: [issues]. Prosessoidaanko uudelleen?" If yes, continue to Step 1.
If transcript_valid: false: Ask user, if yes re-run Steps 2-3, 7-9.
If comments_valid: false: Ask user, if yes re-run comment analysis.

If returns exists: true AND all valid fields are true: Read and follow UPDATE_MODE.md for update workflow.

Step 1: Extract data (metadata, description, chapters)

python3 extract_data.py "<YOUTUBE_URL>" "<output_directory>"

Creates: youtube_{VIDEO_ID}metadata.md, youtube{VIDEO_ID}description.md, youtube{VIDEO_ID}_chapters.json

IMPORTANT: If you ask which language transcript to extract then do not translate that language to english and require that subagent do not translate either. Only if the user requests another language that the original then translate.

Step 2: Extract transcript

Primary method (if transcript available)

If video language is en, proceed directly. If non-English, ask user which language to download.

python3 extract_transcript.py "<YOUTUBE_URL>" "<output_directory>" "<LANG_CODE>"

Creates: youtube_{VIDEO_ID}_transcript.vtt

Track record

Benchmark

4 / 13

test cases passed, vs 2 / 13 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

nicepkg / ai-workflow

workflows/video-creator-workflow/.claude/skills/youtube-to-markdown/SKILL.md

View on GitHub ↗

License MITImported 8/3/2026Version v1

More skills from the same source and nearby in the registry, with their headline benchmark lift.

Ready to supercharge your AI agents?

See it in action

What's inside

YouTube to Markdown

Step 0: Check extracted before

Step 1: Extract data (metadata, description, chapters)

Step 2: Extract transcript

Primary method (if transcript available)

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills