transcript-learn

transcript-learn is a skill for Claude Code from senda-labs/DQIII8. It costs 57 tokens per session (838 once invoked), scanned A, original, MIT.

A tool for extracting structured knowledge from video transcripts, including YouTube videos, courses, seminars, podcasts, and text transcript files. DQ knowledge chunks are reusable pieces of organized information, while skills and agents are saved instructions or roles for AI work.

In plain words
What is it for?
Use it with a YouTube URL or transcript file to extract knowledge, classify its subject area, and convert the results into knowledge chunks, skills, or agent definitions.
Why use it?
It turns long transcripts into organized concepts, methods, tools, data, quotes, and action items. It is only meant to run when the user explicitly asks for it.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: reads .claude/ paths; mentions subagents.

Part of the dqiii8 plugin — 22 skills, 14 commands, 17 agents shipped together

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/senda-labs/dqiii8/transcript-learn
Any agent
npx skills add senda-labs/DQIII8 --skill transcript-learn
Clone the repo
git clone --depth 1 https://github.com/senda-labs/DQIII8

Made for: Claude Code.

Or install dqiii8, the plugin that ships this one along with the rest of its 22 skills, 14 commands, 17 agents.

Wrote 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.

agentmods badge for transcript-learn

README.md
[![agentmods](https://agentmods.dev/badge/skills/senda-labs/dqiii8/transcript-learn.svg)](https://agentmods.dev/skills/senda-labs/dqiii8/transcript-learn)
Your own site
<a href="https://agentmods.dev/skills/senda-labs/dqiii8/transcript-learn"><img src="https://agentmods.dev/badge/skills/senda-labs/dqiii8/transcript-learn.svg" alt="Measured on agentmods" height="20"></a>
Per session 57 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 838 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 5.1 $0.00057 $0.00838
Opus 5 $0.00028 $0.00419
Sonnet 5 $0.00011 $0.00168
Haiku 4.5 $0.00006 $0.00084

Measured 5d ago against content hash 350cde02ae1f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

transcript-learn 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 5d 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.

.claude/skills/transcript-learn/SKILL.md · 105 lines

How it starts

The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/transcript-learn — Video Knowledge Ingestion

Extract structured knowledge from video transcripts and integrate into DQIII8.

Usage

/transcript-learn <youtube-url>
/transcript-learn <path-to-transcript.txt>
/transcript-learn --batch <file-with-urls.txt>

Pipeline

Step 1: Get transcript

  • If YouTube URL: use youtube-transcript MCP tool get_transcript (without timestamps for long videos)
  • If .txt file: read directly
  • If transcript > 25000 tokens: process in a forked subagent to save context

Step 2: Analyze content

Extract from the transcript:

  1. Key concepts — main ideas, definitions, frameworks
  2. Techniques/methods — actionable processes, step-by-step workflows
  3. Tools/technologies — software, libraries, APIs mentioned
  4. Data/metrics — numbers, benchmarks, comparisons
  5. Quotes — notable statements with timestamp if available
  6. Action items — things we could implement in DQ or projects

Step 3: Classify domain

Map content to DQ domain:

  • formal_sciences: math, logic, algorithms, statistics
  • natural_sciences: biology, physics, chemistry, nutrition
  • social_sciences: finance, marketing, law, economics
  • humanities_arts: writing, philosophy, history, design
  • applied_sciences: programming, devops, web dev, AI/ML

Step 4: Generate output

Based on content type, generate ONE OR MORE of:

A) Knowledge chunk (factual knowledge): Save to: knowledge/{domain}/{topic_slug}.md Format: use template .claude/skills/transcript-learn/templates/knowledge_chunk.md

B) Skill proposal (workflow/methodology): Save to: skills-registry/custom/proposed/{skill_name}.md Format: standard SKILL.md with frontmatter Status: PENDING_REVIEW

C) Agent proposal (deep expertise): Save to: .claude/agents/proposed/{agent_name}.md Format: standard agent .md with frontmatter Status: PENDING_REVIEW — user must approve before activation

Step 5: Index

After saving knowledge chunk:

  • Add to the domain's index.json if it exists
  • Print summary of what was generated

Read the full file on GitHub · 105 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. 5d ago First seen · 105 lines · 57 tokens per session scan A 350cde02ae1f

Subscribe to this mod's changes

transcript-learn is a skill published in the GitHub repository senda-labs/DQIII8 (11 stars, last pushed 17d ago), licensed MIT. It adds 57 tokens to every session and 838 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 2026-08-30.

Related

Other skills, from other repositories

continuous-learning

Pattern extraction, confidence-scored evaluation, skill creation, organization, versioning, and cross-project export pipeline.

a5c-ai/babysitter · 25 tokens

continuum-quickstart

Get a Continuum agent up and running — Python 3.13 venv, infra via continuum up, smallest possible BaseAgent + AgentRunner example. Invoke when the user asks "how do I start", "set up Continuum", "run my first agent", or is at the very beginning of a project.

shyftlabs/continuum · 72 tokens

skill-builder

Use when automatically detect source types and build AI skills using Skill Seekers. Use when the user wants to create skills from documentation, repos, PDFs, videos, or other knowledge sources.

oyi77/1ai-skills · 40 tokens

ai-engineering-curriculum

Use when structured AI engineering curriculum — 382 skills + 99 prompts across 20 phases covering ML, deep learning, LLMs, agents, and production systems. Use when learning AI, building AI skills,.

oyi77/1ai-skills · 50 tokens

explain

코드를 비유 기반으로 설명하고 Mermaid 다이어그램을 생성합니다. 파일/기능/줌아웃 3가지 모드 지원. /explain @file.ts (상세 설명), /explain "로그인 기능" (기능 단위), /explain --zoom-out @file.ts (한 단계 위 맵).

Dannykkh/skill-olympus · 76 tokens

book-to-skill

Use when convert technical books and documents (PDF, EPUB, DOCX, HTML, Markdown, RTF, MOBI) into structured agent skills with frameworks, mental models, chapter references, and decision rules. Includes full extraction pipeline. Use when the user wants to turn a book or document collection into a reusable agent skill…

oyi77/1ai-skills · 74 tokens