Tapestry Skills
Seven Claude Code skills: turn a video, article or PDF link into text and an action plan, plus a Scrum coach, a session log and an unblock helper
- 560 ★ on the repository
- Last commit
- MIT
Extended access
Why this level
- The youtube-transcript skill installs yt-dlp through Homebrew, apt or pip
- The skills download pages and videos from links and write files to the working folder
- Session-log reads the whole conversation and writes its summary to a file
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add skills/tapestry-skillsDetects the agents on your machine, shows the access level and pins the version.
Other ways to install
Access and checks
How we reviewExtended accessThe tool runs code or makes network calls and only reads external data.
- The youtube-transcript skill installs yt-dlp through Homebrew, apt or pip
- The skills download pages and videos from links and write files to the working folder
- Session-log reads the whole conversation and writes its summary to a file
This is third-party code. Review the repository files before installing.
What it does
The main skill, learn-this, takes a link, detects the material type (YouTube video, article or PDF), extracts the text and turns it into a five-rep plan with the Ship-Learn-Next method. Both files are saved, and at the end the agent asks when you will ship the first rep. You trigger it with phrases like learn-this, weave or make this actionable followed by a link. The same work is available in parts. The youtube-transcript skill downloads subtitles through yt-dlp, removes duplicate lines, names the file after the video title and offers Whisper transcription when no subtitles exist. Article-extractor strips ads and navigation using Mozilla Readability or trafilatura and saves plain text. The other three skills are not tied to links. Scrum-sage coaches on sprints, backlog, impediments and retrospectives. Session-log appends a session summary to a weekly log file. Unblock-action turns a vague task into a concrete deliverable for the day and a first physical action with two or three questions.
Who it is for. For people who learn from videos and articles and want a working plan out of them, and for team leads and Scrum masters.
Good fit when
- You have a long YouTube lecture and want a clean, deduplicated transcript in a file named after the video
- You want to save an article as plain text without ads and navigation
- You want five short reps with reflection questions out of a tutorial
- A team keeps missing sprint goals and needs impediments and anti-patterns analyzed
- A task is stuck and you need a day-sized deliverable and a first step
Not a fit when
- You want an MCP server that hands transcripts to the agent without saving files: this skill runs yt-dlp
- The pages sit behind a login or paywall: the extractor works with openly available text
- You need SAFe scaling: scrum-sage advises Scrum@Scale and does not recommend SAFe
- Your machine cannot install yt-dlp: the skill installs it through Homebrew, apt or pip
Example request
learn-this https://www.youtube.com/watch?v=VIDEO_IDLimitations
The youtube-transcript skill installs yt-dlp itself through Homebrew, apt or pip. Transcribing videos without subtitles needs Whisper (pip3 install openai-whisper). Article-extractor uses reader (npm install -g reader-cli) or trafilatura and falls back to a less accurate method without them. Results are saved as files in the current folder. The descriptions and instructions are in English. For PDFs, learn-this downloads the file and extracts the text.
How to disable. Delete the skill folders from ~/.claude/skills (or the project's .claude/skills): learn-this, youtube-transcript, article-extractor, ship-learn-next, scrum-sage, session-log, unblock-action.
FAQ
How do I turn a YouTube video into a plan with Claude Code?
Say learn-this and give the link. The skill downloads the subtitles, removes duplicates and builds a five-rep Ship-Learn-Next plan with reflection questions, saving the text and the plan in two files.
What if the video has no subtitles?
The youtube-transcript skill offers Whisper transcription. You install it separately with pip3 install openai-whisper.
How is ship-learn-next different from learn-this?
Ship-learn-next turns text you already have, such as a transcript, into a five-rep plan. Learn-this detects the link type, extracts the content and calls ship-learn-next.
What does session-log write?
It reviews the conversation, finds topics, decisions and reusable outputs and appends them to a YYYY-wWW agent-log.md file without erasing earlier entries. New entries go on top.
How does unblock-action work?
The skill asks no more than two or three questions, clarifies the output, scopes it to one day and names the first physical action. The result is a card with the deliverable, scope and next step.
Discussion
No questions or reviews yet.
Related
SkillsA set of 13 SKILL.md skills: research, a product doc, decks, articles and audits for any compatible agent
A set of everyday agent skills: web search, browser automation, Gmail, Google Calendar and Drive, speech transcription and YouTube transcripts
A library of 229 skills for work and life: sales, marketing, finance, engineering, design and parallel agent runs
The author's personal skills for reading papers and books, dissecting concepts, writing and PNG cards; instructions in Chinese, installed via skills CLI
Lenny's Product Skills
Lenny's Product Skills for Claude Code
A set of product skills for Claude Code and SKILL.md agents: strategy, discovery, launch, growth and team work
Skills that turn a coding agent's output into plain language: honest reports, straight verdicts, followable steps
Comparison with similar tools
Entries that share the main search query, and how they differ.
| Entry | Official | Authentication | Repository stars | Main difference |
|---|---|---|---|---|
| Tapestry Skills (this entry) | no | 560 | ||
| YouTube Fetcher to Markdown | no | 495 | only the YouTube transcript and metadata in Markdown, with no action plan | |
| YouTube Transcript MCP Server | no | not required | 491 | an MCP server that hands transcripts to the agent directly |
README in short
A table at the top lists the seven skills with their benefit. Each is then described with features and example phrases, followed by installation with install.sh or by copying folders, requirements and worked examples. MIT license.
README badge
Original SKILL.md
--- name: learn-this description: Unified content extraction and action planning. Use when user says "learn-this <URL>", "learn this <URL>", "weave <URL>", "help me plan <URL>", "extract and plan <URL>", "make this actionable <URL>", or similar phrases indicating they want to extract content and create an action plan. Automatically detects content type (YouTube video, article, PDF) and processes accordingly. allowed-tools: Bash,Read,Write --- # Tapestry: Unified Content Extraction + Action Planning This is the **master skill** that orchestrates the entire Tapestry workflow: 1. Detect content type from URL 2. Extract content using appropriate skill 3. Automatically create a Ship-Learn-Next action plan ## When to Use This Skill Activate when the user: - Says "learn-this [URL]" or "learn this [URL]" - Says "weave [URL]" - Says "help me plan [URL]" - Says "extract and plan [URL]" - Says "make this actionable [URL]" - Says "turn [URL] into a plan" - Provides a URL and asks to "learn and implement from this" - Wants the full Tapestry workflow (extract → plan) **Keywords to watch for**: learn-this, learn this, weave, plan, actionable, extract and plan, make a plan, turn into action ## How It Works ### Complete Workflow: 1. **Detect URL type** (YouTube, article, PDF) 2. **Extract content** using appropriate skill: - YouTube → youtube-transcript skill - Article → article-extractor skill - PDF → download and extract text 3. **Create action plan** using ship-learn-next skill 4. **Save both** content file and plan file 5. **Present summary** to user ## URL Detection Logic ### YouTube Videos **Patterns to detect:** - `youtube.com/watch?v=`