AI Skill MartBrowse skillsPromptsProgramsLearnWhat is a Skill?
 
← Back to list

codeck Speech Track Generator

Turns a codeck deck into a word-for-word presenter script with stage directions and fragment-synced speaker notes.

Docs & OfficeIntermediate★ 199⑂ 19AI score 7/10Last updated: Aug 8, 2026

What it does

  • Reads deck.md, the latest slide HTML, and project memory inside the codeck deck directory, then writes a slide-by-slide script to speech.md.
  • Asks about speech style (TED / Formal / Casual) and duration (5 / 15 / 30+ min) only once, and only when that info is missing.
  • Inserts stage directions such as [pause 2s], [slow down], [look at audience] in the same language as the transcript.
  • Builds a fragment map from data-f elements, splits the script per reveal step, and writes each segment into HTML data-notes so speaker mode (press P) shows exactly the next line.
  • Produces a per-slide word/time budget table and trims over-budget sections automatically.

Who it's for

  • People already building decks with the codeck plugin.
  • Speakers who want a ready-to-read transcript that fits a time limit.
  • Presenters who want speaking rhythm matched to animation rhythm.

Examples

  1. After /codeck builds a 15-slide deck, invoke this lane to get a 15-minute TED-style speech.md with pause cues.
  2. For a technical talk it picks the Feynman coach persona and rewrites hard concepts as analogies.
  3. A slide with three fragments becomes four script blocks ([on enter] + fragments 1–3) embedded into data-notes, so each arrow press reveals the matching line.

· · · Install guide · · ·

Try it now, no install

Paste this into Claude to use the skill without installing anything.

Read the instructions in this file and follow them to help me:
https://raw.githubusercontent.com/hiyeshu/codeck/HEAD/skills/codeck-speech/SKILL.md

What I want: (describe your task here)

If Claude can't open the link, open it yourself and paste the contents instead.

↓ If it works for you, download the ZIP below and install it. Then it runs on its own — no pasting each time.

Install in the Claude app (no terminal)
  1. Download the ZIP with the button below.
  2. In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
  3. Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
↓ Download ZIP
Install in Claude Code

Let Claude do it — paste this into Claude Code

Install the skill I found on AI Skill Mart.
Copy the skills/codeck-speech folder from the GitHub repo hiyeshu/codeck into my ~/.claude/skills/codeck-speech/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

git clone https://github.com/hiyeshu/codeck.git /tmp/codeck && mkdir -p ~/.claude/skills && cp -r /tmp/codeck/skills/* ~/.claude/skills/

⚠ This is a third-party skill. Check the source repository before installing.

  1. Open a terminal.
  2. Clone the repo: git clone https://github.com/hiyeshu/codeck.git /tmp/codeck
  3. Create the skills folder: mkdir -p ~/.claude/skills
  4. This module depends on the main codeck scripts, so copy all skills: cp -r /tmp/codeck/skills/* ~/.claude/skills/
  5. Restart Claude Code and cd into the project folder for your deck.
  6. Run /codeck first to create the deck state, then ask for a presenter script to trigger the codeck-speech lane.
  7. If the scripts aren't auto-detected, set export CODECK_SKILL_DIR=~/.claude/skills/codeck.
View source on GitHub ↗License: MIT