Podcast Generation
bytedance/deer-flow
Turns written content into a two-host conversational podcast MP3 with a transcript, by drafting a JSON script and running a text-to-speech script.
Builds a short spoken morning news briefing from a few web searches and turns it into one audio clip, on request or on a schedule.
Install Morning News Podcast
$ npx skills add THU-SAGE/syll --skill morning-podcast -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install THU-SAGE/syll morning-podcast --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/THU-SAGE/syll.git skills-src && mkdir -p .claude/skills && cp -r skills-src/syll/skills/morning-podcast .claude/skills/morning-podcast && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "morning-podcast" agent skill from https://github.com/THU-SAGE/syll/tree/main/syll/skills/morning-podcast into .claude/skills/morning-podcast/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "morning-podcast", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/THU-SAGE/syll/tree/main/syll/skills/morning-podcastType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add THU-SAGE/syll --skill morning-podcast -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install THU-SAGE/syll morning-podcast --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/THU-SAGE/syll.git skills-src && mkdir -p .agents/skills && cp -r skills-src/syll/skills/morning-podcast .agents/skills/morning-podcast && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "morning-podcast" agent skill from https://github.com/THU-SAGE/syll/tree/main/syll/skills/morning-podcast into .agents/skills/morning-podcast/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "morning-podcast", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add THU-SAGE/syll --skill morning-podcast -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install THU-SAGE/syll morning-podcast --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/THU-SAGE/syll.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/syll/skills/morning-podcast .cursor/skills/morning-podcast && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "morning-podcast" agent skill from https://github.com/THU-SAGE/syll/tree/main/syll/skills/morning-podcast into .cursor/skills/morning-podcast/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "morning-podcast", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/THU-SAGE/syll.git --path syll/skills/morning-podcast--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add THU-SAGE/syll --skill morning-podcast -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install THU-SAGE/syll morning-podcast --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/THU-SAGE/syll.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/syll/skills/morning-podcast .gemini/skills/morning-podcast && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "morning-podcast" agent skill from https://github.com/THU-SAGE/syll/tree/main/syll/skills/morning-podcast into .gemini/skills/morning-podcast/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "morning-podcast", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install THU-SAGE/syll morning-podcastInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add THU-SAGE/syll --skill morning-podcast -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/THU-SAGE/syll.git skills-src && mkdir -p .github/skills && cp -r skills-src/syll/skills/morning-podcast .github/skills/morning-podcast && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "morning-podcast" agent skill from https://github.com/THU-SAGE/syll/tree/main/syll/skills/morning-podcast into .github/skills/morning-podcast/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "morning-podcast", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add THU-SAGE/syll --skill morning-podcast -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install THU-SAGE/syll morning-podcast --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/THU-SAGE/syll.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/syll/skills/morning-podcast .opencode/skills/morning-podcast && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "morning-podcast" agent skill from https://github.com/THU-SAGE/syll/tree/main/syll/skills/morning-podcast into .opencode/skills/morning-podcast/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "morning-podcast", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
morning-podcast- GitHub stars
- 303
- Token cost
- ~533 tokens
- SKILL.md length
- 267 words
- Files
- 1
- Skills in repo
- 8
- Repo updated
- First seen
- Licence
- MIT
At a glance
Builds a short spoken morning news briefing from a few web searches and turns it into one audio clip, on request or on a schedule.
- Works in 5 steps: Collect stories. Use web_search to… → Summarize in spoken form. For each… → Compose one script. Assemble a single… → …
- Starting the day with a short audio news summary
- SKILL.md covers Steps and Notes
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Gathers three to five stories across tech, world and markets using web search, picks the most substantive ones and drops paywalled or clickbait items. Each story becomes a short spoken-style summary of about 80 to 120 Chinese characters, or around 40 English words, with no markdown and no URLs; outlets are named instead.
The summaries are joined into one script with a greeting that uses the assistant's configured name, short transitions and a sign-off addressed to the user. The speak tool is then called exactly once, because a single call gives better prosody than joined clips. The skill replies with a one-line summary, and the audio travels in the tool result, or as an MP3 attached to a channel message. If speech fails, it falls back to a text briefing and says why.
When your agent uses it
- Starting the day with a short audio news summary
- Scheduling a daily briefing through a cron job
- Delivering a spoken briefing to a chat channel
Example prompts
- “Make me a morning podcast.”
- “Give me today's tech, world and markets news as an audio briefing.”
- “Run the morning podcast and send the MP3 to my chat channel.”
Requirements
- A web_search tool
- A speak text-to-speech tool
Workflow steps
5 steps, taken from the first numbered list in SKILL.md.
- Collect stories. Use web_search to gather 3–5 items across
- Summarize in spoken form. For each story, write ~80–120
- Compose one script. Assemble a single continuous string
- Call speak exactly once with the full script
- Reply briefly. One sentence summarizing what's in the briefing
What it can do on your machine
Read from SKILL.md and the folder at commit 3741347. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Morning News Podcast loads about 533 tokens when it runs. Until then it costs about 20 tokens; SKILL.md has 267 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from THU-SAGE/syll at commit 3741347, republished under its MIT licence (© THU-SAGE). 267 words, ~533 tokens.
Download SKILL.mdSave it as
.claude/skills/morning-podcast/SKILL.md (or your agent's skills folder).- name
- morning-podcast
- description
- Generate a short spoken morning news briefing as an audio clip.
Morning Podcast
Triggered either by the user saying "morning podcast" / "晨间播客" or
by a cron job that runs this skill on a schedule. The output is a
single audio file (via the speak tool) that the web frontend will
auto-render as an <audio> element; if the job is delivering to a
messaging channel, the MP3 travels along the outbound message.
Steps
Collect stories. Use
web_searchto gather 3–5 items across tech, world, and markets. One or two searches is usually enough:web_search(query="今日科技头条", count=5) web_search(query="today world news", count=5)Skim titles/snippets, pick the most substantive stories, and drop anything paywalled or clickbait-y.
Summarize in spoken form. For each story, write ~80–120 Chinese characters (or ~40 English words). No markdown. No URLs in the spoken body — reference the outlet by name instead. Rewrite headlines into natural narration ("今天…", "另一边…").
Compose one script. Assemble a single continuous string:
- Greeting using
{{ghost_name}}, e.g. "{{ghost_name}} 早安播 报，今天是 X 月 Y 日。" - Item 1 → item N with short transitions.
- Sign-off: "以上就是今天的晨间播报，{{user_name}}，祝你有个顺 利的一天。"
- Greeting using
Call
speakexactly once with the full script:speak(text="<full assembled script>")A single call yields the best prosody. Do not call
speakper-item — concatenating multiple clips sounds choppy.Reply briefly. One sentence summarizing what's in the briefing (e.g. "今日播报已生成：科技 / 市场 / 国际 共 4 条"). The audio itself is attached through the tool result's
media— you don't need to repeat the script in the reply.
Notes
- Real tool name is
web_search(notweb.search) andspeak. - If
speakfails, fall back to a text-only briefing and tell the user why ("TTS unavailable: …"). - Never include URLs in the TTS input — Volcengine reads them out character-by-character and it sounds terrible.
© THU-SAGE, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in syll/skills/morning-podcast of THU-SAGE/syll.
Open the folder on GitHubat commit 3741347
Compare with similar skills
Morning News Podcast next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Morning News Podcast this skillTHU-SAGE/syll | 303 | — | ~533 | Automated safety check: Pass | MIT | |
| Podcast Generationbytedance/deer-flow | 84k | 2 repos | ~2.2k | Automated safety check: Pass | MIT | |
| Video Podcast Makerdtsola/xiaoyaosearch | 1k | — | ~3.4k | Automated safety check: Pass | MIT | |
| Podcastzarazhangrui/personalized-podcast | 438 | — | ~2.3k | Automated safety check: Notes | None | |
| Doubao Text-to-Speech Generatorxvirobotics/metabot | 994 | — | ~1.1k | Automated safety check: Notes | MIT | |
| Video Podcast Maker NanoAgents365-ai/video-podcast-maker | 1.7k | — | ~3.6k | Automated safety check: Pass | MIT |
Similar skills
Video Podcast Maker
dtsola/xiaoyaosearch
Turns a topic into a 4K horizontal video podcast through research, scripting, text-to-speech, Remotion rendering and background music, and can learn styles from references.
Podcast
zarazhangrui/personalized-podcast
Generate a podcast episode from content you provide. An agent skill from zarazhangrui/personalized-podcast.
Doubao Text-to-Speech Generator
xvirobotics/metabot
Generates Chinese speech audio from text using Volcengine's Doubao TTS API, for narration, voiceovers or multi-voice podcasts.
Video Podcast Maker Nano
Agents365-ai/video-podcast-maker
Smallest personal narrated-explainer-video pipeline (spoken narration over visuals, not an audio podcast), fully tool-agnostic and autonomous by default — topic → research ∥ asset collection →…
- Official
Azure Realtime Podcast Generation
microsoft/skills
Builds podcast-style audio narration from text with Azure OpenAI's GPT Realtime Mini over WebSocket, from a Python FastAPI backend to a React player.
More from THU-SAGE/syll
All 8 skills in this repoAudition Voice Cleanup
THU-SAGE/syll
Cleans a voice recording by driving Adobe Audition on a macOS host to reduce hiss, hum, background noise and sibilance, after asking for your consent.
File Retrieval
THU-SAGE/syll
Finds a file on the local machine, shows previews of the candidates, and sends the one you pick back through the current chat channel after confirmation.
Photoshop Background Cutout
THU-SAGE/syll
Removes an image background and exports a transparent PNG by driving the real Adobe Photoshop app on a macOS host, after asking your permission to take over the screen.
Desktop GUI Agent
THU-SAGE/syll
Controls desktop applications through screenshots: a vision model reads the screen and returns click, type and scroll actions that pyautogui then performs.
HoYoLAB Check-in Simulator
THU-SAGE/syll
Produces a clearly labeled, research-based stand-in for a Genshin Impact or Honkai: Star Rail daily check-in when no real sign-in can be run.
Local Mail Sim
THU-SAGE/syll
Simulate an overnight local mail summary when there is no real local mailbox integration or recorded GUI workflow available.
Related
Questions about Morning News Podcast
What does Morning News Podcast do?
Builds a short spoken morning news briefing from a few web searches and turns it into one audio clip, on request or on a schedule. Gathers three to five stories across tech, world and markets using web search, picks the most substantive ones and drops paywalled or clickbait items. Each story becomes a short spoken-style summary of about 80 to 120 Chinese characters, or around 40 English words, with no markdown and no URLs; outlets are named instead.
When should I use Morning News Podcast?
Morning News Podcast fits situations like: starting the day with a short audio news summary; scheduling a daily briefing through a cron job; delivering a spoken briefing to a chat channel.
How do I install Morning News Podcast in Claude Code?
Run `npx skills add THU-SAGE/syll --skill morning-podcast -a claude-code`. Or copy the skill folder (syll/skills/morning-podcast in THU-SAGE/syll) into .claude/skills/morning-podcast in your project. Claude Code loads it when a task matches its description.
How do I install Morning News Podcast in Codex?
Run `npx skills add THU-SAGE/syll --skill morning-podcast -a codex`. Or copy the skill folder (syll/skills/morning-podcast in THU-SAGE/syll) into .agents/skills/morning-podcast in your project. Codex loads it when a task matches its description.
Can I use Morning News Podcast in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add THU-SAGE/syll --skill morning-podcast -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/morning-podcast, .gemini/skills/morning-podcast, .github/skills/morning-podcast and .opencode/skills/morning-podcast in your project.
What does Morning News Podcast need to run?
SKILL.md names no scripts, command-line tools or credentials: Morning News Podcast is instructions for the agent only. Our summary lists: A web_search tool; A speak text-to-speech tool.
Does Morning News Podcast access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Morning News Podcast safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Morning News Podcast use?
Morning News Podcast is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Morning News Podcast use?
About 533 tokens (SKILL.md is roughly 2.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Morning News Podcast?
Skills that share tags, products or a category with Morning News Podcast: Podcast Generation (bytedance/deer-flow, 84k stars), Video Podcast Maker (dtsola/xiaoyaosearch, 1k stars), Podcast (zarazhangrui/personalized-podcast, 438 stars) and Doubao Text-to-Speech Generator (xvirobotics/metabot, 994 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Morning News Podcast?
THU-SAGE (a GitHub organization) maintains it in THU-SAGE/syll, which has 303 GitHub stars. The repository holds 8 skills in this directory. The repository was last updated on June 9, 2026.
Source: THU-SAGE/syll on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.