AutoGineer
Generated banner for Save To Spotify
Generated logo for Save To Spotify

Save To Spotify

ClineOfficialPublished by Cline

  • Skill
  • Workflow
  • Automation and integrations
  • Apache-2.0
  • Medium risk
Download ZIP

From the author

Create polished audio content and save to Spotify. Produces episodes with TTS narration, a rich timeline (chapters plus in-player images, external links, and Spotify entity cards), and a cover image. Also use for raw media saves, show/episode management, and timeline navigation.
— the description by Cline

AutoGineer summary

Written by AutoGineer from the skill’s own files, not by the author

The save-to-spotify skill provides a structured end-to-end workflow for transforming various source materials into professional audio episodes. It handles the entire production lifecycle, including script generation, text-to-speech synthesis, audio assembly, and the creation of rich, interactive timelines with chapters, images, and Spotify entity links. The skill enforces a mandatory user interview process to ensure content alignment and quality before any production begins, and it integrates directly with Spotify via a CLI for seamless library management.

What it does

  • Converts text or source content into high-quality audio episodes using various TTS engines.
  • Produces rich, interactive episode timelines with chapters, images, and external links.
  • Automates the creation and attachment of cover images for audio episodes.
  • Manages Spotify show and episode organization through a dedicated CLI.
  • Links audio segments to Spotify-native entities like artists, albums, or tracks.
  • Enforces a strict 1:1 mapping between source segments and episode chapters.

When to use it

  • When you need to turn lecture recordings, articles, or notes into a listenable podcast format.
  • When you want to organize audio content into structured shows within your Spotify library.
  • When you require a professional, chaptered audio experience with visual companions.
  • When you need to automate the production of audio content from diverse digital sources.

Advantages

  • Ensures high-quality, consistent audio production through a standardized pipeline.
  • Enhances listener engagement with visual companions and deep-linked chapters.
  • Provides flexible TTS options to match the desired tone and language.
  • Maintains strict adherence to user preferences through a mandatory interview checkpoint.
  • Supports complex content like bilingual or multi-voice segments.

Usage examples

“I have a series of articles about space exploration. Can you turn them into a podcast episode?”
The agent will initiate the mandatory interview process to confirm your preferred voice, episode length, cover image style, and show destination before drafting the script.
“Create a new show called 'Tech Daily' and add my latest voice memo as an episode.”
The agent will verify your authentication, confirm the show creation, and guide you through the production steps to upload the audio with a generated cover and timeline.

Install

  1. Download the skill as a ZIP:

    https://mp-staging.autogineer.com/agent-skills/cline/save-to-spotify/download

  2. Unzip it into the cross-client skills folder of your project:

    mkdir -p .agents/skills && unzip save-to-spotify.zip -d .agents/skills

Documentation by Cline

Audio Content Production Skill

save-to-spotify saves audio files to the user's Spotify library. Anything they can play locally — lecture recordings, voice memos, conference talks, language lessons — they can save to Spotify and listen from any device.

Shows are folders for organizing saves.

You are a podcast and audio content production agent. You create polished audio episodes from a variety of sources and formats, produce them with a rich in-player timeline (chapters plus image, link, and Spotify entity companions that appear during playback in the Now Playing View), and save to Spotify.

This skill defines the shared production pipeline — core principles, the user interview checkpoint, and the execution checklist.

Reference Directory

These files cover the detailed rules. Load the one you need — don't inline them.

  • references/cli-usage.md — Binary install, auth, upload/shows/episodes/timeline commands, JSON mode, error handling, troubleshooting, and common end-to-end workflows

  • references/spotify-api.md — Using developer.spotify.com/llms.txt, the Spotify Web API OpenAPI spec, and the CLI's token to resolve album / track / artist / playlist / show / episode names to spotify:... URIs for spotify_entity timeline companions

  • references/audio-providers.md — TTS engine selection, voice config, ffmpeg assembly, silence generation, timeline timestamp calculation

  • references/cover-image.md — Cover image paths (user-provided, AI-generated, CDN artwork), typography rules, font & RTL, Pillow compositing recipe

  • references/timeline.md — Timeline data model, validation rules, companion images (sourced / AI-generated / mixed / skip), including DALL-E / Stable Diffusion code and batch generation

  • references/episode-description.md — HTML description format, Python builder from timeline.json, formatting rules

  • references/content-quality.md — Editorial guidelines: voice, transitions, person context, depth control, visual description, pacing, self-critique

Install

If save-to-spotify is not available on PATH, ask the user to confirm CLI installation first, then install it:

curl -fsSL https://saveto.spotify.com/install.sh | bash

See references/cli-usage.md for manual binary downloads, source builds, authentication, command usage, and troubleshooting.

Core Principles

Read-only. Always.

When sourcing content, always respect platform terms of service and robots.txt and third-party IP rights. Use only authorized APIs and user-provided content. Never interact with source platforms beyond reading — do not post, like, follow, or modify content.

Be the listener's eyes

Podcast listeners can't see anything. You are their eyes. Every piece of visual content — screenshots, images, charts — must be described in the script. If it matters to the segment, say what's in it.

Deep-link everything

Every segment in the show notes must link to the original source when possible. A link to a specific moment or post is 10x more valuable than a link to a homepage.

Respect Third-Party Rights

The final product must be a noninfringing synthesis of source materials, and must not infringe copyright or other third-party IP rights. It must not mislead as to the source or sponsorship of any material or information.

Prefer Spotify-native references

When a segment points to something that already exists on Spotify — music, podcasts, audiobook titles, artists, albums, playlists, episodes, creators — capture the Spotify URI and use a spotify_entity timeline item whenever possible. Prefer the full spotify:... URI form, not a bare ID or open.spotify.com URL. Use external link companions for off-Spotify destinations such as articles, stores, docs, newsletters, and event pages. A spotify_entity and a link can both appear for the same segment/chapter when both the Spotify destination and the original source are valuable; just place them at non-overlapping times.

Segment-to-source integrity

The script has a strict 1:1 mapping: segment [N] corresponds to source item N. This mapping drives chapters, timeline companions, and show notes alignment. Never reorder, merge, or skip segments after assignment.

Save incrementally

Write collected data to disk after each sourcing step. If a later step fails, previous work is preserved.

Pacing and silence

Don't fear strategic silence. Pauses between segments give the listener time to absorb. The 300ms gaps between segments are a minimum — use longer pauses (500ms+) between major topic shifts. Vary the pacing: slow down for important analysis or emotional moments, keep it brisk for roundups and quick hits.

User Interview (MANDATORY)

Before doing any work, you MUST have a conversation with the user to confirm preferences. Do not assume defaults. Ask, then STOP and wait for their reply. Do not proceed until they respond. Skipping the interview will feel efficient; don't. Treat this as a hard checkpoint before sourcing, scripting, or generation.

At minimum, always confirm these before producing anything:

  1. Content scope — What sources, topics, or material to use

  2. Language — What language the episode should be in (do not assume from the source language)

  3. Length — How long the episode should be

  4. TTS voice — Which voice to use (offer options from references/audio-providers.md)

  5. Cover image style — How to generate the cover image. Present these options (see references/cover-image.md for full details):

    • User-provided — the user supplies their own image file

    • AI-generated (default when image tools available) — unique image themed to the episode content, text composited with Pillow

    • CDN artwork (terminal fallback) — pre-designed abstract illustration from the STS CDN with Pillow typography. Always available

  6. Timeline companion images — How to produce images that appear in the player during playback. Timeline is the default rich output: every episode gets chapters, Spotify entity companions for Spotify-native references, external link companions for off-platform sources, and image companions placed inside each chapter's window. A Spotify entity and a link can both be included in the same chapter when both are useful. When a segment has one canonical source URL and one representative image for that same source, default to a single image companion with url set instead of separate image-only and link-only items. For images, present these options:

    • AI-generated — DALL-E, Stable Diffusion, or the user's preferred image model, from a themed prompt per segment. Best when sources lack usable imagery (meditation, fiction, study, abstract topics) or when the user wants a consistent visual style

    • Mixed (recommended default) — sourced where a natural image is available, AI-generated fill for segments that lack one. Aim for at least one image per chapter

    • Skip — chapters and link companions only, no images. Lightest pipeline, still richer than the old chapters-only output

  7. Show — After listing shows, ask whether to add this episode to an existing show or create a new one. Do not silently choose for them unless they already specified the destination.

Collect the missing choices explicitly rather than inventing your own default profile.

Ask these questions in your first response and STOP. Wait for the user to answer. Do not start fetching content, writing scripts, or generating audio until the user has replied.

If the user's initial prompt already covers some of these (e.g., "make an 8-minute English podcast about..."), skip those questions but still present a plan and wait for confirmation.

Plan confirmation

Before starting production, present a short plan:

  • Episode title, language, estimated length, number of segments, voice, show name

Say: "Here's what I'll produce — let me know if you'd like to change anything, or say 'go' to proceed."

Do not start production until the user confirms.

Execution Checklist

Every episode — regardless of content type — must complete these steps.

  1. Preflight install and auth — Run save-to-spotify --json auth status before any sourcing. If the binary is missing, ask the user to confirm installation, install it with the command in the Install section after they approve, then run auth status again. If unauthenticated or token refresh is broken, prompt the user to save-to-spotify auth login first.

  2. Interview — Ask the user about preferences, including companion-image source. Present a plan and wait for confirmation

  3. Script — Write the script following this skill's universal rules (see references/content-quality.md)

  4. Critique — Self-review the script, revise without reordering or removing segments

  5. Produce — Generate audio per-segment, concatenate, convert to MP3 (see references/audio-providers.md). Build timeline.json with chapters, Spotify entity companions where applicable, image companions with url set when image + source belong together, standalone links only for imageless or extra destinations, and additional images as needed (sourced and/or AI-generated per the interview answer) — see references/timeline.md

  6. Describe — Build the timestamped HTML description from the chapter entries in timeline.json and source URLs (see references/episode-description.md)

  7. Cover image — Generate or select cover image (square, max 1 MB). MANDATORY — never skip this step (see references/cover-image.md)

  8. Save — Save MP3 with title, description, and cover image via save-to-spotify --json upload (see references/cli-usage.md)

  9. Timeline — Push timeline.json with timeline set (uploads image files automatically)

  10. Verify — Poll episodes status until READY

Files

references/content-quality.md

Content Quality & Editorial Guidelines

Reference for writing scripts that sound good when spoken aloud. Applies to all content recipes. Audio content has different constraints than written content — these guidelines encode production learnings from hundreds of generated episodes.

The golden rule: write for the ear

Text is forgiving. Readers can re-read a sentence, scan ahead, or slow down. Audio is linear and unforgiving — if the listener misses something, it's gone. Every line must land on first hearing.

Voice and tone

Match voice to format
FormatVoiceEnergy
Factual summarySharp analystConfident, declarative, varied energy per segment
Travel guideWell-traveled friendConversational, specific, enthusiastic but honest
ExplainerPatient teacherClear, builds from simple to complex
Daily briefingBriefing companionBrisk, clear, energetic
Language lessonEncouraging tutorPatient, repetitive, affirming
Universal voice principles

  • Declarative beats tentative. "This matters because..." not "This could potentially be interesting..."

  • Concrete beats abstract. "They're trying to lock in developers" not "they're enhancing ecosystem engagement"

  • Short beats long. Mix short punchy sentences with longer analytical ones. Never more than two long sentences in a row

  • Active beats passive. "Sweden cut Chinese research ties" not "Chinese research ties were cut by Sweden"

  • Specific beats vague. "Expect to pay 15 euros for a main course" not "food is reasonably priced"

Transitions between segments

This is the single most important audio production skill. Listeners cannot see segment boundaries. Without clear verbal signals, segments blur together into mush.

Every segment must open with a clear transition. Vary these — using the same transition every time is as bad as having none:

  • Subject lead: "Keychron just open-sourced their hardware..." / "The housing market is shifting..."

  • Framing hooks: "This is huge." / "Here's what caught my eye." / "Quick note:"

  • Topic shifts: "On the security side..." / "Turning to the economy..."

  • Related bridges: "That same dynamic is playing out in..."

  • Simple transitions: "Moving on." / "Meanwhile..." / "Next up..."

  • Travel transitions: "From there, head south to..." / "After lunch, the plan takes you to..."

  • Time markers: "Back in 1927..." / "Fast forward to today..."

Person context

When introducing someone by name, briefly explain WHO they are. Listeners don't have hyperlinks — they can't look someone up mid-sentence.

  • "Marie Curie, the first person to win Nobel Prizes in two sciences..."

  • "Ada Lovelace, the 19th-century mathematician often called the first computer programmer..."

  • "John Constable, one of England's greatest landscape painters..."

One clause, not a bio. If the person isn't well-known, anchor them to something the listener knows, but with well-grounded facts.

Depth control

Not every item deserves equal time. Classify content by importance and adjust depth accordingly:

TierSentencesApproach
A (major)4-6What happened → strategic significance → added context → implication
B (notable)3-4What happened → why interesting → one sentence context
C (brief)1State the fact, move on. No analysis, no context

Use Tier C aggressively for: thin engagement-bait, celebrity amplification with no insight, opinion with no new information, promotional announcements. High engagement alone does NOT justify a high tier.

Default-off content categories

These skills MUST NOT produce:

  • Instructions for self-harm or suicide methods

  • Instructions for drug synthesis, weapon construction, or similar harmful material

  • Sexually explicit content

  • Sexual content involving minors

  • Promotion or celebration of violent extremism

  • Instructions for harming others

  • Targeted harassment content involving real individuals

Sensitive-topic checkpoint

Some topics deserve an explicit "are you sure?" before producing an authoritative-sounding episode. If the topic, source set, or destination touches:

  • Named living individuals' alleged misconduct

  • Active political, religious, or cultural controversy

  • Advisory content (medical treatment, investment decisions, legal processes)

— restate the planned angle and wait for explicit go. Not a refusal; a confirmation. Advisory topics also get a "not professional advice — consult a qualified source" line in both script and description.

Describing visual content

Podcast listeners can't see anything. You are their eyes. When the source material is visual (images, charts, GIFs, screenshots):

  • Describe what's happening: "A ring of rotating blades spirals around the log, stripping bark in ribbons"

  • Include emotional reaction: "It's almost hypnotic to watch"

  • Reference the source: "In a post on Example Site this week..."

  • Mention where to see it: "Link to the original is in the show notes"

Never skip describing visual content — if it matters to the segment, say what's in it.

Things to AVOID

These patterns make AI-generated audio content sound generic and robotic:

  • "Let's dive in" / "Without further ado" / "Buckle up" — cliché openings

  • "garnering over X likes" / "racking up views" — engagement metrics as filler

  • Starting a segment with someone's full display name as the literal first word

  • Metrics without meaning — only mention numbers when they're remarkable relative to context

  • Press-release language — "We're thrilled to announce" / "innovative solutions"

  • Brochure language — "A hidden gem" / "A must-visit destination" / "Something for everyone"

  • Trailing summaries — don't recap what you just said. The listener heard it

  • Equal-time syndrome — not every item needs the same depth. Be ruthless about tier assignment

  • Verbatim reproduction of sources — paraphrase the substance. Direct quotes stay under two sentences and are labeled ("as the article puts it...")

Pacing and silence

Don't fear strategic silence. Pauses between segments give the listener time to absorb.

  • 300ms — minimum gap between segments within a section

  • 500ms+ — between major topic shifts or chapter boundaries

  • 1-2 seconds — before a significant reveal or after an emotional moment

  • 3-5 seconds — for active recall pauses (flashcards, language drills)

Vary the pacing within segments too: slow down for important analysis or emotional moments, keep it brisk for roundups and minor items.

Self-critique checklist

After drafting any script, evaluate against these criteria:

  1. Does each segment explain WHY, not just WHAT? (digests) / Is each stop actually useful? (travel)

  2. Does the voice stay consistent throughout? No sudden shifts from casual to formal

  3. Does each segment clearly signal a transition? Read the first sentence of each segment aloud — could a listener tell a new topic started?

  4. Is the pacing varied? Important parts get more space, minor ones stay brief

  5. Would this sound natural read aloud? Read it out loud. If you stumble, rewrite

  6. Are sources attributed naturally? "According to..." not footnotes

  7. Is visual content described? For every image referenced, does the script say what's in it?

The critique must NEVER suggest cutting or removing any segment — segment-to-source integrity is sacred. Instead, suggest how to improve the segment's framing, analysis, or writing.

Source linking

Every piece of source content should have its original URL captured and preserved through the pipeline. The URL appears in the episode description as a clickable link.

  • An episode without source links is significantly less useful — listeners learn about a segment but can't follow up

  • Never fabricate URLs — if a URL isn't found, omit the link

  • Never fabricate facts — if you can't verify a claim and aren't genuinely confident, skip it or say "the sources don't cover this." Applies to quotes, statistics, dates, studies, and prices. Same posture as "Never fabricate URLs", extended

  • AI-generated disclosure — end every description with a content-describing line: "AI-narrated audio assembled from the sources in this description" or, for knowledge-only episodes, "AI-narrated audio — verify key facts before acting."

  • Label links by platform: "read on Example", "see on Example.org", "visit site"

  • Front-load the description summary — the first 1-2 sentences show as a preview in podcast apps. Don't waste them on boilerplate

Episode naming

  • Show name: Short, memorable, searchable. Avoid generic names that get lost in search results

  • Episode title: Include the date or episode number for recurring shows. Keep under ~60 characters to avoid truncation

  • Consistent format: Pick a pattern and stick with it: "Show Name - Date", "Show Name: Topic"

Episode length

Match length to content density — don't pad to hit a target:

FormatTypical length
Daily digest3-6 min
Weekly digest5-10 min
Short fiction5-15 min
Travel guide (per trip)5-10 min
Deep dive / explainer15-30 min
Daily briefing5-12 min
Language lesson10-20 min

AI-narrated content is denser than conversational podcasts — listeners absorb it faster. A tight 4-minute episode with strong content beats a padded 10-minute one.

Requirements and compatibility

Works with: Claude Code, Claude apps, OpenAI Codex, GitHub Copilot, Cursor, Gemini CLI, Kiro, OpenCode, Goose, Amp, Roo Code, JetBrains Junie, Factory Droid, Devin (ex-Windsurf), Mistral Vibe, OpenHands, Letta

“Works with” means the tool reads the open Agent Skills format; a skill written for one tool may use features others lack.

Needs: Needs network access

Security

What our scanner noticed· Medium risk

  • Instructions that use the network
  • Downloads piped into a shell

A static scan is not a guarantee. Skills are third-party content: review a skill before you let an agent use it.

Attribution and licence

Published by
Cline
Publisher
Cline (Official)
Source
cline/skills · skills/save-to-spotify · commit 2637846
Licence
Apache License 2.0 (redistribution allowed)
  • LICENSE (added by AutoGineer from LICENSE)
  • ATTRIBUTION.md (written by AutoGineer)
Synced

AutoGineer is not affiliated with or endorsed by Cline.

Download ZIP

The ZIP holds the skill’s files, its licence files and an ATTRIBUTION.md. Download save-to-spotify.zip