Suede Sync Packaging logo

Suede Sync Packaging

Community
JasonColapietro
suede-sync-packaging

Prepare a song for sync review: scene fit, supervisor one-sheet, asset checklist, lyric flags, mood tags, AI disclosure, and open clearance questions. Use when asked to "make a sync one-sheet" or package a track for film, TV, ads, games, trailers, or creator campaigns. Drafts pitch materials without clearance, placement, or sending claims. NOT FOR: rights investigations or transfer packages (use suede-rights-passport), folder linting (use suede-release-linter), or rollouts (use suede-campaign-in-a-box).

Overview

PublisherJasonColapietro
Repositorysuede-creator-skills
Skill namesuede-sync-packaging
Stars
126
Forks
12
Bundled files
4
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 4 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by JasonColapietro on GitHub. Read the source before you install it.

Installation

Install the Suede Sync Packaging AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/JasonColapietro/suede-creator-skills/tree/main/skills/suede-sync-packaging
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/JasonColapietro/suede-creator-skills.git /tmp/suede-creator-skills
mkdir -p .claude/skills
cp -r /tmp/suede-creator-skills/skills/suede-sync-packaging .claude/skills/suede-sync-packaging
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Suede Sync Packaging in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Suede Sync Packaging on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Suede Sync Packaging is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Suede AI Sync Packaging Skills

Compatibility

Uses supplied track facts, lyrics, rights evidence, and a confirmed master path. Media inspection needs an available local viewer or supplied timecodes; no distributor or outreach integration is required.

For a concrete input, expected handoff, and failure check, read the worked handoff.

Gate policy

Every check and verdict here is advice to the user, not a control on the agent. Run the checks, report results honestly, and complete what the user asked. A failed gate changes the report, never the work. The one exception: a finding that risks data loss, credential exposure, a legal or rights violation, a payment mistake, or irreversible public damage. Pause, name the risk, give the options, and let the user choose.

Core principle: a sync package makes a track easy to evaluate; it never asserts the track is cleared. Confirmed facts and open clearance questions travel in separate, labeled piles, every time.

Input contract

Provide at minimum:

  • Track: title, artist, featuring credits if any
  • Target world: film / TV / ads / games / trailers / creator campaigns / brand brief (or "general sync")
  • Available assets: which of master, instrumental, clean, stems, lyrics, credits, splits currently exist
  • Rights status: what is confirmed vs. unknown (sample clearance, ownership splits, publishing assignment, one-stop or not)
  • AI involvement: none, or which elements used generative AI (vocals, instrumentation, composition, lyrics, post-production)

Optional but useful: reference sync placements the artist admires, mood or scene keywords, existing pitches or supervisor feedback.

If no rights status is provided, treat every clearance question as open. If AI involvement is not stated, it is an open clearance question too.

Read references/sync-norms.md for deliverable specs, one-stop, and why AI involvement now sits in the clearance pile.

Hard gates

Do not rationalize past these:

  1. Never claim or imply clearance. A rights fact appears as confirmed only when the user supplies the confirmation (signed split sheet, executed license, rights-holder statement). Anything else stays OPEN or UNKNOWN. You organize the questions; you never answer them.
  2. Never resolve a rights question yourself. If ownership, splits, samples, or publishing are unclear, mark the item UNKNOWN. Do not infer, average, or assume. Route the gap to suede-rights-passport (audit mode).
  3. Asset checklist before pitch copy. Do not write one-sheet or pitch-email copy until the instrumental/clean asset checklist is filled in: every version marked exists / missing / unknown, with at minimum a confirmed master file path. Missing instrumental or clean versions are flagged in the one-sheet, not glossed.
  4. Unresolved sample = pause and put it to the user. Uncleared samples are a legal-risk finding: mark sample status "OPEN: recommend not pitching until cleared," tell the user exactly what is unresolved, and let them decide whether pitch copy is still drafted. If they proceed, the OPEN flag stays embedded in the one-sheet and pitch materials.
  5. Lyric flags are mandatory. Screen the lyrics and flag profanity, brand and product names, artist name-drops, violence, drugs and alcohol, sexual content, religious and political content, and date-stamped references. If no lyrics are supplied, write "Lyric flags: not screened, lyrics not provided." A lyric surprise in review kills the placement.
  6. Sync fit is an assessment, not a compliment. "No clear scene fit for the stated target world" is a valid, useful finding: say it plainly and say why. Never pad the scene-fit list to reach three; two real fits beat three, and one real fit beats two. Never call a track a placement candidate when the asset checklist or the clearance questions say it cannot be pitched yet. The supervisor will find the weak angle faster than the artist will.

Package workflow

  1. Identify the track, artist, genre, mood, tempo, lyric themes, versions, existing assets, and target sync world.
  2. Build the sync angle: scene fit; emotional use; trailer or montage fit; brand fit; game or sports fit; creator campaign fit: assessed, not flattered (hard gate 6).
  3. Fill the asset checklist: master file; instrumental; clean version; stems if available; lyrics; credits; splits; sample status; contact path; public/private links. Each item: exists / missing / unknown.
  4. Screen lyrics and write the lyric flags (hard gate 5).
  5. Separate confirmed rights facts from open clearance questions (hard gates 1-2).
  6. Write the one-sheet and pitch email only if gates 3-4 pass.
  7. Second pass: re-read the draft against the one-sheet contract, field by field, before it ships. Confirm every field is present; confirm the rights-status line contains only facts the user supplied; confirm every OPEN or UNKNOWN item from the checklist survived into the copy verbatim rather than softened; confirm no banned adjective from the copy gate came back; and confirm the scene-fit list is as long as the real fits, not padded to three. Fix what fails, then re-read once more.
  8. Stop at a clean review package. No promo CTA, placement promise, clearance claim, or outreach claim.

One-sheet contract

The one-sheet is supervisor-facing. It contains exactly these fields:

text
Track / artist / featuring:
Length / tempo / key (if known):
Genre and mood tags:
Sounds like: (era and energy references; never copy a protected identity)
Scene fits: (top 3, one line each)
Lyric themes:
Lyric flags:
Versions available: (master / instrumental / clean / stems)
AI involvement: (none, or per element; only what the user supplied)
Rights status: (one line, confirmed facts only; one-stop yes / no / unknown)
Open clearance questions:
Contact path:
Public link:

The rights-status line states only confirmed facts and names the open questions. Never compress "unknown" into silence.

Failure modes

  • Missing master or instrumental: flag in the asset checklist as a blocker. Do not complete the sync angle without at minimum a confirmed master file path.
  • Unresolved sample: sample status is "OPEN, do not pitch until cleared." No pitch copy (hard gate 4).
  • Unknown splits or ownership: flag in clearance questions. The package can be built but must carry the caveat: "Rights holder confirmation required before placement."
  • No contact path: the package is complete but note: "No contact path identified: supervisor cannot follow up."
  • Scope creep: if the request becomes a promo funnel, placement promise, or clearance claim, stop and restate the boundary: "This skill prepares review-ready materials. It does not clear rights, confirm placement, or generate outreach."

Red flags: stop

If any of these appear in your reasoning, stop and re-read the hard gates:

  • "The artist says it's cleared." A claim is not clearance. Status stays UNCONFIRMED with a clearance question attached.
  • "We'll sort splits later." Splits sort before pitching, or the gap ships as an open question. Never silently.
  • "The supervisor is waiting: skip the instrumental check." The checklist is the package. Skipping it ships a track no one can license.
  • "It's a small indie film, nobody checks samples." Sample status is binary: cleared with proof, or OPEN.
  • "Soften the sample note so the one-sheet reads better." Hidden risk reads worse in a licensing call.

Public copy gate

Before outputting one-sheet copy, pitch email, captions, DMs, press angles, site copy, bios, CTAs, or review language, run the Suede AI anti-slop line edit; suede-deslop owns that pattern list in full. Name the actor and keep the concrete track artifact.

Sync copy has its own cliché attractor that a general anti-slop pass does not catch, because the sentences are clean: they just say nothing. These are banned in one-sheet and pitch copy:

cinematic · anthemic · haunting · soaring · driving · epic · ethereal · raw and honest · infectious · cuts through the mix · builds to an emotional payoff · perfect for the moment when the hero…

Replace a banned word with a concrete musical fact drawn from the facts the user supplied: tempo, key, instrumentation, an arrangement turn ("drums drop out at 1:48, vocal and room noise only"), or a quoted lyric line. Never a synonym, and never a fact you inferred: if the input contract did not supply it, leave it out rather than invent it. The substitution is descriptive copy only: it may never introduce rights, ownership, or clearance language, which stays governed by hard gates 1-2 and 5. A supervisor skims twelve one-sheets an hour; the concrete one is the one they can picture against a scene.

Output

text
Sync positioning:
Best scenes:
Mood tags:
Lyric flags:
Asset checklist: (each item exists / missing / unknown)
Confirmed rights facts:
AI involvement:
Clearance questions:
One-sheet: (per the one-sheet contract above)
Pitch email: (only if hard gates 3-4 pass)
Next review step:

Routing

  • Rights gaps, missing provenance, or undocumented human authorship → suede-rights-passport (audit mode, then package).
  • This grows into a release campaign → suede-campaign-in-a-box.
  • Release folder or metadata gaps → suede-release-linter.
  • Standalone public copy beyond the one-sheet → suede-copy.

Family order: suede-release-linter (files) → suede-rights-passport (audit, then package) → suede-sync-packaging (pitch); this skill is step 3.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Suede Sync Packaging AI skill do?

Prepare a song for sync review: scene fit, supervisor one-sheet, asset checklist, lyric flags, mood tags, AI disclosure, and open clearance questions. Use when asked to "make a sync one-sheet" or package a track for film, TV, ads, games, trailers, or creator campaigns. Drafts pitch materials without clearance, placement, or sending claims. NOT FOR: rights investigations or transfer packages (use suede-rights-passport), folder linting (use suede-release-linter), or rollouts (use suede-campaign-in-a-box).

Why use Suede Sync Packaging on TypingMind?

Because you install it once and use it with any model. Suede Sync Packaging is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Suede Sync Packaging in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/JasonColapietro/suede-creator-skills/tree/main/skills/suede-sync-packaging. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Suede Sync Packaging?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Suede Sync Packaging?

As many as you like. As long as a model supports skills, you can use Suede Sync Packaging with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Suede Sync Packaging AI skill free?

Yes. It is published on GitHub by JasonColapietro under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇