jasoncolapietro/suede-rights-audit
Find the rights gaps before packaging: ownership, splits, samples, provenance, metadata, licensing readiness, royalties, and intake blockers.
npx skills add https://github.com/JasonColapietro/suede-creator-skills --skill suede-rights-audit
Every claim-verification step, check, quality gate, and ship verdict in this
skill is a recommendation to the user, not a control on the agent. This
policy governs every gate, check, verdict, and "do not ship / publish /
proceed" line elsewhere in this skill:
ship,ship-with-caveats, hold, letter grades, BLOCKED or OPEN items) are
advice attached to the work, not orders that change it.
because a check failed or a gate said hold. Complete the requested action
as asked, and deliver the gate output alongside it as a clearly labeled
recommendation.
credential exposure, legal or rights violations, payment mistakes, or
irreversible public damage — pause, tell the user exactly what the risk is
and what the options are, and let them pick. Their choice is final.
The rights-readiness enchilada. Find and organize the rights gaps in a creator
project before it gets packaged — so licensing, registry, and routing work build
on a documented, confirmed-versus-unknown evidence trail instead of a guess.
Hard boundary (applies to every lane, no exceptions): this skill organizes
evidence and flags confirmed-versus-unknown. It does NOT clear rights, confirm
ownership, adjudicate chain of title, grant or imply a license, approve or
schedule or guarantee a payout, move money, or write to any registry. It
prepares the conversation; humans and legal make the calls. Never turn an
inference into a fact. Do not treat any output here as legal clearance.
Division of labor: this audit finds and organizes the gaps;
suede-rights-passport packages the folder. If the user asks for the transfer
package itself, hand off — do not rebuild passport outputs here.
suede-release-linter handles file and metadata lint.
State the lane(s) you are running before you start. Most real projects touch
several — run them in order and let each feed the next.
credits, splits, samples, licenses, provenance, and public context. Start here
when you do not yet know where the gaps are.
masters, artwork, lyrics, documents, metadata, public URLs, hashes, conflicts —
without overclaiming. Run when the origin trail is thin or unconfirmed.
sample status, URLs, restrictions, and rights notes into a brief for a sync,
brand, or partner conversation — flagging clearance gaps. Run before any
licensing discussion. (Not a sync one-sheet — that is suede-sync-packaging.)
where payment would land, before any payout — readiness, not approval,
public-safe, moves no money. Run when prepping for routing review or intake.
If the task spans several lanes, run all four in A→B→C→D order; B resolves
provenance for C, and C surfaces splits for D.
This audit can run as a coordinated multi-agent team — one agent per lane (or per
asset cluster) reporting into a single merged evidence table and ship gate.
**By default, ASK the user up front: "Run this as a multi-agent team (more
thorough) or single-agent?"** Never silently spawn a fleet. Note plainly that
multi-agent mode may use slightly more tokens than most. If the user does not
choose, run single-agent and say so.
Every lane uses the same evidence table before giving any recommendation,
conclusion, brief, or routing status:
Item / asset / claim / fact:
Status: confirmed | inferred | unconfirmed | disputed | unknown | not-applicable
Evidence:
Hash or path: (provenance — relative path and/or hash when available)
Risk: low | medium | high | unknown
Blocks:
Next action:
Severity model:
high: blocks registry, licensing language, sync pitch language, royaltyrouting readiness, published statement, or agent-readable commerce until a creator/
legal/rights-holder confirmation exists.
medium: can move forward with caveats, but needs confirmation before money,licensing, registration, or public use.
low: cleanup or documentation issue that does not block review.unknown: not enough evidence to rate.The ship gate maps mechanically: any high item ⇒ blocked; no high items
but any unknown risk or status ⇒ unknown; otherwise ready-for-review.
Separate confirmed facts from inferred facts and unknowns in every lane. Do not
turn an inference into a fact. Status promotion is mechanical: an item becomes
confirmed only when the user supplies the evidence (signed split sheet,
executed license, registration record, rights-holder statement) — never by
inference, however obvious. When torn between two statuses, record the weaker
one. You mark gaps UNKNOWN or UNCONFIRMED; you never resolve them.
If any of these appear in your reasoning, stop and re-read the hard boundary:
clearance. Status: unconfirmed.
needs the sheet plus every party's confirmation.
evidence shows.
is the rights holder's job, not yours.
what Lane B exists to expose.
Identify rights and intake gaps before packaging. Sweep all seven audit lanes:
confirmations.
artists, visual contributors, and managers.
caveats.
unknowns.
license notes.
and evidence trail. (Hand off to Lane B when this is thin.)
Run the shared evidence table per item. Output:
Confirmed facts:
Missing facts:
Evidence table:
Blockers:
Questions for creator:
Safe public wording:
Next lane / skill: suede-rights-passport | Lane B provenance | Lane C licensing | Lane D routing
Do not treat the audit as legal clearance.
Make the origin trail readable without overclaiming what is known.
videos, documents, metadata files, and public URLs.
should not be shared publicly.
High-risk provenance gaps block registry, licensing, royalty routing,
published statements, or agent commerce until the origin trail is confirmed. Output:
Asset map:
Known origin:
Evidence:
Evidence table:
Unknowns:
Conflicts:
Do-not-share items:
Next questions:
Prepare creator materials for licensing review while keeping evidence boundaries
visible. Does NOT claim rights are cleared.
public URLs, and restrictions.
High-risk items block licensing language, sync pitch language, published statements, or
agent-readable commerce until confirmed. Safe copy can say what is known and what
still needs rights-holder review. Output:
Licensing brief:
Confirmed rights facts:
Evidence table:
Open questions:
Restrictions:
Unsafe claims removed:
Next step:
Summarize whether a project is ready for royalty-routing discussion. Readiness,
not approval. Public-safe. Moves no money.
unresolved parties.
approved, sent, scheduled, or guaranteed.
administration facts only at a safe level (never expose sensitive payment
details).
High-risk items block routing readiness when contributor identity, role, split
percentage, payment destination, publisher, label, territory, tax, or rights-
administration facts are missing, disputed, or unsafe to expose. Output:
Routing status:
Confirmed splits:
Evidence table:
Missing confirmations:
Payout caveats:
Creator questions:
Safe summary:
Ship gate: ready-for-review | blocked | unknown
Think of your song or project like a guitar case full of stuff before a big
show. Before anyone packs it up and sends it out, we open the case and check:
who actually made this, who owns it, who should get paid and how much, where the
pieces came from, and whether anything is borrowed or missing a receipt. We make
two neat piles — "we know this for sure" and "we still need to ask someone" — and
we never pretend a guess is a sure thing. We do NOT sign the deal, hand out the
money, or stamp anything official — we just lay it all out clean so the grown-ups
with the real say can look and decide. That is it.
holder**.
next skill (suede-rights-passport, suede-release-linter).
rights, confirms no ownership, approves no payout, moves no money, and writes
to no registry.
suede-release-linter.
suede-campaign-in-a-box.
Take jasoncolapietro/suede-rights-audit from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.