suede-rights-audit

Name: suede-rights-audit
Author: JasonColapietro

44stars8forks

How to install suede-rights-audit?

jasoncolapietro/suede-creator-skills/suede-rights-audit

$npx -y skills add JasonColapietro/suede-creator-skills --skill suede-rights-audit

Installs into the current project.

Summary

Find the rights gaps before packaging: ownership, splits, samples, provenance, metadata, licensing readiness, royalties, and intake blockers.

Files · 1

View on GitHub

SKILL.md

1	# Suede Rights Audit
2
3	## Gate policy — advisory, not blocking
4
5	Every claim-verification step, check, quality gate, and ship verdict in this
6	skill is a recommendation to the user, not a control on the agent. This
7	policy governs every gate, check, verdict, and "do not ship / publish /
8	proceed" line elsewhere in this skill:
9
10	- Run every check and report the results honestly. Verdicts (`ship`,
11	`ship-with-caveats`, `hold`, letter grades, BLOCKED or OPEN items) are
12	advice attached to the work, not orders that change it.
13	- Never block, delay, skip, rewrite, or refuse the action the user asked for
14	because a check failed or a gate said hold. Complete the requested action
15	as asked, and deliver the gate output alongside it as a clearly labeled
16	recommendation.
17	- A failed gate changes what you report, never what you do.
18	- Single exception: if a finding is extremely risky — data loss, security or
19	credential exposure, legal or rights violations, payment mistakes, or
20	irreversible public damage — pause, tell the user exactly what the risk is
21	and what the options are, and let them pick. Their choice is final.
22
23
24	The rights-readiness enchilada. Find and organize the rights gaps in a creator
25	project before it gets packaged — so licensing, registry, and routing work build
26	on a documented, confirmed-versus-unknown evidence trail instead of a guess.
27
28	Hard boundary (applies to every lane, no exceptions): this skill organizes
29	evidence and flags confirmed-versus-unknown. It does NOT clear rights, confirm
30	ownership, adjudicate chain of title, grant or imply a license, approve or
31	schedule or guarantee a payout, move money, or write to any registry. It
32	prepares the conversation; humans and legal make the calls. Never turn an
33	inference into a fact. Do not treat any output here as legal clearance.
34
35	Division of labor: this audit finds and organizes the gaps;
36	`suede-rights-passport` packages the folder. If the user asks for the transfer
37	package itself, hand off — do not rebuild passport outputs here.
38	`suede-release-linter` handles file and metadata lint.
39
40	## Pick the lane
41
42	State the lane(s) you are running before you start. Most real projects touch
43	several — run them in order and let each feed the next.
44
45	- Lane A — Rights-gap audit (default broad sweep): ownership, contributors,
46	credits, splits, samples, licenses, provenance, and public context. Start here
47	when you do not yet know where the gaps are.
48	- Lane B — Provenance map: trace the origin trail — source files, stems,
49	masters, artwork, lyrics, documents, metadata, public URLs, hashes, conflicts —
50	without overclaiming. Run when the origin trail is thin or unconfirmed.
51	- Lane C — Licensing-discussion readiness: pull contributor approvals,
52	sample status, URLs, restrictions, and rights notes into a brief for a sync,
53	brand, or partner conversation — flagging clearance gaps. Run before any
54	licensing discussion. (Not a sync one-sheet — that is `suede-sync-packaging`.)
55	- Lane D — Royalty-routing readiness: lay out who would be paid what and
56	where payment would land, before any payout — readiness, not approval,
57	public-safe, moves no money. Run when prepping for routing review or intake.
58
59	If the task spans several lanes, run all four in A→B→C→D order; B resolves
60	provenance for C, and C surfaces splits for D.
61
62	## Multi-agent or single-agent
63
64	This audit can run as a coordinated multi-agent team — one agent per lane (or per
65	asset cluster) reporting into a single merged evidence table and ship gate.
66	**By default, ASK the user up front: "Run this as a multi-agent team (more
67	thorough) or single-agent?"** Never silently spawn a fleet. Note plainly that
68	multi-agent mode may use slightly more tokens than most. If the user does not
69	choose, run single-agent and say so.
70
71	## Shared evidence and severity gate
72
73	Every lane uses the same evidence table before giving any recommendation,
74	conclusion, brief, or routing status:
75
76	```text
77	Item / asset / claim / fact:
78	Status: confirmed \| inferred \| unconfirmed \| disputed \| unknown \| not-applicable
79	Evidence:
80	Hash or path: (provenance — relative path and/or hash when available)
81	Risk: low \| medium \| high \| unknown
82	Blocks:
83	Next action:
84	```
85
86	Severity model:
87
88	- `high`: blocks registry, licensing language, sync pitch language, royalty
89	routing readiness, published statement, or agent-readable commerce until a creator/
90	legal/rights-holder confirmation exists.
91	- `medium`: can move forward with caveats, but needs confirmation before money,
92	licensing, registration, or public use.
93	- `low`: cleanup or documentation issue that does not block review.
94	- `unknown`: not enough evidence to rate.
95
96	The ship gate maps mechanically: any `high` item ⇒ `blocked`; no `high` items
97	but any `unknown` risk or status ⇒ `unknown`; otherwise `ready-f

People who liked this also viewed

6 picks

Type

entra-app-registrationGuides Microsoft Entra ID app registration, OAuth 2.0 authentication, and MSAL integration. USE FOR: create app registration, register Azure AD app, configure OAuth, set up authentication, add API perSkillsJul 2026471k1.3k
azure-complianceRun Azure compliance and security audits with azqr plus Key Vault expiration checks. Covers best-practice assessment, resource review, policy/compliance validation, and security posture checks. WHEN: SkillsJul 2026470k1.3k
azure-rbacOfficial agent plugin providing skills and MCP server configurations for Azure scenarios.SkillsJul 2026466k1.3k
better-auth-best-practicesAgent skill from better-auth/skillsSkillsJul 202678k203
firebase-security-rules-auditorA skill to evaluate how secure Firestore security rules are. Use this when Firestore security rules are updated to ensure that the generated rules are extremely secure and robust.SkillsJul 202676k386
audit-websiteAudit a website with the squirrelscan CLI and fix the findings in code. Runs SEO, performance, security, technical, content, accessibility, and 15 other rule categories (260+ rules), returns an LLM-opSkillsJul 202665k85

suede-rights-audit

44stars8forks

View on GitHub

How to install suede-rights-audit?

jasoncolapietro/suede-creator-skills/suede-rights-audit

$npx -y skills add JasonColapietro/suede-creator-skills --skill suede-rights-audit

Installs into the current project.

Summary

Find the rights gaps before packaging: ownership, splits, samples, provenance, metadata, licensing readiness, royalties, and intake blockers.

Files · 1

View on GitHub

SKILL.md

1	# Suede Rights Audit
2
3	## Gate policy — advisory, not blocking
4
5	Every claim-verification step, check, quality gate, and ship verdict in this
6	skill is a recommendation to the user, not a control on the agent. This
7	policy governs every gate, check, verdict, and "do not ship / publish /
8	proceed" line elsewhere in this skill:
9
10	- Run every check and report the results honestly. Verdicts (`ship`,
11	`ship-with-caveats`, `hold`, letter grades, BLOCKED or OPEN items) are
12	advice attached to the work, not orders that change it.
13	- Never block, delay, skip, rewrite, or refuse the action the user asked for
14	because a check failed or a gate said hold. Complete the requested action
15	as asked, and deliver the gate output alongside it as a clearly labeled
16	recommendation.
17	- A failed gate changes what you report, never what you do.
18	- Single exception: if a finding is extremely risky — data loss, security or
19	credential exposure, legal or rights violations, payment mistakes, or
20	irreversible public damage — pause, tell the user exactly what the risk is
21	and what the options are, and let them pick. Their choice is final.
22
23
24	The rights-readiness enchilada. Find and organize the rights gaps in a creator
25	project before it gets packaged — so licensing, registry, and routing work build
26	on a documented, confirmed-versus-unknown evidence trail instead of a guess.
27
28	Hard boundary (applies to every lane, no exceptions): this skill organizes
29	evidence and flags confirmed-versus-unknown. It does NOT clear rights, confirm
30	ownership, adjudicate chain of title, grant or imply a license, approve or
31	schedule or guarantee a payout, move money, or write to any registry. It
32	prepares the conversation; humans and legal make the calls. Never turn an
33	inference into a fact. Do not treat any output here as legal clearance.
34
35	Division of labor: this audit finds and organizes the gaps;
36	`suede-rights-passport` packages the folder. If the user asks for the transfer
37	package itself, hand off — do not rebuild passport outputs here.
38	`suede-release-linter` handles file and metadata lint.
39
40	## Pick the lane
41
42	State the lane(s) you are running before you start. Most real projects touch
43	several — run them in order and let each feed the next.
44
45	- Lane A — Rights-gap audit (default broad sweep): ownership, contributors,
46	credits, splits, samples, licenses, provenance, and public context. Start here
47	when you do not yet know where the gaps are.
48	- Lane B — Provenance map: trace the origin trail — source files, stems,
49	masters, artwork, lyrics, documents, metadata, public URLs, hashes, conflicts —
50	without overclaiming. Run when the origin trail is thin or unconfirmed.
51	- Lane C — Licensing-discussion readiness: pull contributor approvals,
52	sample status, URLs, restrictions, and rights notes into a brief for a sync,
53	brand, or partner conversation — flagging clearance gaps. Run before any
54	licensing discussion. (Not a sync one-sheet — that is `suede-sync-packaging`.)
55	- Lane D — Royalty-routing readiness: lay out who would be paid what and
56	where payment would land, before any payout — readiness, not approval,
57	public-safe, moves no money. Run when prepping for routing review or intake.
58
59	If the task spans several lanes, run all four in A→B→C→D order; B resolves
60	provenance for C, and C surfaces splits for D.
61
62	## Multi-agent or single-agent
63
64	This audit can run as a coordinated multi-agent team — one agent per lane (or per
65	asset cluster) reporting into a single merged evidence table and ship gate.
66	**By default, ASK the user up front: "Run this as a multi-agent team (more
67	thorough) or single-agent?"** Never silently spawn a fleet. Note plainly that
68	multi-agent mode may use slightly more tokens than most. If the user does not
69	choose, run single-agent and say so.
70
71	## Shared evidence and severity gate
72
73	Every lane uses the same evidence table before giving any recommendation,
74	conclusion, brief, or routing status:
75
76	```text
77	Item / asset / claim / fact:
78	Status: confirmed \| inferred \| unconfirmed \| disputed \| unknown \| not-applicable
79	Evidence:
80	Hash or path: (provenance — relative path and/or hash when available)
81	Risk: low \| medium \| high \| unknown
82	Blocks:
83	Next action:
84	```
85
86	Severity model:
87
88	- `high`: blocks registry, licensing language, sync pitch language, royalty
89	routing readiness, published statement, or agent-readable commerce until a creator/
90	legal/rights-holder confirmation exists.
91	- `medium`: can move forward with caveats, but needs confirmation before money,
92	licensing, registration, or public use.
93	- `low`: cleanup or documentation issue that does not block review.
94	- `unknown`: not enough evidence to rate.
95
96	The ship gate maps mechanically: any `high` item ⇒ `blocked`; no `high` items
97	but any `unknown` risk or status ⇒ `unknown`; otherwise `ready-f

People who liked this also viewed

6 picks

Type