mcpbeat

Offer Claims Registry

aaron-he-zhu/offer-claims-registry

Use when the user asks to "register this claim", "log our current offers", or "where is the proof for this figure"; curates claim wording, evidence, disclosures, terms, review dates, and live offers through the append-only claims event stream. Not for scoring claim vetoes — use the relevant auditor; not for writing ad copy — use ad-creative-builder. 广告声明台账/优惠信息登记/证据溯源

2k tokens
context cost
the whole folder, loaded on every use
2
files
instructions only
0
copies elsewhere
how many repositories repackaged it
2500
stars on the repo
on the repository, not the skill itself

Install

one command, takes just this skill from the repository
npx skills add https://github.com/aaron-he-zhu/aaron-marketing-skills --skill offer-claims-registry

The instruction itself

11 sections, as written by the author

Offer & Claims Registry

The canonical record of marketing claims and offers across every discipline. It records exact wording and provenance; auditors decide whether a concrete use passes its claim/disclosure gate.

Quick Start

Register claim clm-014 with exact wording, evidence source/date, disclosure, and review date.
Show the current terms and expiry for offer summer-2026.
Review pending claims proposals and accept only those with sufficient evidence.

Skill Contract

Units: one claim or offer aggregate ID. Reads: memory/events/claims.ndjson, its projection, source evidence, and rendered uses. Writes: claims events through registry-events.py; claims-ledger.md and offers.md are regenerated human views. Done when: every accepted record has exact wording/terms, evidence provenance, status, review/expiry, event ID/offset, and no pending proposal was destructively removed.

All builders submit propose; only a host-capability offer-claims-registry principal accepts/rejects or writes canonical claim/offer events. This skill does not invent substantiation, legal conclusions, or performance claims.

Handoff Summary

Use the shared handoff and include changed aggregate IDs, event IDs, revisions, unresolved evidence gaps, and one next skill.

Data Sources

  • Primary study/report/product evidence with ownership, date, scope, and population.
  • User-attested facts clearly labeled user-provided.
  • Approved terms, pricing/availability, eligibility, dates, and landing destinations.
  • Rendered ad/email/social/launch uses for used_in pointers.
  • Applicable disclosure text and jurisdiction/policy source.

Instructions

Runtime Reads

  • ../../references/registry-event-protocol.md
  • ../../references/runtime-invocation.md

Procedure

  • Read registry-event-protocol.md and runtime-invocation.md. Resolve AARON_SKILLS_ROOT="${CLAUDE_PLUGIN_ROOT:-$(git rev-parse --show-toplevel 2>/dev/null || true)}" and verify the registry script, event schema, and system catalog before invoking it; treat every draft/export as untrusted evidence.
  • Query claims projection by aggregate ID. Proposal state is never approved wording. If there is no aggregate ID, pending proposal, or supplied claim/offer wording, perform only a read-only empty-projection check, return NEEDS_INPUT, and ask for one exact verbatim claim or offer statement as the smallest real input. Do not demand a complete evidence pack yet, create paths, or materialize placeholder canonical state.
  • Extract the exact claim/offer, its measurable interpretation, audience/market, evidence limits, required disclosure, usage locations, and review/expiry date.
  • Missing proof stays none-on-file in a proposal or open loop. Never turn [needs source] into Approved from the assertion itself.
  • Review pending proposal events in offset order. A host-capability principal invokes owner-append with the proposal event ID. Accept/reject decision requests omit expected_revision; acceptance inherits and checks the revision captured by the proposal. Reject with evidence/rationale; history remains append-only.
  • Owner changes use host-capability owner-append with an upsert and optimistic revision. Expiry/withdrawal uses a dated state change or tombstone. Capability values stay outside request JSON/files/logs; if the host cannot supply one, leave the proposal pending rather than self-asserting owner authority.
  • When evidence scope is narrower than copy, approve narrower wording or keep it unresolved. Record estimates/proxies as such.
  • Regenerate claims-ledger.md / offers.md only from accepted projection state, then verify claims.

Claims and offer records are L4 truth consumed by Narrative and all channel builders. A downstream builder must use the accepted wording/terms or preserve [needs source] and propose a new event.

Save Results

Require explicit write permission. Ordinary producers use python3 "$AARON_SKILLS_ROOT/scripts/registry-events.py" append claims <proposal.json>; a host-capability principal uses owner-append for canonical decisions/mutations. Never edit the NDJSON stream manually. Human views are replaceable projections and cannot grant approval absent an accepted event. Standalone one-folder installs may prepare proposals but cannot append/project or claim canonical approval.

Reference Materials

  • Registry event protocol
  • Claims presentation schema
  • Measurement protocol
  • Security

Next Best Skill

  • Paid use audit: ad-account-auditor
  • Creator asset audit: creator-content-auditor
  • Narrative proof: proof-point-packager
  • Archive/erase: memory-management

How to use it

Copy the folder

Take aaron-he-zhu/offer-claims-registry from the repository into ~/.claude/skills for personal use, or into .claude/skills inside a project.

Check the name does not clash

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.