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

Quality

87%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

75%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A dense, well-structured protocol skill: terse Quick Start, a precise Skill Contract, an 8-step sequenced procedure with validation guards, and clean references to bundled materials. It is strong across the board but carries minor redundancy and leaves the verify-retry feedback loop implicit.

Suggestions

Add an explicit verify-failure feedback loop after step 8 (e.g., "If `verify claims` fails, fix the offending event/wording and re-run verify before regenerating views") to reach full workflow-clarity credit.

De-duplicate the registry-events.py invocation and capability-boundary statements between Skill Contract, Procedure, and Save Results so each is stated once and cross-referenced.

Reconcile Runtime Reads and Reference Materials so each external file is listed once with its purpose, eliminating the overlap that currently blurs navigation.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence (no explaining what a claim or NDJSON is), but the registry-events.py invocation and capability-boundary statements recur across Skill Contract, Procedure, and Save Results, a minor redundancy that keeps it just below level 5.	4 / 5
Actionability	Concrete executable guidance is present (`python3 "$AARON_SKILLS_ROOT/scripts/registry-events.py" append claims <proposal.json>`, env-var resolution, named projections, status enums), but the full proposal schema is externalized and `<proposal.json>` is a placeholder, so it is mostly rather than fully copy-paste ready.	4 / 5
Workflow Clarity	An explicit 8-step procedure with validation checkpoints (read-only NEEDS_INPUT guard, revision checks, `verify claims`) and append-only safety; it is not level 5 because the verify-failure retry loop is implied rather than spelled out as a fix-and-revalidate cycle.	4 / 5
Progressive Disclosure	Clear sectioned overview with well-signaled one-level-deep references (the bundled claims-ledger-schema.md is real and correctly linked), but Runtime Reads and Reference Materials overlap in listing the same protocol files, a minor organization gap below level 5.	4 / 5
	Total	16 / 20 Passed

Description

100%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is exemplary: third-person voice, concrete actions, natural trigger phrases, explicit what/when, and clear boundary disambiguation from adjacent auditor and creative skills. The trailing Chinese summary line is mild redundancy but does not detract from specificity.

Dimension	Reasoning	Score
Specificity	"curates claim wording, evidence, disclosures, terms, review dates, and live offers through the append-only claims event stream" lists multiple specific concrete actions with comprehensive coverage, matching the level-5 anchor; it is not level 4 because there are no real coverage gaps.	5 / 5
Completeness	It explicitly answers both what ("curates claim wording, evidence, disclosures, terms, review dates, and live offers") and when ("Use when the user asks to...") with concrete trigger phrases, plus boundary guidance; this is the level-5 anchor exactly.	5 / 5
Trigger Term Quality	The quoted triggers "register this claim", "log our current offers", and "where is the proof for this figure" are natural phrases a user would actually say, giving comprehensive coverage; not level 4 since common variations are present rather than missing.	5 / 5
Distinctiveness Conflict Risk	A clear niche (marketing claims/offers registry) with distinct triggers and explicit "Not for... use the relevant auditor; ... use ad-creative-builder" boundary guidance naming adjacent skills, minimizing conflict risk; matches the level-5 anchor.	5 / 5
	Total	20 / 20 Passed

Validation

81%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_field	'metadata' should map string keys to string values	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 9 suspicious	Warning

	Total	13 / 16 Passed

Repository: aaron-he-zhu/aaron-marketing-skills
Path: protocol/offer-claims-registry/SKILL.md
Commit: 64562bc

Reviewed: 1 day ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.