consent-registry

Use when the user asks to "log this subscriber's opt-in", record unsubscribes/complaints, or query lawful basis; curates pseudonymous consent facts through the append-only consent stream and applies suppression/erasure tombstones immediately. Not for SEND scoring — use email-quality-auditor; not for building segments — use list-segment-builder. 订阅同意台账/实时退订抑制/合法性依据登记

Quality

81%

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

62%Weight 40%Scale 1-3

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

The body is well-structured with clear sequencing and explicit verification for sensitive consent operations, but it leans verbose and mixes concrete commands with abstract policy, while detailed protocol rules that belong in referenced files are kept inline.

Suggestions

Tighten overloaded sentences in Skill Contract and Instructions by splitting nested caveats into short declarative rules, removing repeated capability restatements.

Move detailed capability/erasure/restore protocol rules into registry-event-protocol.md and keep SKILL.md as a lean overview pointing to them, improving both conciseness and progressive disclosure.

Add concrete, copy-pasteable command examples for the append/verify/suppress operations alongside the existing is-suppressed command so the actionability matches the workflow's verify steps.

Dimension	Reasoning	Score
Conciseness	Free of concept-explanation padding, but many sentences are overloaded with stacked caveats (e.g. "Capability signing happens only in a trusted host boundary, never an agent-controlled shell") and repeated capability rules that could be tightened, fitting the mostly-efficient-but-could-be-tighter anchor.	2 / 3
Actionability	Provides one fully concrete command ("python3 \"$AARON_SKILLS_ROOT/scripts/registry-events.py\" is-suppressed <subject-id>") and an env-var resolution, but much of the guidance is abstract policy and operation names ("append consent", "verify consent") rather than copy-paste executable steps.	2 / 3
Workflow Clarity	A numbered 1–8 sequence with explicit verification checkpoints — step 4's "append consent → confirm projection regenerated → verify consent → is-suppressed" and step 8's regenerate-then-verify-re-run loop — matches the clear-sequence-with-validation anchor for these sensitive operations.	3 / 3
Progressive Disclosure	Sections are well-organized and references are one-level-deep and signaled (Reference Materials + inline links), but no bundle files exist alongside the skill and large amounts of detailed capability/protocol rules live inline in Skill Contract and Instructions rather than in the referenced protocol files.	2 / 3
	Total	9 / 12 Passed

Description

100%Weight 40%Scale 1-3

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 specific, trigger-rich, complete on both what and when, and sharply disambiguated from sibling skills via explicit negative scoping. It is a strong, well-targeted skill description.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "log this subscriber's opt-in", "record unsubscribes/complaints", "query lawful basis", "curates pseudonymous consent facts through the append-only consent stream", "applies suppression/erasure tombstones" — matching the multiple-specific-actions anchor.	3 / 3
Completeness	Explicitly answers both what ("curates pseudonymous consent facts... applies suppression/erasure tombstones") and when ("Use when the user asks to..."), satisfying the explicit-trigger anchor for both.	3 / 3
Trigger Term Quality	Leads with natural user phrasings framed by "Use when the user asks to 'log this subscriber's opt-in', record unsubscribes/complaints, or query lawful basis", giving good coverage of terms a user would actually say.	3 / 3
Distinctiveness Conflict Risk	Explicit negative scoping — "Not for SEND scoring — use email-quality-auditor; not for building segments — use list-segment-builder" — carves a clear niche unlikely to trigger the wrong skill.	3 / 3
	Total	12 / 12 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: 10 suspicious	Warning

	Total	13 / 16 Passed

Repository: aaron-he-zhu/aaron-marketing-skills
Path: protocol/consent-registry/SKILL.md
Commit: 4a77c48

Reviewed: 9 days 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.