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

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

73%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 well-structured, actionable skill body with a clear validated workflow and good reference signaling. Its main weakness is verbosity in the procedure steps and unverifiable/possibly-over-inlined reference material.

Suggestions

Break the long run-on sentences in Procedure step 4 (and similar) into shorter bullets or sub-steps so each instruction is scannable.

Show the actual registry-events.py invocation forms for upsert, suppress, and erase (not just is-suppressed) so all mutation paths are copy-paste executable.

Move dense protocol/field-schema detail into registry-event-protocol.md and keep SKILL.md as the overview, ensuring the referenced files exist in the bundle.

Dimension	Reasoning	Score
Conciseness	Largely assumes Claude's competence (no basic concept explanations) and is information-dense, but several Procedure steps are long run-on sentences with repeated caveats (e.g. step 4) that could be tightened without losing meaning.	3 / 5
Actionability	Provides an executable command (python3 .../registry-events.py is-suppressed <subject-id>), env resolution, an exact host sequence, and concrete field requirements; minor gaps where upsert/suppress/erase invocations are described semantically rather than as shown commands.	4 / 5
Workflow Clarity	An 8-step procedure is clearly sequenced with explicit validation checkpoints ("verify consent", re-run "is-suppressed", a "Done when" contract, and only-proceed-when-valid gating) and feedback loops appropriate to its destructive suppress/erase operations.	5 / 5
Progressive Disclosure	Uses well-signaled one-level-deep references (Runtime Reads list, Reference Materials links to ../../references/*.md), but the bundle directories (references/, scripts/, assets/) are not present so the referenced files cannot be verified, and some dense protocol detail inlined in the body might better live in the referenced protocol file.	4 / 5
	Total	16 / 20 Passed

Description

92%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.

A strong, specific description with explicit trigger guidance and clear boundary statements that distinguish it from sibling skills. Minor room for broader synonym coverage, but it cleanly answers both what and when.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "log this subscriber's opt-in", "record unsubscribes/complaints", "query lawful basis", "curates pseudonymous consent facts", "applies suppression/erasure tombstones" — giving comprehensive coverage of the skill's capabilities.	5 / 5
Completeness	Explicitly answers both what ("curates pseudonymous consent facts... applies suppression/erasure tombstones") and when ("Use when the user asks to... record unsubscribes/complaints, or query lawful basis") with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural phrases users would say ("log this subscriber's opt-in", "record unsubscribes/complaints", "query lawful basis") plus synonyms (opt-in, unsubscribe, complaint, lawful basis), but a few common variations are absent — not quite the full synonym/extension coverage of a 5.	4 / 5
Distinctiveness Conflict Risk	Carves a clear niche and adds explicit boundary guidance — "Not for SEND scoring — use email-quality-auditor; not for building segments — use list-segment-builder" — minimizing wrong-skill triggering.	5 / 5
	Total	19 / 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: 10 suspicious	Warning

	Total	13 / 16 Passed

Repository: aaron-he-zhu/aaron-marketing-skills
Path: protocol/consent-registry/SKILL.md
Commit: 5cd4a80

Reviewed: 5 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.