creator-registry

Use when the user asks "what did we pay this creator last time" or to "update the creator roster"; curates creator identity, rate, rights, exclusivity, compliance-event, and performance facts through the append-only creators event stream. Not for scoring fit — use fit-scorer; not for reviewing content — use creator-content-auditor. 创作者档案/达人名册

Quality

86%

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

81%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.

The body is a well-organized, actionable protocol skill with a sequenced procedure, explicit validation checkpoints, and clear reference navigation. Its main weaknesses are slight density in the contract sections and references that resolve outside the local bundle.

Suggestions

Tighten the Skill Contract and Data Sources sections to bullet essentials, trimming prose that restates the procedure.

Add an explicit verify-failure recovery sub-step (e.g. 'if `verify creators` reports conflicts, re-read expected_revision, reconcile, and re-run') to make the feedback loop copy-paste explicit.

Clarify which referenced files are package-root shared vs. bundle-local so a standalone installer can tell what is present without resolving parent paths.

Dimension	Reasoning	Score
Conciseness	The body is dense but information-rich and domain-specific, with executable commands and minimal over-explanation of concepts Claude already knows; a few sentences in the Skill Contract and Data Sources sections could be tightened.	4 / 5
Actionability	Provides concrete executable commands (e.g. `python3 "$AARON_SKILLS_ROOT/scripts/registry-events.py" get creators <aggregate-id>`, `verify creators`) with mostly complete guidance; the write path is gated behind host-capability principals so it is not fully copy-paste ready.	4 / 5
Workflow Clarity	A clearly sequenced 9-step procedure with explicit validation ("Run `verify creators`", "projection verification passes" in Done-when) and a recovery feedback loop for stale revisions ("must be re-read and reconciled, not forced").	5 / 5
Progressive Disclosure	Well-structured overview with clearly signaled one-level-deep markdown references (registry-event-protocol.md, runtime-invocation.md, state-model.md, SECURITY.md); most referenced files live at package-root paths outside this bundle, leaving minor navigational gaps for a standalone reader.	4 / 5
	Total	17 / 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.

The description is explicit, concrete, and well-bounded, clearly stating both capabilities and trigger conditions while disambiguating against sibling skills. It is a strong, third-person trigger description with only minor synonym coverage gaps.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete curatorial actions — "creator identity, rate, rights, exclusivity, compliance-event, and performance facts" — with comprehensive coverage of the registry's scope.	5 / 5
Completeness	Explicitly answers both what ("curates creator identity, rate, rights, exclusivity, compliance-event, and performance facts") and when ("Use when the user asks..."), anchored by concrete trigger phrases.	5 / 5
Trigger Term Quality	Quotes natural user phrases ("what did we pay this creator last time", "update the creator roster") that users would actually say; a few synonymous trigger terms (e.g. "creator list", "influencer roster") are absent.	4 / 5
Distinctiveness Conflict Risk	Clear niche (creator roster facts) reinforced by explicit negative boundaries ("Not for scoring fit — use fit-scorer; not for reviewing content — use creator-content-auditor"), minimizing conflict risk.	5 / 5
	Total	19 / 20 Passed

Validation

75%

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 — 12 / 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
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	12 / 16 Passed

Repository: aaron-he-zhu/aaron-marketing-skills
Path: protocol/creator-registry/SKILL.md
Commit: 9df28a0

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.