CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Medium

Suggest reviewing before use

SKILL.md
Quality
Evals
Security

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.

A well-engineered, protocol-style skill body: lean prose, an executable read path, and a fully sequenced workflow with validation and reconciliation loops. The residual weaknesses are a write path lacking a complete command example, duplicated reference listings, and heavy dependence on out-of-bundle ../../ files for the core protocol details.

Suggestions

Show one complete `owner-append` invocation (exact registry-events.py subcommand plus a minimal request JSON conforming to registry-event.schema.json) so the write path is as copy-paste ready as the read path.

Consolidate 'Runtime Reads', the Handoff Summary link, and 'Reference Materials' into a single reference section so each file is linked exactly once and navigation lives in one place.

Vendor the shared protocol references (registry-event-protocol.md, runtime-invocation.md, state-model.md) inside the skill bundle, or inline the essential event-schema fields, so the skill does not depend on ../../ paths that are absent in a standalone install.

DimensionReasoningScore

Conciseness

The body is dense and operational with no explanations of concepts Claude already knows and no padding (e.g., the Skill Contract compresses reads/writes/done-when into one paragraph). It is not a 5 because of mild duplication: `registry-event-protocol.md` and `runtime-invocation.md` are listed under both "Runtime Reads" and "Reference Materials", and procedure step 1 repeats those reads.

4 / 5

Actionability

The read path is executable and copy-paste ready ("python3 \"$AARON_SKILLS_ROOT/scripts/registry-events.py\" get creators <aggregate-id>", "Run `verify creators`", and the AARON_SKILLS_ROOT resolution snippet), matching anchor 4. It falls short of anchor 5 because the write path only names `owner-append` without a complete invocation or request-JSON example, deferring the common write cases to out-of-bundle references.

4 / 5

Workflow Clarity

A 9-step sequenced procedure with explicit validation (step 9 "Run `verify creators` and report accepted/rejected proposal IDs, revision, conflicts"), authorization checkpoints (step 3 confirms explicit user authorization and lawful basis), and feedback loops for error recovery ("A stale revision must be re-read and reconciled, not forced"; same-date conflicts preserve both events with adjudication rationale). The destructive/batch cap does not apply because verification steps are present, so this matches the anchor 5 example's validate-fix-retry structure.

5 / 5

Progressive Disclosure

The body is an overview with labeled, one-level-deep links and a dedicated Reference Materials section, and the one bundle file present (`references/creator-record-template.md`) is real and appropriately separated. It is not a 5 because references are scattered across three sections (Runtime Reads, Handoff Summary, Reference Materials) with duplicates, and most referenced material (`../../references/registry-event-protocol.md`, `runtime-invocation.md`, `state-model.md`, `../../SECURITY.md`, `scripts/registry-events.py`) lives outside this bundle via `../../` paths that do not exist here — more than the "easy navigation" anchor 5 requires, but consistent with anchor 4's minor organization gaps.

4 / 5

Total

17

/

20

Passed

Description

87%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 description: concrete quoted trigger phrases, a specific capability statement, and explicit disambiguation from sibling skills. The only gaps are a single compressed action verb and a few missing synonyms (e.g., "influencer"), which keep specificity and trigger coverage at 4 rather than 5.

DimensionReasoningScore

Specificity

The description states it "curates creator identity, rate, rights, exclusivity, compliance-event, and performance facts through the append-only creators event stream", naming the domain, several concrete fact classes, and the mechanism. It stops short of anchor 5 because the capabilities collapse into a single "curates" verb — the distinct operations (query, accept/reject proposals, dedupe handles) are only implied via the trigger phrases.

4 / 5

Completeness

It explicitly answers "when" with concrete verbatim trigger phrases ('Use when the user asks "what did we pay this creator last time" or to "update the creator roster"') and "what" with a specific capability statement, matching the anchor for both what and when with concrete triggers. Anchor 4's caveat ('when' could be more explicit) does not apply since the triggers are quoted user queries.

5 / 5

Trigger Term Quality

It quotes natural user phrasings ("what did we pay this creator last time", "update the creator roster") plus domain terms (rate, rights, exclusivity, compliance) and Chinese synonyms (创作者档案/达人名册). Not anchor 5 because common variations such as "influencer", "talent", or "KOL" are absent, leaving a few natural terms missing.

4 / 5

Distinctiveness Conflict Risk

Explicit negative boundaries ("Not for scoring fit — use fit-scorer; not for reviewing content — use creator-content-auditor") plus a narrow registry niche give it a clear trigger territory with minimal conflict risk, matching the anchor 5 example's disambiguation quality.

5 / 5

Total

18

/

20

Passed

Validation

75%

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

CriteriaDescriptionResult

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

Reviewed

Table of Contents

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.