creator-content-auditor

Use when the user asks to "review this influencer content" or "check if this post meets brand guidelines"; runs the typed STAR pre-publish gate, scores Trust and Appeal on the deliverable, folds in the creator Suitability read, computes the profile-weighted SQS, checks the disclosure/claim/brand-safety and fraud/fake-engagement vetoes, and writes constructive revision feedback. Not for drafting the brief — use brief-generator; not for partnership terms — use contract-helper. 达人内容审核/发布前质检

Quality

88%

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

77%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 a dense, well-sequenced auditor workflow with concrete commands, a validation checklist, and error-recovery loops. Its main weaknesses are mild cross-section redundancy and a progressive-disclosure mismatch where most signaled references do not resolve to the bundled files and two bundled files are orphaned.

Suggestions

Wire the standalone bundle: either point the Reference Materials links at the bundled files (auditor-runtime.md, quality-review-aids.md, review-templates.md) or add the missing bundled references (auditor-runbook.md, scoring-semantics.md, star-benchmark.md, runtime-invocation.md, humanizer-slop.md) so every signaled path resolves.

Reference quality-review-aids.md and review-templates.md from the body (or remove them from the bundle) so no bundled file is orphaned.

Dedupe the restated veto/decision logic across Instructions, §3 Guardrails, and §5 Translation so each rule lives in one canonical place.

Dimension	Reasoning	Score
Conciseness	The body is dense and never explains concepts Claude already knows, but §3 Guardrails, Validation Checkpoints, and §5 Translation restate veto/decision logic already given in the Instructions (e.g. 'a refused audit is Unknown, never a pass' and the SHIP/FIX/BLOCK decisions appear in multiple sections), so it is mostly efficient but could be tightened; not the level-3 'every token earns its place'.	2 / 3
Actionability	Provides executable commands and concrete contracts — 'python3 "$AARON_SKILLS_ROOT/scripts/rubric-score.py" score <run.json>', 'validate-audit-artifact.py', env resolution 'AARON_SKILLS_ROOT="${CLAUDE_PLUGIN_ROOT:-...}"', and exact output fields ('score_state: NOT_SCORED'); for an instruction skill this is specific and copy-paste-ready guidance.	3 / 3
Workflow Clarity	A clear sequence (Runtime/Setup → numbered Evidence & Scoring → Creator Feedback → Persistence) with an explicit Validation Checkpoints checklist and feedback loops (runtime unavailable → NOT_SCORED; validate → fix → revalidate), matching the 'clear sequence with explicit validation steps; feedback loops; checklists' anchor.	3 / 3
Progressive Disclosure	Sections are well-signaled and one-level-deep, but scored against the actual bundle: only 'references/auditor-runtime.md' resolves to a bundled file, while 'auditor-runbook.md', 'scoring-semantics.md', 'star-benchmark.md', 'runtime-invocation.md', and 'humanizer-slop.md' point outside the bundle, and the bundled 'quality-review-aids.md'/'review-templates.md' are never referenced — orphaned bundle files and unresolved references keep it at the 'some structure but could be better organized' anchor.	2 / 3
	Total	10 / 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 strong across all four dimensions: it opens with explicit natural-language triggers, enumerates concrete gate/scoring/veto/feedback actions, and disambiguates against sibling skills. It fully satisfies the what/when/specificity/distinctiveness anchors.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'runs the typed STAR pre-publish gate, scores Trust and Appeal on the deliverable, folds in the creator Suitability read, computes the profile-weighted SQS, checks the disclosure/claim/brand-safety and fraud/fake-engagement vetoes, and writes constructive revision feedback' — matching the 'lists multiple specific concrete actions' anchor.	3 / 3
Completeness	Explicitly answers both what (the enumerated gate/scoring/veto/feedback actions) and when via a clear 'Use when the user asks to...' clause, satisfying the 'clearly answers both what AND when with explicit triggers' anchor; not capped at 2 since the trigger is explicit.	3 / 3
Trigger Term Quality	Quotes natural user phrasing — 'review this influencer content' and 'check if this post meets brand guidelines' — terms a user would actually say, plus 'influencer content'/'post meets brand guidelines' variations; not the level-2 single-keyword case.	3 / 3
Distinctiveness Conflict Risk	A distinct influencer pre-publish-gate niche with explicit 'Not for drafting the brief — use brief-generator; not for partnership terms — use contract-helper' disambiguation, making wrong-skill conflicts unlikely; exceeds the 'somewhat specific but could overlap' anchor.	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: 9 suspicious	Warning

	Total	13 / 16 Passed

Repository: aaron-he-zhu/aaron-marketing-skills
Path: influencer/activate/creator-content-auditor/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.