social-quality-auditor

Use when the user asks to "audit our social presence" or "is this batch safe to publish"; runs either the typed ECHO asset gate or a separate program-maturity profile, with channel-truth, claim, disclosure, manipulation, UGC-rights, and denominator checks. Not for creator deliverables — use creator-content-auditor; not for launch readiness — use launch-readiness-auditor. 社媒资产门/运营成熟度/发布前放行

Quality

74%

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

Fix and improve this skill with Tessl

tessl review fix ./social/host/social-quality-auditor/SKILL.md

Quality

Content

62%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 content is a well-structured, concise auditor runbook with explicit checkpoints and a validation loop, but much executable detail is deferred to references that are not bundled here, and some catalog-level content is inlined rather than split out. Actionability and progressive disclosure land at 3 while conciseness and workflow clarity reach 4.

Suggestions

Surface one minimal copy-paste invocation (scorer command or exact runtime call) inline so the body is actionable without loading external references.

Move the inline item-ID listings and veto catalog into the bundled auditor-runtime reference and keep the body as a pointer, improving progressive disclosure.

Ensure all root references cited in the body (auditor-runbook, scoring-semantics, echo-benchmark, measurement-protocol) are present in the bundle or clearly marked as root-install-only.

Dimension	Reasoning	Score
Conciseness	The body is dense and largely free of padding, listing procedure, vetoes, and checkpoints without explaining concepts Claude already knows, though a few governing/contract sentences could be tightened. Efficient with minor trim opportunities.	4 / 5
Actionability	It names exact item IDs, vetoes, environment resolution, and persistence paths, but actual scoring/execution lives in external references and the bundled runtime; the body itself gives high-level procedure rather than copy-paste executable steps.	3 / 5
Workflow Clarity	A clear sequenced procedure (declare context, score per profile, verify vetoes, report, validate, persist) with explicit Validation Checkpoints and a validate-fix-revalidate loop; minor gaps keep it just below the fully explicit anchor.	4 / 5
Progressive Disclosure	Structure and signaled references are present, but the body inlines substantial catalog/procedure detail that belongs in the referenced runbooks, and most cited root references are not bundled with the skill, leaving navigation only partially clear.	3 / 5
	Total	14 / 20 Passed

Description

86%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 strong: it gives concrete capabilities, natural trigger phrases, explicit when-guidance, and clear disambiguation against sibling skills. Minor gaps in trigger synonym coverage and a fully comprehensive action list keep specificity and trigger quality at 4 rather than 5.

Dimension	Reasoning	Score
Specificity	Names several concrete checks (channel-truth, claim, disclosure, manipulation, UGC-rights, denominator) and the two profile types, but stops short of a comprehensive action list, fitting the 'several specific actions; minor gaps' anchor.	4 / 5
Completeness	Explicitly states what it does (ECHO asset gate or program-maturity profile with named checks) and when to use it via quoted trigger phrases, plus explicit exclusions, matching the clear what-and-when anchor.	5 / 5
Trigger Term Quality	Quotes natural user phrases ('audit our social presence', 'is this batch safe to publish') but lacks synonyms/extension variants a user might say, so good-but-not-comprehensive coverage.	4 / 5
Distinctiveness Conflict Risk	Carves a clear niche and names the sibling skills it is not (creator-content-auditor, launch-readiness-auditor), minimizing overlap and conflict risk.	5 / 5
	Total	18 / 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: 9 suspicious	Warning

	Total	13 / 16 Passed

Repository: aaron-he-zhu/aaron-marketing-skills
Path: social/host/social-quality-auditor/SKILL.md
Commit: 9df28a0

Reviewed: 4 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.