narrative-quality-auditor

Use when the user asks to "audit our brand narrative" or "is this message on-canon"; runs separate typed TALE truth, system, or effectiveness profiles and never averages them into one composite. Checks differentiation, canon, landing consistency, and evidence integrity. Not for launch readiness — use launch-readiness-auditor; not for social operations — use social-quality-auditor. 品牌叙事分层审计/发布前一致性放行

Quality

81%

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

67%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-organized, lean auditor skill body with a clear sequenced workflow, explicit validation checkpoints, and sensible progressive disclosure into bundled reference files. Its main weakness is actionability: concrete executable steps are deferred to external runtime/scorer references rather than given inline.

Suggestions

Inline one minimal concrete invocation example (e.g., the exact command or call shape to run the typed scorer for one profile) so Claude can execute without first loading a runtime reference.

Reconcile the mixed reference paths — standardize on either `references/` (bundled) or `../../../references/` (root) per path so navigation is unambiguous.

Make at least one validation checkpoint a concrete verify-and-retry loop (e.g., 'run validate-audit-artifact.py; if it fails, fix the flagged field and re-run') rather than describing validation abstractly.

Dimension	Reasoning	Score
Conciseness	The body is dense and mostly lean, assuming Claude's competence with terse instructions ('Declare target, profile/mode, brand scope...'), but some sentences are tightly packed with jargon and version markers that could be trimmed for clarity.	4 / 5
Actionability	It provides concrete procedure guidance (profile procedures, veto IDs TALE-T1/A1/L1/E1, persistence paths) but the executable parts are largely routed to external runtime references and typed scorers rather than copy-paste-ready commands, leaving gaps in directly executable detail.	3 / 5
Workflow Clarity	A clear sequenced workflow is present (declare inputs → runtime reads → profile procedure → report/verdict → validation checkpoints → persistence) with explicit validation checkpoints, though some checkpoints are described abstractly rather than as concrete verify-and-retry steps.	4 / 5
Progressive Disclosure	Content is well-structured into clearly labeled sections with one-level-deep references to bundled files (auditor-runtime.md, auditor-runbook.md, scoring-semantics.md, tale-benchmark.md), though references are split between relative `../../../references/` and local `references/` paths which adds minor navigational friction.	4 / 5
	Total	15 / 20 Passed

Description

95%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 actions, natural trigger phrases, explicit what/when guidance, and clear exclusions that distinguish it from sibling auditors. Minor specificity gaps keep it from perfect coverage but it is well above the midpoint.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ('runs separate typed TALE truth, system, or effectiveness profiles', 'Checks differentiation, canon, landing consistency, and evidence integrity') but the actions are domain-abstract rather than fully enumerated, leaving minor gaps in coverage.	4 / 5
Completeness	Explicitly answers what it does ('runs separate typed TALE...profiles and never averages them') and when to use it ('Use when the user asks to audit our brand narrative or is this message on-canon'), plus clear exclusion guidance.	5 / 5
Trigger Term Quality	Includes natural phrases users would say ('audit our brand narrative', 'is this message on-canon') plus clear trigger keywords (differentiation, canon, landing consistency, evidence integrity) and explicit scope terms; comprehensive coverage.	5 / 5
Distinctiveness Conflict Risk	Explicitly names the skills it is NOT ('not for launch readiness — use launch-readiness-auditor; not for social operations — use social-quality-auditor'), carving a clear niche with minimal conflict risk.	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: 9 suspicious	Warning

	Total	13 / 16 Passed

Repository: aaron-he-zhu/aaron-marketing-skills
Path: narrative/evaluate/narrative-quality-auditor/SKILL.md
Commit: 888dd38

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.