message-system-architect

Use when the user asks to "author our durable brand message hierarchy", "build the brand message house that seeds the canon", or "define the main narrative, three pillars, and tagline for the whole brand"; produces the DURABLE brand message system — main narrative, three value pillars, per-persona proof points (each labeled Measured / User-provided / '[needs source]'), and the tagline/one-liner — that seeds the narrative-registry canon and from which every per-launch house derives. Not for a single launch's message house or PR-FAQ — use message-house-builder; not for claim adjudication — use offer-claims-registry; not for the change-narrative arc itself — use strategic-narrative-designer. 品牌消息屋/主叙事/三支柱/标语/持久叙事 canon

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

73%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-organized, workflow-driven skill body with strong sequencing and embedded validation, tailored to an instruction-only domain skill. Its main weakness is verbosity from repeated protocol incantations and restated scope, plus references that point outside the skill's own bundle.

Suggestions

De-duplicate the 'via an authorized operation: propose request to registry-events.py' wording by defining the proposal path once in the Skill Contract and referencing it by name in steps 8-9 and Save Results.

Collapse the restated canon/seeding/TALE framing so the intro paragraph, Scope Guard, and Skill Contract each carry distinct information rather than overlapping.

For the Reference Materials list, clarify which entries are sibling-skill/repo references versus in-bundle files, so a reader knows which paths are navigable from this skill alone.

Dimension	Reasoning	Score
Conciseness	Mostly structured and efficient, but noticeably padded — the phrase 'via an authorized operation: propose request to registry-events.py' recurs ~5 times and the canon/seeding/TALE framing is restated across the intro, scope guard, and contract sections, so it could be tightened.	3 / 5
Actionability	The 9-step instructions name concrete targets — exact memory paths, the Measured/User-provided/[needs source] labels, the banned-vocabulary and slop self-check steps, and registry-events.py — giving mostly executable guidance with only minor gaps; no code is appropriate for this instruction-only skill.	4 / 5
Workflow Clarity	A clearly sequenced 9-step process with explicit validation checkpoints — step 1 NEEDS_INPUT stop on missing inputs, step 6 banned-vocab/slop self-checks, step 7 internal-consistency pass, step 8 claims sweep — and a feedback loop ('Any contradiction is resolved by sharpening the hierarchy, not by softening wording').	5 / 5
Progressive Disclosure	Good section structure (Quick Start, Skill Contract, Data Sources, Instructions, Save Results, Reference Materials, Next Best Skill) with a dedicated one-level-deep reference list that is clearly signaled; the only gap is that the referenced files live in sibling skill/repo paths rather than in this skill's own (empty) references/scripts/assets bundle.	4 / 5
	Total	16 / 20 Passed

Description

100%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, well-crafted description: it pairs explicit quoted trigger phrases with a concrete enumeration of outputs and clear negative-scope boundaries against sibling skills. Third-person voice and the 'Use when …' clause are both present and correct.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete deliverables — 'main narrative, three value pillars, per-persona proof points (each labeled Measured / User-provided / [needs source]), and the tagline/one-liner' — giving comprehensive coverage of the skill's outputs.	5 / 5
Completeness	Explicitly answers both what ('produces the DURABLE brand message system …') and when ('Use when the user asks to …') with concrete trigger phrases, plus negative scope to disambiguate.	5 / 5
Trigger Term Quality	Provides three quoted natural trigger phrasings ('author our durable brand message hierarchy', 'build the brand message house that seeds the canon', 'define the main narrative, three pillars, and tagline for the whole brand') covering the synonyms a user in this domain would actually say.	5 / 5
Distinctiveness Conflict Risk	Clear niche (durable brand-level message hierarchy) with explicit disambiguation from message-house-builder, offer-claims-registry, and strategic-narrative-designer, minimizing wrong-skill triggering.	5 / 5
	Total	20 / 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: 42 suspicious	Warning

	Total	13 / 16 Passed

Repository: aaron-he-zhu/aaron-marketing-skills
Path: narrative/architect/message-system-architect/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.