message-house-builder

Use when the user asks to "build a message house", "write a PR-FAQ for our launch", or "define the launch narrative and value pillars"; derives from the positioning canvas a message house — tagline, one-liner, three value pillars, per-persona proof points (each labeled Measured / User-provided / [needs source]) — plus a working-backwards PR-FAQ narrative spine (launch-day tense, empty-chair test, five external + five internal FAQs) and per-channel message angle packs (angles, not finished copy). Not for the positioning canvas itself — use positioning-mapper; not for finished blog posts or pages — use content-writer; not for ad or email units — use each discipline creative builder; not for claim adjudication — use offer-claims-registry. 消息屋/PR-FAQ/价值支柱/发布叙事

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

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 tightly scoped, well-sequenced instruction skill with explicit validation feedback loops and clear cross-skill handoffs. The main gaps are a trimmable scope-guard paragraph and the absence of a concrete fill-in output template for the deliverables.

Suggestions

Add a compact output template (tagline / one-liner / pillars / proof-point table / PR-FAQ / angle-pack) that the agent can populate directly, raising actionability without adding verbosity.

Tighten the scope-guard paragraph and drop the trailing Chinese summary echoed from the frontmatter to remove redundancy.

If detailed Output Voice banned-vocabulary lists or angle-pack schemas exist, move them into a references/ bundle file and link one level deep rather than describing them inline.

Dimension	Reasoning	Score
Conciseness	The body is lean, assumes Claude's competence, and avoids explaining basic concepts; a few dense glosses (the scope-guard paragraph, the repeated trailing Chinese summary) could be trimmed to fully earn every token.	4 / 5
Actionability	Numbered steps name concrete deliverables with specific constraints (e.g. 'launch-day tense', 'five external + five internal FAQs', 'angles, not finished copy'), but the instruction-only guidance lacks an explicit output template the agent could fill directly.	4 / 5
Workflow Clarity	A clear seven-step sequence with explicit validation checkpoints — verify L1 inputs (step 1), claims sweep (step 6), banned-word self-check with rewrite loop (step 7) — plus a 'Done when' gate and termination rules.	5 / 5
Progressive Disclosure	No bundle files exist alongside the skill; the body keeps overview-level content inline and signals one-level-deep external references (skill-contract.md, ramp-benchmark.md, SECURITY.md) clearly in a Reference Materials section, with minor organization gaps.	4 / 5
	Total	17 / 20 Passed

Description

92%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 precise, well-scoped description that pairs concrete deliverables with explicit trigger phrases and clear handoff boundaries to neighboring skills. Minor weakness is jargon density that could crowd out a few natural-language synonyms.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete deliverables — tagline, one-liner, three value pillars, per-persona proof points labeled by evidence type, a PR-FAQ spine (launch-day tense, empty-chair test, 5+5 FAQs), and per-channel angle packs — giving comprehensive coverage.	5 / 5
Completeness	Explicitly answers both what (derives message house / PR-FAQ / angle packs with named components) and when (opens with 'Use when the user asks to...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural trigger phrases users would actually say ('build a message house', 'write a PR-FAQ for our launch', 'define the launch narrative and value pillars'), but the surrounding vocabulary is domain-jargon heavy and a few common synonyms are absent.	4 / 5
Distinctiveness Conflict Risk	Names a clear niche and explicitly excludes four adjacent skills ('Not for the positioning canvas itself — use positioning-mapper; ... use content-writer; ... use offer-claims-registry'), minimizing 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: 21 suspicious	Warning

	Total	13 / 16 Passed

Repository: aaron-he-zhu/aaron-marketing-skills
Path: launch/assemble/message-house-builder/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.