strategic-narrative-designer

Use when the user asks to "design our change narrative", "build the old-world-to-new-game story arc", or "frame the shift our category is undergoing"; produces a Raskin-style strategic narrative arc — old world → the undeniable shift → winners vs losers under the new rules → the promised land → proof the promised land is real — derived from the positioning truth set and the belief/objection map, feeding the TALE Architecture arc sub-item. Every proof beat is labeled Measured / User-provided / [needs source] and this skill never adjudicates a claim. Not for the message house hierarchy — use message-system-architect; not for the pitch deck narrative — use pitch-narrative-builder; not for claim substantiation — use offer-claims-registry. 变革叙事弧/旧世界/应许之地/战略叙事结构

Quality

85%

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

70%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 content is well-structured with a clear contract, sequenced workflow, and explicit validation checkpoints. Its main weaknesses are token-padding from repeated registry phrasing and dense link prose, plus a lack of executable examples or a concrete arc template that would lift actionability.

Suggestions

Add a concrete five-beat arc template or a short worked example so Claude can produce the output by filling rather than inferencing (lifts actionability).

Dedupe the recurring 'via an authorized operation: propose request to registry-events.py' phrasing into a single defined term referenced later, to tighten conciseness.

Provide a local reference file (e.g. references/arc-template.md) and point to it so detail-heavy sections can move out of SKILL.md, improving progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The body is information-dense but heavily padded with repeated scope guards, dense cross-skill link prose, and verbose registry/operation phrasing ('via an authorized operation: propose request to registry-events.py' appears multiple times), which could be tightened to respect the token budget.	2 / 3
Actionability	The seven numbered steps give concrete conceptual guidance and labeling rules, but there is no executable artifact (no template, no script call, no example arc) and the actual writing of the arc is described rather than templated, leaving key output details to inference.	2 / 3
Workflow Clarity	The Instructions section is a clear seven-step sequence with an explicit NEEDS_INPUT checkpoint in step 1, a self-check/empty-chair validation in step 7, and a 'Done when' contract plus termination rules, satisfying the explicit-validation anchor.	3 / 3
Progressive Disclosure	References are one level deep and well-listed in a Reference Materials section, but no bundle files (references/, scripts/, assets/) are present in this skill, so cross-skill links point outside the bundle and the SKILL.md carries a lot of inline detail that is not split into local reference files.	2 / 3
	Total	9 / 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.

This is a high-quality description: third-person, action-specific, with explicit 'Use when' triggers and strong negative-scoping that distinguishes it from sibling skills. It loses little to verbosity — the trailing Chinese summary and dense linking add length without harming clarity, but the core what/when contract is excellent.

Dimension	Reasoning	Score
Specificity	The description enumerates concrete actions (produces a five-beat arc: old world, shift, winners/losers, promised land, proof) and names concrete labeling behavior (Measured/User-provided/[needs source]), which matches the 'multiple specific concrete actions' anchor.	3 / 3
Completeness	It opens with an explicit 'Use when...' clause answering when, and the body answers what via the five-beat arc and labeled proof beats, satisfying both what AND when with explicit triggers.	3 / 3
Trigger Term Quality	Quotes natural user phrases verbatim ('design our change narrative', 'build the old-world-to-new-game story arc', 'frame the shift our category is undergoing'), which is exactly the kind of phrasing a user would say when needing this skill.	3 / 3
Distinctiveness Conflict Risk	Explicit negative-scoping ('Not for the message house... use message-system-architect; not for the pitch deck... use pitch-narrative-builder; not for claim substantiation... use offer-claims-registry') carves a clear niche, making wrong-skill triggering unlikely.	3 / 3
	Total	12 / 12 Passed

Validation

75%

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 — 12 / 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: 33 suspicious	Warning
referenced_paths_exist	Referenced path issues: 3 missing, 3 deeper-than-1-level	Warning

	Total	12 / 16 Passed

Repository: aaron-he-zhu/aaron-marketing-skills
Path: narrative/architect/strategic-narrative-designer/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.