What does this skill do, and when should you use it?
Strategic Narrative Designer is the Narrative/Architect skill in Aaron Marketing Skills. It builds a five-beat strategic change narrative: the old world, the undeniable shift, winners and losers under new rules, the promised land, and proof that the promised land is real. It reads a positioning truth set, a belief and objection map, approved claims, and existing narrative canon, while labeling evidence as Measured, User-provided, or [needs source]. It does not create the message house, write a pitch-deck narrative, or adjudicate claims.
Checks that the positioning truth set and belief map exist; reads approved claim wording and existing narrative canon; defines the status quo and its shaky assumptions; states a dated, evidence-grounded market shift; maps who benefits or is stranded under the new rules; describes a segment-relevant promised land; anchors each proof beat to labeled evidence; and produces the five-beat arc, objection reframes, a [needs source] list, and a standard handoff summary. Optional Tavily, GDELT, and Wayback connectors can supply proxy signals, which must never be labeled Measured.
- A brand team has completed positioning and audience-belief work and needs the durable narrative before building a message house.
- A category is changing visibly, and a marketing lead needs to explain why the old rules are becoming untenable.
- A product team wants to frame its market shift around customer value rather than a list of features.
- A narrative team needs to stress-test whether its promised-land story has evidence or unresolved proof gaps.
- A team needs a structured strategic arc to hand off to message-system architecture.
How do you install this skill?
- The positioning truth set and belief/objection map are mandatory inputs; if either is missing, the skill should stop rather than invent positioning or audience beliefs.
- Tavily, GDELT, and Wayback signals must remain proxy evidence, never Measured; every unverified proof point should enter the claims proposal flow for adjudication elsewhere.
- Before use, confirm that registry-events.py authorization, project-root scoping, and memory-write protections are actually deployed; this review was static and did not execute them.
- The skill declares version 18.0.0 while SECURITY.md identifies 17.x as the supported line; verify the supported release and update path before production use.
- Shell / CLI
- Network access
- Local filesystem
Python standard library scripts
The skill is distributed in the GitHub repository aaron-he-zhu/aaron-marketing-skills. It is marked compatible with Claude Code and compatible Agent Skills hosts. In Claude Code, run /plugin marketplace add aaron-he-zhu/aaron-marketing-skills, then /plugin install aaron-marketing@aaron. On a generic compatible host, run npx skills add aaron-he-zhu/aaron-marketing-skills -s aaron-strategic-narrative-designer. The repository can also be cloned with git clone https://github.com/aaron-he-zhu/aaron-marketing-skills.
tmp="$(mktemp -d)"
git clone --depth 1 https://github.com/aaron-he-zhu/aaron-marketing-skills.git "$tmp"
mkdir -p ~/.claude/skills
cp -R "$tmp/narrative/architect/strategic-narrative-designer" ~/.claude/skills/
rm -rf "$tmp"Generated from the source repository and skill path; it copies only this skill's folder. If the author's install steps above differ, follow those first. To scope it to one project, replace ~/.claude/skills with that project's .claude/skills.
How do you use this skill?
Provide a product or brand together with the positioning truth set and belief map. Example prompts include: Design the change narrative for [product/brand] from the positioning truth set and belief map. Give me the five-beat arc. and Frame the shift our category is going through: old world, the undeniable change, winners vs losers, the promised land, the proof. If either upstream input is missing, the skill should stop with NEEDS_INPUT rather than invent positioning or beliefs. It asks for confirmation before saving results to memory.
What are this skill's strengths and limitations?
- Uses a concrete five-beat structure that keeps the output focused on change and stakes.
- Requires traceable evidence labels and separates unsupported proof from established evidence.
- Has explicit scope boundaries around message systems, pitch narratives, and claim adjudication.
- Works at Tier 1 with user-provided data and does not require paid narrative tooling or MCP.
- Requires both a positioning truth set and an audience belief or objection map.
- Does not determine whether claims are true; unresolved proof must be handled by the claims registry.
- The supplied source does not provide independent tests or case studies for this individual skill.
- Market-change connectors produce proxy signals, not Measured evidence.
How does this skill compare with similar options?
Side by side with related skills; every score comes from the same FSRS standard.
| Skill | FS score | Stars | Last updated | License |
|---|---|---|---|---|
| Strategic Narrative Designer this page | 54 · Use with care | ★ 3k | 12d ago | Apache-2.0 |
| Positioning Truth Tracer | 61 · Recommended | ★ 3k | 12d ago | Apache-2.0 |
| Narrative Baseline Mapper | 57 · Use with care | ★ 3k | 12d ago | Apache-2.0 |
| Proof Point Packager | 60 · Recommended | ★ 3k | 12d ago | Apache-2.0 |
| Brand Message System Architect | 57 · Use with care | ★ 3k | 12d ago | Apache-2.0 |
How did FollowSkills review this skill?
The skill treats pasted notes and fetched content as untrusted data, limits writes to working memory and authorized proposal events, asks for confirmation before saving, and clearly describes data flow, evidence labels, and canonical-writer boundaries. Six points are deducted because the skill itself does not verify the authorization runtime, rollback behavior, or actual connector security, while permitting optional external market-signal connectors.
The five-beat procedure, NEEDS_INPUT behavior, termination rules, evidence labeling, and handoff are fairly coherent and diagnosable. Two points are deducted because it depends on several unprovided upstream skills, protocols, and runtimes, with no skill-specific tests, representative outputs, or reproducible abnormal-input validation; static scoring therefore stays at or below 10.
Triggers, audience task, inputs, outputs, non-fit boundaries, and next-skill routing are explicit, with some Chinese-language metadata. Six points are deducted because Chinese support is not complete, geo-relevance is declared low, access to Tavily, GDELT, and Wayback is not shown to be reliable from mainland China, and semantic exclusion rules are limited.
The documentation is layered across frontmatter, Quick Start, Skill Contract, Instructions, save rules, and handoff structure, and includes Apache-2.0 licensing, version, compatibility, and repository security guidance. Six points are deducted because the selected skill lacks a changelog, named maintenance responsibility, and a clear update path; SECURITY.md identifies 17.x as the supported current line while the skill and README state 18.0.0, creating version-governance inconsistency.
The expected output, five narrative beats, evidence states, objection reframes, source-needed list, and handoff are clearly specified and should produce a usable strategic narrative draft. One point is deducted because the main value is structured synthesis that still requires human fact checking and copy refinement, and no verified representative output is provided; static scoring therefore stays at or below 7.
The skill requires each proof beat to be labeled Measured, User-provided, Estimated, or proxy and traced to claims events, providing useful audit hooks. Two points are deducted because there are no skill-specific tests, third-party execution records, or independent reproduction materials; the supplied repository tests cover architecture and audit validation rather than this skill's key paths, so static scoring stays at or below 5.
Open a dimension to read why it scored that way
Evidence confidence：Low — Mostly static review, author material or a limited demo; useful for discovery, not high-risk decisions.
See the full review method →