What does this skill do, and when should you use it?
Audience Belief Mapper is a Narrative / Trace skill in Aaron Marketing Skills. It focuses on a defined beachhead and organizes buyers’ existing beliefs and mental models, recurring objections with reframe candidates, and the JTBD forces behind switching: push, pull, anxiety, and habit. Each item is tied to user-provided evidence and labeled Measured, User-provided, or Estimated. It is a fit for teams preparing brand narrative work, but it does not build personas, reconcile positioning, adjudicate claims, or score TALE.
It reads user-provided interview transcripts, win-loss notes, sales-call summaries, and support tickets, plus an audience-mapper persona base and read-only claims ledger when available. It extracts buyer beliefs and verbatim language, builds an objection / frequency-source / reframe-candidate table, maps evidence to push, pull, anxiety, and habit, and marks unverified quotes or comparative statements as “[needs source]”. It produces a belief map, four-forces map, open-source-needed list, and standard handoff summary; with authorization, it can also save working memory or submit registry-event proposals.
- A product marketing team has interview notes and wants to understand how its beachhead views the problem and available alternatives.
- A sales team is reviewing lost deals and needs to separate the forces that create urgency from the forces that preserve the status quo.
- A brand narrative team keeps hearing the same objection and wants to preserve the buyer’s wording while drafting reframe candidates.
- A research team wants to synthesize support-ticket concerns into raw material for narrative development.
How do you install this skill?
- Do not treat Estimated reframes or user quotations as verified facts; comparative and product claims require later registry review.
- Confirm authorization for persona, interview, and win-loss materials, and redact personal or sensitive commercial information before processing.
- Verify that the host supports registry-events.py, the required memory paths, and authorization capabilities; otherwise produce a draft only and do not write.
- Note the inconsistency between the README's 18.0.0 version and SECURITY.md's statement that 17.x is the supported line.
- Shell / CLI
- Local filesystem
Python standard library runtime
Install the collection in Claude Code with /plugin marketplace add aaron-he-zhu/aaron-marketing-skills, then /plugin install aaron-marketing@aaron. On an Agent Skills-compatible host, run npx skills add aaron-he-zhu/aaron-marketing-skills, or clone https://github.com/aaron-he-zhu/aaron-marketing-skills. The skill file is narrative/trace/audience-belief-mapper/SKILL.md.
tmp="$(mktemp -d)"
git clone --depth 1 https://github.com/aaron-he-zhu/aaron-marketing-skills.git "$tmp"
mkdir -p ~/.claude/skills
cp -R "$tmp/narrative/trace/audience-belief-mapper" ~/.claude/skills/
rm -rf "$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?
Confirm the target beachhead, then provide interview or win-loss evidence. Example: Map the beliefs, objections, and switching forces for [product]'s beachhead. Here are [N] interview / win-loss notes: [paste]. If the persona base is missing, the skill routes to audience-mapper before mapping beliefs for a segment.
What are this skill's strengths and limitations?
- Provides a concrete structure covering beliefs, objection reframes, and all four JTBD switching forces.
- Requires each item to be tied to specific evidence and labeled by evidence status.
- Preserves verbatim win-loss language and flags unsupported quotes or comparisons.
- Has a defined handoff to strategic-narrative-designer and the shared narrative registry workflow.
- Depends on user-provided interviews, win-loss notes, or comparable qualitative evidence.
- Stops when the audience-mapper persona base is missing.
- Does not handle demographic or firmographic profiling, positioning reconciliation, claim adjudication, or TALE scoring.
- Public review language is limited to excerpts the user provides; optional connector retrieval is labeled proxy rather than Measured.
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 |
|---|---|---|---|---|
| Audience Belief Mapper this page | 57 · Use with care | ★ 3k | 12d ago | Apache-2.0 |
| Category Narrative Map | 58 · Recommended | ★ 3k | 12d ago | Apache-2.0 |
| Narrative Quality Gate | 60 · Recommended | ★ 3k | 12d ago | Apache-2.0 |
| Message Test Designer | 61 · Recommended | ★ 3k | 12d ago | Apache-2.0 |
| Brand Language Codifier | 63 · Recommended | ★ 3k | 12d ago | Apache-2.0 |
Compared with audience-mapper, this skill focuses on beliefs, objections, and switching forces rather than demographic or firmographic profiling. Compared with positioning-truth-tracer, it does not reconcile a positioning canvas against shippable reality.
How did FollowSkills review this skill?
The skill treats interviews and scraped material as untrusted data, limits inputs to user-provided evidence, requires beachhead confirmation, and routes claims through authorized propose events rather than direct canonical writes. It also asks for confirmation before saving or promoting memory. Deducted 7 points because handling of sensitive interview or support data lacks explicit redaction, retention, and access-control rules, and rollback is not fully specified in this skill.
Instructions, inputs, outputs, completion criteria, and termination rules are comparatively explicit, including a stop-and-route behavior when persona evidence is missing. Deducted 12 points because this static review found no skill-specific tests or real failure-run evidence covering key paths; authorized writes, referenced paths, and host capabilities introduce environment-dependent failure modes.
Triggers, audience, input materials, output shape, and non-fit boundaries are clear. Core operation does not require overseas connectors, and Chinese labels and metadata are present. Deducted 4 points because handling of missing interviews, conflicting evidence, very small samples, and non-English material is not sufficiently defined; mainland-China reachability is supported mainly by manual input rather than demonstrated environment validation.
The skill includes versioning, Apache-2.0 licensing, quick starts, contract, data sources, instructions, references, handoff, next-skill guidance, and limitation disclosures; the README adds installation and architecture context. Deducted 5 points because there is no skill-specific changelog, clearly assigned maintenance owner, or update path; README and SECURITY contain a version-line inconsistency between 18.0.0 and supported 17.x; the handoff format depends on an external reference not supplied here.
The expected deliverable is concrete: a belief map, objection-and-reframe table, JTBD four-forces map, evidence lines, labels, and needs-source list, suitable for downstream narrative work. Deducted 9 points because no representative output or third-party execution evidence is included; usefulness depends heavily on complete user-provided notes and an existing persona base, while reframes still require later review.
The skill requires evidence-line tracing, verbatim language, Measured/User-provided/Estimated separation, and needs-source routing for unverified claims, providing some auditability. Deducted 6 points because evidence remains primarily user-supplied, with no independent corroboration, fixed examples, skill-specific tests, or third-party results; repository tests cover shared architecture and artifact validation, not this skill's key paths.
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 →