audience-belief-mapper

Use when the user asks to "map what our buyers believe", "capture the objections we keep hearing", or "find the switching forces that move the beachhead"; produces a belief map of the beachhead — held beliefs and mental models, the recurring objections and their reframes, and the JTBD four forces (push of the problem, pull of the new, anxiety of switching, habit of the present) — each item sourced from interviews or win-loss notes (User-provided) and labeled Measured / User-provided / Estimated, with any unverified quote or comparative claim marked "[needs source]" and routed to the claims candidates, never adjudicated here. Not for demographic or persona profiling — use audience-mapper; not for the positioning canvas — use positioning-truth-tracer. 受众信念/异议地图/切换四力/流失语言

Quality

88%

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

77%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 body is well-structured and highly actionable with a clear sequenced workflow and verification gates, but it is not token-efficient: the same registry-routing and scope-guard language is repeated across several sections. Progressive disclosure is only moderate because, despite well-signaled links, the skill ships no actual bundle files and keeps all instruction content inline.

Suggestions

Replace the repeated "via an authorized operation: propose request to registry-events.py" boilerplate with a single defined shorthand (e.g. in the Skill Contract) and reference it, to cut ~6 redundant copies.

Move the detailed routing/claims-protocol specifics into a referenced file under references/ (which is currently absent) so the body stays a lean overview rather than restating governance in every section.

Consolidate the duplicated scope-guard content that appears in both the intro paragraph and the Scope guard section into one authoritative statement.

Dimension	Reasoning	Score
Conciseness	The phrase "via an authorized operation: propose request to registry-events.py" is repeated verbatim ~7 times and the scope/claims-routing guard is restated in the intro, Scope guard, Contract, and Save Results sections — domain-protocol boilerplate that could be tightened to a single reference. Not level 3 (lean/efficient) due to this repetition; not level 1 because it does not explain basic concepts Claude already knows.	2 / 3
Actionability	Seven numbered steps give concrete direction (read persona base from a named path, list objections with sourced frequency, separate push/pull/anxiety/habit each citing an evidence line) plus copy-paste-ready Quick Start prompt templates and a specific Measured/User-provided/Estimated labeling scheme. For an instruction-only skill the guidance is specific and executable.	3 / 3
Workflow Clarity	A clear 7-step sequence with an explicit stop-and-route checkpoint at step 1 (route to audience-mapper if no persona base), a verification gate in step 6 (Sweep the claims), and a "Done when" completion checklist. Not level 2 because validation/checklist guidance is explicit rather than implied.	3 / 3
Progressive Disclosure	References are well-signaled and one-level-deep (tale-benchmark.md, skill-contract.md, CONNECTORS.md, SECURITY.md, sibling skills), but no bundle files exist in references/scripts/assets to verify, and substantial instruction content is inline in one file rather than split into the bundle. Not level 3 because content is not actually separated into verifiable bundle files; not level 1 because navigation is clear with no deeply nested references.	2 / 3
	Total	10 / 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.

The description is strong across all four dimensions: it states concrete capabilities, gives three natural-voice triggers, covers both what and when, and explicitly distinguishes itself from sibling skills. Its main weakness is density — it is a single long run-on sentence packed with governance detail — but the rubric rewards specificity, triggers, and completeness, all of which are present.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — produces a belief map (held beliefs/mental models), recurring objections and reframes, and the JTBD four forces (push/pull/anxiety/habit), each labeled Measured/User-provided/Estimated with unverified claims marked [needs source]. Not level 2 because the action set is comprehensive rather than partial.	3 / 3
Completeness	Clearly answers both what (produces the belief/objection/four-forces map) and when (explicit "Use when the user asks to…" triggers), satisfying the explicit-trigger anchor. Not level 2 because when-guidance is explicit, not implied.	3 / 3
Trigger Term Quality	Three explicit quoted user-voice triggers — "map what our buyers believe", "capture the objections we keep hearing", "find the switching forces that move the beachhead" — are natural phrasings a buyer would say, matching the anchor's good-coverage bar despite surrounding marketing jargon.	3 / 3
Distinctiveness Conflict Risk	Explicit exclusions — "Not for demographic or persona profiling — use audience-mapper; not for the positioning canvas — use positioning-truth-tracer" — carve a clear niche unlikely to trigger the wrong skill.	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: 27 suspicious	Warning
referenced_paths_exist	Referenced path issues: 2 missing, 2 deeper-than-1-level	Warning

	Total	12 / 16 Passed

Repository: aaron-he-zhu/aaron-marketing-skills
Path: narrative/trace/audience-belief-mapper/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.