category-narrative-mapper

Use when the user asks to "map the category narrative", "tear down how competitors tell their story", or "find the language conventions in our market"; produces a category narrative map — the dominant stories and points of view in the category, its language conventions and framing clichés, and a per-competitor narrative teardown (arc, claimed onlyness, proof pattern) plus how each rival's messaging has shifted over time (scraped copy vs archived copy). Not for the positioning canvas itself — use positioning-mapper; not for the beachhead's beliefs and objections — use audience-belief-mapper; not for SERP keyword targeting — use keyword-research; not for claim adjudication — use offer-claims-registry. 品类叙事/竞争叙事拆解/语言惯例/叙事演变

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 body is a well-structured, multi-step instruction skill with explicit acceptance criteria and clean reference navigation. It loses points on conciseness (intro/scope-guard redundancy with the description) and actionability (specific scripts are named but never shown as executable invocations, leaving the teardown/drift steps reliant on inferred connector interfaces).

Suggestions

Show executable connector invocations (e.g., `python scripts/connectors/firecrawl.py <url>` and the expected output shape) in the teardown and drift steps so the guidance is copy-paste ready rather than relying on inferred connector interfaces.

Tighten the opening paragraph and 'Scope guard' — they restate the description's scope and non-goals; consolidate them to remove redundancy and reclaim tokens.

Add an explicit scrape-failure recovery loop (e.g., if a page 404s or robots.txt blocks the fetch, fall back to a Tavily proxy read or mark the row Estimated) so the workflow has a clear validate → fix → retry feedback path.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and task-specific (no basic-concept explaining), but the opening paragraph and the 'Scope guard' restate the description's scope/non-goals, and the TALE-framework positioning rationale is dense padding that could be trimmed.	2 / 3
Actionability	Names concrete tools and destinations ('scripts/connectors/firecrawl.py', 'memory/events/claims.ndjson', 'operation: propose request to registry-events.py') but never shows executable invocation syntax, and the Quick Start uses placeholder prompts rather than copy-paste-ready commands, so key operational detail is missing.	2 / 3
Workflow Clarity	A clear 7-step numbered sequence (confirm → name stories → catalog language → teardown → trace drift → assemble → hand off) with explicit acceptance checkpoints in 'Done when', a 'Robots pre-flight applies to every scrape' gate, and a Measured/User-provided/Estimated labeling discipline.	3 / 3
Progressive Disclosure	Well-organized into labeled sections with a 'Reference Materials' list giving one-line descriptions of one-level-deep references (tale-benchmark.md, CONNECTORS.md, SECURITY.md, sibling skills); no bundle files exist in the skill directory itself, so the cross-collection references are legitimately one level deep and clearly signaled.	3 / 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.

A strong description: it states concrete capabilities, opens with natural trigger phrases a user would say, covers both what and when, and explicitly disambiguates four neighboring skills to avoid misfires. It uses the standard third-person/trigger form rather than first or second person, so no voice penalty applies.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'produces a category narrative map', 'a per-competitor narrative teardown (arc, claimed onlyness, proof pattern)', 'how each rival's messaging has shifted over time (scraped copy vs archived copy)' — matching the 'lists multiple specific concrete actions' anchor.	3 / 3
Completeness	Explicitly answers both 'what' ('produces a category narrative map — the dominant stories...') and 'when' ('Use when the user asks to...') with explicit triggers, matching the top anchor.	3 / 3
Trigger Term Quality	Quotes natural user phrasings ('map the category narrative', 'tear down how competitors tell their story', 'find the language conventions in our market') that a user would actually say, giving good coverage of natural terms.	3 / 3
Distinctiveness Conflict Risk	Explicitly carves out four adjacent skills ('not for the positioning canvas... use positioning-mapper; not for... audience-belief-mapper; not for SERP keyword targeting... keyword-research; not for claim adjudication... offer-claims-registry'), giving 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: 33 suspicious	Warning
referenced_paths_exist	Referenced path issues: 8 missing, 8 deeper-than-1-level	Warning

	Total	12 / 16 Passed

Repository: aaron-he-zhu/aaron-marketing-skills
Path: narrative/trace/category-narrative-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.