content-gap-analysis

Use when the user asks to "find content gaps", "竞品写了什么", or "还应该写什么"; builds a competitor-relative coverage map of missing topics, keyword gaps, and editorial-calendar opportunities. Not for raw keyword demand discovery — use keyword-research. 内容缺口/选题规划

Quality

83%

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

78%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured, mostly lean skill body with executable connector commands, clear decision gates, and properly split one-level-deep references. Main weakness is that several workflow steps are directive rather than fully executable with explicit validation.

Suggestions

Tighten the Data Sources and Decision Gates sections — consolidate the connector blurbs into a single short pointer to CONNECTORS.md to trim tokens.

Add an explicit validation/checkpoint step in the 9-step Instructions (e.g. after Identify Keyword Gaps, confirm each gap carries a named competitor + volume estimate before proceeding) to make the workflow's quality bar enforceable.

Make the per-step guidance more executable by referencing the specific template block in references/analysis-templates.md each step should populate, rather than describing the step abstractly.

Dimension	Reasoning	Score
Conciseness	The body is largely lean — short Quick Start prompts, a compact 9-step list, and no padding with concepts Claude already knows — with only minor sections (Data Sources, Decision Gates) that could be tightened further.	4 / 5
Actionability	It provides concrete, executable commands (e.g. firecrawl.py map/scrape invocations with flags and limits) and a templated write path, though several of the 9 numbered steps remain high-level guidance rather than fully executable instructions.	4 / 5
Workflow Clarity	A clearly numbered 9-step sequence is reinforced by Decision Gates (stop/ask vs continue silently), a 'Done when' contract, and a quality bar, but per-step validation/feedback checkpoints are mostly implicit rather than explicit.	4 / 5
Progressive Disclosure	The body is an overview that points cleanly to three real one-level-deep references (analysis-templates.md, gap-analysis-frameworks.md, example-report.md), each signaled with a one-line purpose in the Reference Materials section, yielding easy navigation.	5 / 5
	Total	17 / 20 Passed

Description

87%Weight 40%Scale 1-5

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, third-person description that pairs a concrete 'what' with explicit bilingual trigger phrases and a clear negative boundary against a sibling skill. Minor room to expand the action list and synonyms.

Dimension	Reasoning	Score
Specificity	The description names several concrete actions — 'builds a competitor-relative coverage map of missing topics, keyword gaps, and editorial-calendar opportunities' — covering multiple specific outputs, though a few sub-activities are implied rather than enumerated.	4 / 5
Completeness	It explicitly answers both what (builds a competitor-relative coverage map) and when (an explicit 'Use when the user asks to...' clause with concrete triggers), plus a negative boundary ('Not for raw keyword demand discovery — use keyword-research').	5 / 5
Trigger Term Quality	It surfaces natural trigger phrases users would say — 'find content gaps', '竞品写了什么', '还应该写什么' — with good English/Chinese synonym coverage, but a few common phrasings (e.g. 'what should I write', 'competitor content') are absent.	4 / 5
Distinctiveness Conflict Risk	The competitor-relative gap niche is clearly staked out and the explicit 'Not for raw keyword demand discovery — use keyword-research' boundary minimizes conflict with adjacent skills.	5 / 5
	Total	18 / 20 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: 10 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: seo-geo/survey/content-gap-analysis/SKILL.md
Commit: 9df28a0

Reviewed: 4 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.