keyword-research

Use when the user asks to "find keywords", "挖词", or "搜什么词"; prioritizes search volume, keyword difficulty, intent, and topic clusters from provided or connected data. Not for competitor-relative coverage gaps — use content-gap-analysis. 关键词研究/内容选题

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, actionable skill body with an explicit 8-phase workflow, a concrete completion checklist, exact scoring formulas, and clean one-level-deep references. The main improvement area is tightening the Data Sources prose and adding an explicit validate/retry loop to the workflow.

Suggestions

Tighten the Data Sources paragraphs (striking-distance shortcut, keyless SERP/pageviews sampling) into terser bullet form to lift conciseness.

Add an explicit validate→fix→retry feedback loop (e.g. re-checking intent against live SERP and re-scoring) to the workflow so workflow_clarity can reach 5.

Inline one or two concrete expansion-pattern examples or a mini intent table in the 8-phase section so the core phases are not solely deferred to references.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient—lean 8-phase list, an exact opportunity formula, and no padding with concepts Claude already knows—but the Data Sources prose paragraphs (e.g. the striking-distance shortcut and keyless SERV sampling) are wordy and could be trimmed; not a 5 due to these minor instances of over-explanation.	4 / 5
Actionability	It provides copy-paste-ready commands (full `python3 "${CLAUDE_PLUGIN_ROOT}/scripts/connectors/..."` invocations) and an exact scoring formula with Intent Value mapping, but the core 8-phase steps (Scope, Discover, Variations, Classify) are high-level one-liners that defer full templates to references; not a 5 because of those minor gaps in the inline workflow guidance.	4 / 5
Workflow Clarity	The 8 phases are clearly sequenced and announced as `[Phase X/8: Name]` with an explicit "Done when" completion checklist (volume + difficulty + intent per keyword, pillar + cluster grouping, ≥3 named opportunities) and a quality bar; not a 5 because there is no explicit validate→fix→retry feedback loop, leaving a minor validation gap.	4 / 5
Progressive Disclosure	SKILL.md is a clear overview pointing to one-level-deep, well-signaled references (instructions-detail, keyword-intent-taxonomy, topic-cluster-templates, keyword-prioritization-framework, example-report), all of which exist as real files and are listed with descriptions in a Reference Materials section; not below 5 because structure and navigation are clean.	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 concrete capability dimensions with explicit natural-language triggers (including Chinese synonyms) and a clear boundary against a sibling skill. Minor room to broaden English trigger variations within the description field itself.

Dimension	Reasoning	Score
Specificity	The description names the domain and several concrete prioritization dimensions ("search volume, keyword difficulty, intent, and topic clusters"), listing multiple specific capabilities with only minor coverage gaps; not a 5 because it uses a single verb ("prioritizes") over a list of metrics rather than multiple distinct concrete actions.	4 / 5
Completeness	It explicitly answers both "what" ("prioritizes search volume, keyword difficulty, intent, and topic clusters") and "when" ("Use when the user asks to...") with concrete trigger phrases, satisfying the anchor for a clear what-and-when with explicit triggers; not below 5 because neither half is vague or missing.	5 / 5
Trigger Term Quality	It includes natural trigger phrases users would say ("find keywords", "挖词", "搜什么词", plus "关键词研究/内容选题") with cross-language synonyms; not a 5 because a few natural English variations (e.g. "keyword ideas", "what to write about") appear only in when_to_use rather than the description itself.	4 / 5
Distinctiveness Conflict Risk	The explicit boundary clause ("Not for competitor-relative coverage gaps — use content-gap-analysis") carves out a clear niche with distinct triggers and minimal conflict risk; not below 5 because the deconfliction guidance is concrete and named.	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: 8 suspicious	Warning
referenced_paths_exist	Referenced path issues: 1 missing, 1 deeper-than-1-level	Warning

	Total	12 / 16 Passed

Repository: aaron-he-zhu/aaron-marketing-skills
Path: seo-geo/survey/keyword-research/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.