CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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

84%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

92%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.

An exemplary instruction-style skill body: concrete executable commands, an explicit scoring model, sequenced phases with a done-when checklist, and a clean one-level reference bundle that keeps the overview lean. The only improvement space is trimming a few provenance/justification asides.

DimensionReasoningScore

Conciseness

The body is dense with non-obvious domain specifics (the Opportunity formula, the GSC API's lack of a position filter, funnel-stage patterns) rather than concepts Claude already knows; only minor padding exists, such as the provenance parenthetical "(Impact×Confidence + funnel-stage scoring adapted from an external SEO-ops competitive analysis)" — anchor 4, not 5, since a few lines could be trimmed.

4 / 5

Actionability

Copy-paste-ready commands with arguments (suggest.py --expand, firecrawl.py search --limit 10, pageviews.py --months 12), an exact scoring formula with intent-value constants (1/1/2/3), enumerated evidence labels, an exact save path, and a concrete rewrite rule ("Rewrite generic advice into a concrete keyword + volume + difficulty + reason") fully cover the common cases per anchor 5.

5 / 5

Workflow Clarity

Eight clearly sequenced phases announced as [Phase X/8], an explicit 'Done when' checklist (every keyword carries volume + difficulty + intent with source ref and evidence label), plus Unknown/NOT_SCORED handling rules provide explicit validation checkpoints; this is read-only research, so the destructive/batch validation cap does not apply.

5 / 5

Progressive Disclosure

A ~95-line overview with full templates, expansion patterns, and worked examples correctly split into five real one-level-deep reference files (verified present in the bundle), each clearly signaled with a one-line description in the Reference Materials section — clear navigation with only a single sibling cross-link.

5 / 5

Total

19

/

20

Passed

Description

73%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 well-crafted description with exemplary trigger phrasing (including bilingual quotes) and explicit boundary disambiguation against a sibling skill. Its main weakness is the thin 'what' clause: a reader learns it prioritizes and clusters keywords but not that it discovers/expands them or produces a keyword brief.

Suggestions

State the full capability set in the description, e.g. 'Discovers, expands, and scores seed keywords, then clusters them into pillar + cluster hubs and delivers a prioritized keyword brief', so the 'what' matches the skill's actual phases.

Add the missing high-frequency English trigger phrases already present in when_to_use ('keyword research', 'long-tail keywords', 'what to write about', 'search volume') to the description itself for broader natural-term coverage.

Name the concrete deliverable (prioritized keyword brief with volume/difficulty/intent per keyword) so users know what output to expect.

DimensionReasoningScore

Specificity

"prioritizes search volume, keyword difficulty, intent, and topic clusters from provided or connected data" names the domain with roughly two concrete actions (prioritize, cluster), but omits keyword discovery/generation and the deliverable, matching anchor 3 rather than the several-distinct-actions bar of anchor 4.

3 / 5

Completeness

Explicit "Use when the user asks to..." clause with concrete quoted triggers satisfies the 'when' fully, and a what-clause is present, but the what is a single clause that doesn't mention discovering keywords or producing a prioritized brief — between anchors 4 and 5.

4 / 5

Trigger Term Quality

Includes quoted natural triggers ("find keywords", "挖词", "搜什么词") plus named factors users would say (search volume, keyword difficulty, topic clusters), but misses common English variations like "keyword research", "SEO keywords", or "long-tail keywords" — good coverage, short of anchor 5's comprehensive synonym list.

4 / 5

Distinctiveness Conflict Risk

"Not for competitor-relative coverage gaps — use content-gap-analysis" explicitly disambiguates the nearest sibling skill, and the keyword-research niche has distinct triggers, giving minimal conflict risk per anchor 5.

5 / 5

Total

16

/

20

Passed

Validation

75%

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

CriteriaDescriptionResult

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: 9 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

Reviewed

Table of Contents

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.