research-keywords

Finds high-value SEO and GEO keywords using web search, AI analysis, and optionally paid tools like Ahrefs or Semrush. Produces a validated keywords.csv file with a fixed schema for downstream pipeline consumption.

Quality

68%

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

Fix and improve this skill with Tessl

tessl review fix ./research-keywords/SKILL.md

Quality

Content

77%

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

The body is highly actionable with concrete search patterns, an exact CSV contract, and a well-sequenced five-phase workflow with validation checkpoints. Its main weaknesses are repetition that hurts conciseness and a dangling reference to a schema file not present in the bundle.

Suggestions

State the 'target keywords must be 1-3 words' rule once in the Rules section and reference it from Phase 2 instead of repeating it five times.

Either ship keywords.csv.schema.md in references/ and link to it, or inline the schema inline and stop referencing it as an external file, to resolve the dangling reference.

Consolidate the raw-CSV output contract into Phase 5 and keep only a one-line pointer in the intro to remove the duplicated explanation.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and actionable, but it repeats the '1-3 words' rule five times (lines 14, 72-75, 96, 105, 309) and restates the raw-CSV output contract in both the intro and Phase 5, with occasional justifying fluff ('they waste space on the list and won't rank') — matching 'mostly efficient but could be tightened' rather than lean.	2 / 3
Actionability	Provides concrete search-query patterns per method, an exact CSV header, a full column contract with allowed enum values, and a copy-paste-ready example with a pre-emit checklist — fully executable, copy-paste ready guidance.	3 / 3
Workflow Clarity	Five phases are clearly sequenced with explicit user-confirmation checkpoints ('Ready to move to Phase 2?'), a dedicated validation/pruning phase, and a pre-emit checklist that functions as a feedback loop for the batch CSV artifact.	3 / 3
Progressive Disclosure	The scripts/ directory is referenced and its files (keyword-explorer.mjs, serp-analyzer.mjs) exist as one-level-deep optional references, but keywords.csv.schema.md is referenced as a real file yet is absent from the bundle, and the otherwise-inline 310-line body is fairly monolithic — 'some structure but references not fully clean / content that could be separate is inline.'	2 / 3
	Total	10 / 12 Passed

Description

60%

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 states concrete, third-person capabilities and names specific tools, giving it strong specificity. It is held back by the absence of any explicit 'Use when...' trigger guidance and some jargon padding, which cap completeness and trigger-term quality at 2.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user needs an SEO/GEO keyword list for content planning or wants to validate keywords with Ahrefs/Semrush data.'

Trim jargon like 'high-value', 'downstream pipeline consumption', and bare 'GEO' in favor of natural phrasings such as 'keyword research' and 'search terms' a user would actually say.

Add a disambiguating cue (e.g. 'For full-question GEO/AI-citation targeting, use geo-content-research instead') to reduce conflict risk with the related GEO skill.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions in third person — 'Finds high-value SEO and GEO keywords', 'using web search, AI analysis, and optionally paid tools like Ahrefs or Semrush', and 'Produces a validated keywords.csv file with a fixed schema' — matching the level-3 anchor of several specific actions.	3 / 3
Completeness	It clearly answers 'what does this do' but provides no 'Use when...' clause or equivalent explicit trigger guidance, which per the judging guidelines caps completeness at 2.	2 / 3
Trigger Term Quality	Contains relevant natural terms ('SEO', 'keywords', 'Ahrefs', 'Semrush') but pads them with jargon ('high-value', 'GEO', 'downstream pipeline consumption') and omits common variations like 'keyword research' or 'search terms', so it sits at 'some relevant keywords but missing common variations' rather than full coverage.	2 / 3
Distinctiveness Conflict Risk	The SEO/GEO niche with named paid tools is somewhat specific, but the body explicitly notes overlap with a separate 'geo-content-research' skill and the description lacks explicit triggers to disambiguate, placing it at 'somewhat specific but could still overlap with similar skills' rather than a clearly distinct niche.	2 / 3
	Total	9 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: onvoyage-ai/gtm-engineer-skills
Path: research-keywords/SKILL.md
Commit: 3777930

Reviewed: about 19 hours 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.