CtrlK
BlogDocsLog inGet started
Tessl Logo

keyword-research

Discover keyword opportunities, evaluate metrics and SERPs, and save/tag promising terms.

60

Quality

70%

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

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/keyword-research/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

75%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.

The body is a lean, well-structured, actionable workflow with concrete MCP tool usage and sensible guardrails; its main weakness is a duplicated Search Console procedure and the absence of an explicit validate-fix-retry loop around the batch save operation.

Suggestions

De-duplicate the striking-distance Search Console instructions — keep the full procedure in one place (e.g., the tools entry) and reference it from workflow step 1.

Add an explicit validation checkpoint before save_keywords (e.g., confirm the shortlist is deduped against list_saved_keywords, then re-confirm with the user) to form a validate-fix-retry loop.

Optionally extract the tool catalog and output-table spec into a references file so SKILL.md stays a lean overview, pushing progressive_disclosure toward 5.

DimensionReasoningScore

Conciseness

The body is efficient — concrete tool list, numbered workflow, table spec, and guardrails with no over-explanation of basics — but the striking-distance Search Console procedure is repeated in both the tools section and workflow step 1, keeping it short of anchor 5.

4 / 5

Actionability

Gives exact MCP tool names with concrete parameters ('1-5 seeds', '150 results', 'up to 700 keywords', 'filter average position 5-20 client-side', tag formats like 'topic:<topic>'), which is mostly executable guidance; not a 5 because no copy-paste-ready argument payloads are shown.

4 / 5

Workflow Clarity

A clearly numbered 1-10 workflow with checkpoints (list_projects fallback, 30-day dedup check before spending credits, explicit save confirmation, 'write unknown' guardrail) — matching anchor 4; not a 5 because there is no explicit validate-fix-retry feedback loop for the batch save step.

4 / 5

Progressive Disclosure

Single well-organized SKILL.md with clear sections (Goal, Inputs, Project context, Tools, Workflow, Output, Guardrails) and no nested references; at ~80 lines it exceeds the under-50-line simple-skill exception, so it sits at anchor 4 rather than 5.

4 / 5

Total

16

/

20

Passed

Description

66%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.

The description is concrete and domain-specific with three clear actions and reasonable trigger terms, but it lacks any explicit 'Use when...' guidance, capping completeness at the midpoint.

Suggestions

Add an explicit 'Use when...' clause naming trigger phrases (e.g., 'Use when researching keywords, planning SEO content, or evaluating search demand').

Include more natural synonyms users say — 'SEO', 'search volume', 'keyword difficulty' — to broaden trigger coverage.

Tighten the niche signal by mentioning the SERP/metric evaluation stage that distinguishes this from generic content planning.

DimensionReasoningScore

Specificity

Names the keyword-research domain and three concrete actions — 'Discover keyword opportunities, evaluate metrics and SERPs, and save/tag promising terms' — matching anchor 4's several-specific-actions profile; not a 5 because coverage is moderate rather than comprehensive.

4 / 5

Completeness

It has a clear 'what' (discover, evaluate, save/tag) but no explicit 'when'/'Use when...' trigger clause, which per the judging guidelines caps completeness at 3 rather than 4.

3 / 5

Trigger Term Quality

Includes natural terms users say ('keyword opportunities', 'metrics', 'SERPs', 'save/tag') but omits common synonyms like 'SEO', 'search volume', and 'keyword difficulty', so it sits above anchor 3 yet short of comprehensive anchor 5.

4 / 5

Distinctiveness Conflict Risk

The keyword/SERP framing carves a mostly distinct niche with only minor overlap risk against broader SEO or content-research skills; not a 5 because some overlap with general SEO skills remains.

4 / 5

Total

15

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
every-app/open-seo
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.