CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

seo-coach

Enter a friendly OpenSEO coach mode that explains workflows, recommends next steps, and helps users use agents, web search, scraping, and MCP data effectively.

Quality

74%

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 ./plugins/openseo/skills/seo-coach/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

82%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 tightly written, highly actionable coaching guide with concrete tool names, example dialogues, and sequenced procedures. Its only real costs are a partially duplicated workflow list and the absence of failure-path guidance.

DimensionReasoningScore

Conciseness

The body is dense and imperative with almost no explanation of concepts Claude already knows (it never explains what SEO, MCP, or scraping are), but "Suggested next actions" substantially duplicates "What each workflow does", and "Guardrails" repeats response-format rules ("Keep replies under a screen"). Efficient with a few redundant sections that could be merged — not a 5 because of this duplication, not a 3 because there is no significant over-explanation or padding.

4 / 5

Actionability

For an instruction-only skill the guidance is fully concrete: exact MCP tool names (get_project_context, update_project_context, get_search_console_performance, list_reports), copy-paste handoff phrasing ("Want the full version? /seo-audit crawls the site..."), two complete example replies, and user-phrase-to-skill mappings that cover the common coaching cases. Absence of code is not penalized since the guidance is actionable throughout.

5 / 5

Workflow Clarity

The project-context procedure is a numbered 4-step sequence with checkpoints (call get_project_context first, check the research log before spending credits, write back on finish), and coaching patterns are sequenced by intent. Not a 5 because there are no explicit feedback loops for edge cases such as GSC not being connected or a workflow failing mid-run; not a 3 because sequences and checkpoints are explicit and no destructive/batch operations require validation.

4 / 5

Progressive Disclosure

No bundle directories (references/, scripts/, assets/) exist, so this scores against the actual single-file structure: clear, well-labeled sections that are easy to navigate. Not a 5 because the 11-entry workflow catalog in "What each workflow does" is inline reference material that could live in a separate reference file; not a 3 because organization is good and nothing is buried.

4 / 5

Total

17

/

20

Passed

Description

53%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 names a distinct, brand-anchored niche but reads more like a mode announcement than a trigger-optimized skill description: it has a moderately clear "what" and no "when" at all. Adding an explicit "Use when..." clause with natural SEO trigger terms would move it into the good-example range.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user asks for SEO guidance, wants to understand an OpenSEO workflow, or isn't sure what to do next with their site."

Include natural keywords users would actually say — "SEO help", "keyword research", "audit", "what should I do next" — not only tool names like "MCP data".

Replace the generic "helps users use agents, web search, scraping, and MCP data effectively" with concrete capabilities such as "recommends which workflow to run next and hands off to it".

DimensionReasoningScore

Specificity

"Enter a friendly OpenSEO coach mode that explains workflows, recommends next steps" names the domain and two concrete actions, but "helps users use agents, web search, scraping, and MCP data effectively" is generic filler rather than a specific capability. This matches the anchor for naming the domain with 1-2 concrete actions without comprehensive coverage; it is not a 4 because the third clause adds no concrete action, and not a 2 because two real actions are named beyond the domain.

3 / 5

Completeness

The "what" is stated (a coach mode that explains workflows and recommends next steps), but there is no "Use when..." clause or equivalent trigger guidance anywhere in the description. Per the judging guidelines, a missing "when" caps completeness at 3; it cannot be a 4 because the "when" is entirely absent rather than merely imprecise.

3 / 5

Trigger Term Quality

Natural terms like "coach", "workflows", "next steps", "web search", "scraping", and "MCP" are present, but common user phrasings — standalone "SEO", "audit", "keyword research", "ranking", "what should I do next" — are absent. This matches the anchor for some relevant keywords while missing common variations; it is not a 4 because core natural SEO terms a user would actually say are missing.

3 / 5

Distinctiveness Conflict Risk

"OpenSEO coach mode" anchors a clear brand-specific niche with minimal conflict risk, but the generic tail "helps users use agents, web search, scraping, and MCP data effectively" overlaps slightly with general agent/tool-coaching descriptions. This sits between "mostly distinct; minor overlap risk" and "clear niche with distinct triggers" — closer to 4 because the tail dilutes an otherwise distinctive trigger.

4 / 5

Total

13

/

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

every-app/open-seo

Path

plugins/openseo/skills/seo-coach/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.