CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

seo-project-setup

Populate a project's shared OpenSEO context — site scope, goals, positioning, competitors, key pages, and preferences — plus MCP checks and Search Console intake.

Quality

82%

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

88%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-engineered, self-contained workflow: concrete MCP tool contracts, a clearly sequenced 10-step interview with validation and error-recovery branches, and honest guardrails against fabricating state. The only structural note is that everything lives inline in one file with no progressive-disclosure layer.

DimensionReasoningScore

Conciseness

The body is dense and instructional — exact tool calls, patch-op shapes, and file-naming conventions with almost no padding or explanation of concepts Claude already knows. Minor asides (the Tone section, "GSC is the richest first-party signal: ...") could be trimmed, keeping it just below the 'every token earns its place' anchor.

4 / 5

Actionability

Guidance is copy-paste ready for an instruction-only skill: exact MCP tool signatures (`update_project_context(projectId, updates)`), concrete patch-op shapes (`{ section: "business_overview" | ... }`, `{ addCompetitors: [{ domain, name?, notes? }] }`), specific tool names for every branch, and literal CSV filenames like `gsc/queries-last-3-months.csv`. Specific examples cover the common cases throughout.

5 / 5

Workflow Clarity

Ten numbered steps in a logical dependency order (resolve projectId before any writes, read existing context before asking), with explicit validation checkpoints and feedback loops: "If the project list is ambiguous, ask the user", "If no project matches, offer to create one", "If the MCP is unavailable, tell the user to connect", and "do not claim Search Console is connected unless `get_search_console_performance` confirms it".

5 / 5

Progressive Disclosure

No bundle files exist, and the single-file body is cleanly sectioned with a scannable checklist, output template, and guardrails — nothing that clearly belongs in a separate reference file is inlined. It does not reach 5 because there are no well-signaled references at all and the ~190-line body keeps everything at one level, leaving minor organization headroom (e.g. the GSC export details or next-workflow table could live in a reference file).

4 / 5

Total

18

/

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.

A specific, third-person description that clearly states what the skill populates, with good natural domain keywords. Its main weakness is the absence of any 'Use when...' trigger clause, so a user (or Claude) has to infer when to invoke it, and the word "SEO" itself never appears.

Suggestions

Add an explicit trigger clause, e.g. "Use when starting work on a new SEO project or website, when project context is missing or stale, or when the user asks to set up their OpenSEO project."

Include the term "SEO" and common user phrasings like "set up" or "new project" so the description matches how users naturally ask for this skill.

Mention re-runnability (e.g. "safe to re-run; merges into existing context") to further distinguish it from one-shot audit skills.

DimensionReasoningScore

Specificity

The description enumerates concrete content targets — "site scope, goals, positioning, competitors, key pages, and preferences" — plus distinct actions "MCP checks and Search Console intake". It stays below the 5 anchor because "Populate" is a single umbrella verb with modifiers rather than multiple independent concrete actions.

4 / 5

Completeness

The 'what' is clear and specific (populate the shared OpenSEO context with the listed sections), but there is no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines. It is not a 2 because the 'what' half is concrete and unambiguous, not vague.

3 / 5

Trigger Term Quality

Natural domain keywords are well covered ("positioning", "competitors", "key pages", "Search Console", "goals"), matching the 'good keyword coverage; a few natural terms missing' anchor. It never says "SEO", "set up", or "new project" — the most common phrasings a user would say — so it falls short of the 5 anchor's comprehensive synonym coverage.

4 / 5

Distinctiveness Conflict Risk

"Populate a project's shared OpenSEO context" carves a clear niche (context intake vs. audits or research), giving mostly distinct triggers. It stays at 4 rather than 5 because within the OpenSEO skill family the boundary with research/audit skills relies on implied intent, and the missing 'when' clause leaves minor overlap risk with closely related skills.

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

every-app/open-seo

Path

plugins/openseo/skills/seo-project-setup/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.