SKILLEMALL.ai

CF siteagent-elementor-studio

Helps with WordPress + Elementor work via the elementor-mcp MCP server — building new pages, editing existing ones, inspecting site state, or exploring what's possible. Auto-detects Elementor Pro (native Form, Theme Builder, Loop Grid, Popups, Dynamic Tags, Sticky/Motion vs free-tier workarounds) AND the page engine (classic vs Elementor 4 atomic/V4 — atomic uses add-flexbox/add-atomic-* tools since classic writes don't persist on a V4 page). Detects ACF + Crocoblock/JetEngine for dynamic-data binding (Tier-0; bind ACF via Pro dynamic tags, place Jet widgets via add-widget with runtime-verified types). On atomic (V4) sites, authors the Elementor 4 design system — Global Classes, Variables (design tokens), and per-element Interactions — and recovers from the fork's schema-in-error and governance responses. Asks what the user wants before acting. Use when the user references the Elementor MCP, invokes `/siteagent-elementor-studio`, or runs `mcp__elementor__elementor-mcp-*` tools. Also covers initial install of the MCP Adapter + elementor-mcp plugins, app-password auth wiring, schema-loading discipline, and the widget-vs-HTML decision tree. SKIP for Bricks, Divi, Beaver Builder, or non-Elementor WordPress builds.

Not recommendedcritical or high security findings
ClawHub Agent Skills author: Ben Kalsky v1.6.0 MIT-0 20 files · 1 script body ≈ 9 347 tokens Open the sourceclawhub.ai analyzed 31 h ago

Helps with WordPress + Elementor work via the elementor-mcp MCP server — building new pages, editing existing ones, inspecting site state, or exploring what's…

As a process F 47/100 · Will not run — References files that are not bundled: references/verticals/{dental,salon,car-wash,local-business,portfolio}.md

IntegrationWordPressAI and agentstype and topics are labelled automatically from the skill text
JSON
Technical rating
C
67/100
safety, quality, tests
Safety 60%
82
Quality 40%
44
Run on models
none yet
Process rating
F
47/100
Will not run
References files that are not bundled: references/verticals/{dental,salon,car-wash,local-business,portfolio}.md
Tools and files w 18
0
Result and completion w 14
0
Inputs and preconditions w 11
0
the three weakest of ten parameters · all ten

What is at stake

The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.

Exfiltration
If you install

The instructions or scripts send data out: environment variables, keys, file contents, chat history. You may never notice, because the agent performs the upload as "part of the task".

For the author

If the upload is not needed for the task, remove it: catalogs flag such skills and delist them. If it is needed, name the destination explicitly, say what leaves the machine, and give the user a switch.

How to improve

  1. Address the high-severity findings: each costs 18 safety points. If one is a false positive, add the rule id to guard.allow in spec.yaml.
  2. Shorten the description to 1024 characters.
  3. The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
  4. The text references files that are not there: add them or drop the references.
For the model run — optional
  • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
  • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

Guard findings · 1

  • high Exfiltration exfil-send-secrets-to-url SKILL.md:502
    Instruction to send secrets/history to an external endpoint (destination host is a configured variable)
    **Live host (cPanel/Cloudways/Kinsta/etc.):** Plugin install via WP Admin → Plugins → Add New → Upload Plugin (manual upload of the two zips). Auth is the same — REST API + Application Password. **MCP
    variable host

Files scanned: 20. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • error description-long description is 1229 chars, limit 1024
  • warning body-long SKILL.md body ≈ 9347 tokens (recommended < 5000); move details to references/
  • warning missing-ref reference to a missing file: references/verticals/{dental,salon,car-wash,local-business,portfolio}.md
  • note frontmatter-key unknown frontmatter key "permissions"

Process rating: all ten parameters 47/100

Will not run. References files that are not bundled: references/verticals/{dental,salon,car-wash,local-business,portfolio}.md
  • 0Tools and files. 1 referenced file(s) missing: references/verticals/{dental,salon,car-wash,local-business,portfolio}.md
  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 40Execution cost. Instruction body is 9347 tokens: crowds the task out of the window
  • 60Steps. 94 steps, 5 vague phrases
  • 100When it triggers. States when to use and when not to
  • 100Failures and branches. 4 branches, has a failure section
  • 100Consistency. Name and required fields are in place
  • 100Running it twice. Mutating operations check current state
  • 100Progress reporting. Reports progress
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low 24 top-level sections: this looks like several domains in one skill
  • low The response is described with custom markup (7 tags): a typed call is more reliable

Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

Quality signals

  • +5Description has no quoted example phrases that should trigger the skill
  • +4Description does not say when NOT to use the skill (false activations)
  • +3Description length 1229: 120–800 characters recommended
  • +3Output format is not stated: the model decides each time
  • +2Single-language instructions
  • +4Structure: 38 headings
  • +3Step-by-step instructions: 94 items
  • +4Has examples (9 code blocks)
  • +4Reference files are cited in the instructions (12 of 12)
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 44.

External checks

ClawHub: suspicious
The skill is openly designed to control a WordPress/Elementor site, but it installs mutable plugin code and stores a reusable site password, so it should be reviewed carefully before use.
LLM: suspicious (high) · 13 Sept 2026