clickmax-pages
Use when the user wants to create, inspect, restyle, rebuild, clone, configure, or publish a native Clickmax-hosted page.
Install / Use
npx skills add bilhon-technologies/clickmax-skills --skill clickmax-pagesInstalls into whichever agent you are using.
SKILL.md
Installable skill definition
Quality Score
Category
Development & EngineeringSupported Platforms
Our assessment of clickmax-pages
clickmax-pages scores 60/100 on our quality scale, 4030th of 4,572 Development & Engineering skills we index.
Its SKILL.md is 6.6 KB long, split into 7 sections and no code examples: a thorough specification that gives an agent plenty to work with.
It has no GitHub stars yet, so there is no community track record; judge it on its content.
Maintenance, license and trust
- We could not determine when the repository was last updated.
- No license is declared. By default that means all rights are reserved: you can read it, but reusing or redistributing it is not clearly permitted. Ask the author before building on it commercially.
- Its trust signals score 68/100, with 3 cautions from licensing, adoption, age or documentation. These come from repository metadata, not a code audit — read the skill file before letting an agent act on it.
Safety scan
No issues foundOur scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands.
Automated pattern scan on 2026-10-09. It catches known dangerous patterns, not every risk — read a skill before letting an agent act on it.
clickmax-pages compared with similar skills
All 4 of these similar skills score higher than clickmax-pages; compare them before choosing.
| Skill | Score | Stars | Updated | Format |
|---|---|---|---|---|
| clickmax-pages (this skill)by bilhon-technologies | 60 | 0 | — | SKILL.md |
| ai-job-searchby MadsLorentzen | 100 | 45.3k | today | CLAUDE.md |
| claude-howtoby luongnv89 | 100 | 41.8k | 8d ago | CLAUDE.md |
| algorithmic-artby anthropics | 100 | 177.9k | 16d ago | SKILL.md |
| pptxby anthropics | 100 | 177.9k | 16d ago | SKILL.md |
Frequently asked questions
- How do I install clickmax-pages?
- Run
npx skills add bilhon-technologies/clickmax-skills --skill clickmax-pages. The install tabs above show the steps for each supported agent. - Which AI agents does clickmax-pages work with?
- It is written for Universal, as a SKILL.md file. Other agents that read the same format can often use it too.
- Is clickmax-pages safe to use?
- Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. It declares no license and scores 68/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
- Is clickmax-pages still maintained?
- We could not determine when the repository was last updated.
Skill content
View source on GitHubname: clickmax-pages description: Use when the user wants to create, inspect, restyle, rebuild, clone, configure, or publish a native Clickmax-hosted page.
When this applies
Any native Clickmax page job: discovery, inspection, authoring a page with real content, a targeted edit, a clone, configuration, checkout binding, or publication.
Scope boundary — pick the right skill first:
|Situation|Skill|
|-|-|
|Page already lives on a domain NOT connected to Clickmax (Framer, Webflow, own site)|clickmax-external-pages|
|Whole connected funnel with several pages and edges|clickmax-funnels|
|Offer, price, guarantee, deliverable|clickmax-offers|
|Form/quiz behavior, fields, logic|clickmax-forms-quizzes|
|One native page — content, visual system, structure, publish|this skill|
Key assumptions
- A page with real content is authored as one full HTML document and imported.
pages_createalone produces a blank page or a template copy — no copy, no sections, no working form. - The authoring path is validated by machine, not by taste: recipe capabilities and every
requiredSectionsid are checked before import. Guessing the shape wastes a round trip. - Default design = the bundled editorial HTML bases. Explicit user references win; otherwise start from the matching resource in visual system, not a blank document or a catalog guess.
- The project's style guide is a fresh default (commonly light mode, blue/navy palette, small type scale) until someone changes it, and no tool changes it. A dark/accent request that conflicts with it must be satisfied by an explicit local palette applied to every section — never by half-styled markup that lets bare tags inherit the default.
- Imported author scripts are stripped. Use native HTML/CSS interactions or the documented declarative motion contract.
- One capture form per page. Two forms record the lead twice and make the funnel's
form_submittrigger ambiguous. - Missing facts/assets → content discovery before authoring. Explicitly requested fictional samples stay visibly labeled in draft; replace/remove before publication. Never invent actual payment, delivery, contact or access links.
Thought process
- Resolve the target page first — existing page, new page in a project, or a page inside a funnel. Never act on a remembered id without a fresh lookup this turn.
- Classify the job: read/config · blueprint only · new page with content · targeted edit · explicit full rebuild · clone · publish.
- Narrow request on an existing page → smallest possible edit. Never regenerate unrelated sections.
- Resolve account facts and ask the unanswered content discovery questions. A request for the default design does not skip discovery.
- Pick the recipe, read its bundled HTML base (or the explicit reference), then select composition variants and map verified content into slots. Reuse the funnel palette.
- Author, validate, fix every error, import as draft.
- Publication is always a separate, explicitly approved step.
Execute guide
- Content discovery — ask only missing facts/assets, including proof and real next-step URLs: content discovery.
- Pipeline and tool ordering — recipes, manifest, generation context, validation error codes, target rules, clone, configuration, and publication: authoring pipeline.
- Visual system — choosing the curated design, mapping it onto the injected tokens, type scale, color ramp, spacing, container, and breakpoints: visual system.
- Structure and copy — the mandatory spine, page jobs, section logic, and copy rules: sections and copy.
- Components — the CSS-only building blocks that survive import, plus the form, checkout, CTA, and motion contracts: components.
- Whop/Hotmart/Stripe/Pagar.me checkout — selling through the workspace's own account: integration check FIRST (no integration → instruct the user to connect it, never build without it), catalog walk,
externalCheckout, limits to tell the user: external checkout.
Report
- Open with the page job, target product/offer, and any material assumption made.
- Blueprint answers: sections in order as
section → job → final copy → visual treatment; cap long lists with+N more sections. - Build/edit answers: the visible sections, the chosen design, the responsive behavior, and exactly what changed. Do not dump markup unless asked.
- List missing business facts and assets as explicit gaps, named.
- Uncertain or failed save → say so and say what must be re-checked. Never claim success from a call that did not confirm.
- Before reporting a finished layout, inspect the imported draft on desktop and mobile; repair overflow, missing assets, typography and inactive actions. If no browser is available, disclose that visual review is pending. Publication remains a separate opt-in.
- After a create/publish that finishes the requested work, follow
clickmax-getting-startedto close with at most one opt-in offer of the next setup task.
Warnings
- Never publish without explicit consent, and never as part of a build step.
- Never replace a non-empty page unless the user asked for a full rebuild.
- Never hand-write checkout markup — the payment runtime looks for specific ids and a mistake breaks charging with no visible symptom.
- Whop/Hotmart/Stripe/Pagar.me checkout requested and the integration is missing or incomplete → instruct the user to connect/complete it in Integrações and stop; never deliver that page without its checkout.
- Never invent an image URL. A broken image in production is worse than a section without one.
- A validation call that returns
valid: falsemeans fix and revalidate — not try a different tool. - Warnings on a successful import are actionable: re-import the same page id with the corrected CSS.
Anti-patterns
- Recreating the default visual system from prose instead of adapting the bundled HTML base.
- A generic "modern and clean" direction with no concrete visual concept.
- Writing copy before deciding the page job, the audience's awareness level, and the objection being answered.
- The same centered card layout in every section.
- Padding the page with schedule, modules, instructors, certificate, and bonus blocks the user never gave data for.
- Regenerating the whole page for a color, spacing, or one-section request.
- Creating a blank page and telling the user to fill it in themselves.
Clickmax skill revision: 58919835e9a0
Related Skills
ai-job-search
45.3kThe job search that runs on your machine. AI job application framework built on Claude Code: evaluate postings, tailor CVs, write cover letters, prep interviews. Fork it and own it.
claude-howto
41.8kA visual, example-driven guide to Claude Code — from basic concepts to advanced agents, with copy-paste templates that bring immediate value.
algorithmic-art
177.9kCreating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems.
pptx
177.9kUse this skill any time a .pptx or .potx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx or .potx file (even if the extracted content will be used elsewhere, like in an em…
Trust signals
From repository metadata: license, adoption, age and documentation. Not a code audit — see the Safety scan above for what the skill file itself contains.
