Pixelesq

Pixelesq Agent Skills

Manage websites built on Pixelesq from any AI agent. Build and edit pages section by section, write content into collections, tune SEO and structured data, read Search Console and site analytics, manage redirects and images, restyle the theme, and publish when the user says so.

This repository is three things at once:

• Seven skills in the Agent Skills format, loaded by Claude Code, Cursor, Codex, Copilot, Gemini CLI, Goose and other compatible agents.
• Four specialist agents for Claude Code (and any platform that reads agents/*.md).
• The Pixelesq MCP connector, declared in .mcp.json: https://mcp.pixelesq.app/mcp, 68 tools, OAuth sign-in with your Pixelesq account.

Install

Claude Code (plugin)

/plugin marketplace add pixelesq/pixelesq-skills
/plugin install pixelesq@pixelesq

Then run /mcp and sign in to Pixelesq. The skills load on demand, the agents are available as @pixelesq:site-manager, @pixelesq:seo-specialist, @pixelesq:content-strategist and @pixelesq:design-consultant, and the connector is registered from .mcp.json.

Claude Code (connector only)

claude mcp add --transport http pixelesq https://mcp.pixelesq.app/mcp

Claude.ai and Claude Desktop

Settings, Connectors, Add custom connector, paste https://mcp.pixelesq.app/mcp, sign in.

ChatGPT

Settings, Apps & Connectors, Advanced, developer mode, Create, paste https://mcp.pixelesq.app/mcp.

Cursor

Install the plugin from the Cursor Marketplace, or add the server to mcp.json:

{ "mcpServers": { "pixelesq": { "url": "https://mcp.pixelesq.app/mcp" } } }

VS Code

{ "servers": { "pixelesq": { "type": "http", "url": "https://mcp.pixelesq.app/mcp" } } }

Other platforms

Clone the repository, point the agent's skills directory at skills/, and configure the MCP server URL https://mcp.pixelesq.app/mcp. Clients register dynamically or present a client ID metadata document; both are accepted.

Sign-in and scopes

The connector uses OAuth 2.1 with PKCE. Sign in with Google or with a Pixelesq email and the code it sends. A Pixelesq account with at least one project is required; sign up at https://app.pixelesq.ai.

Scopes are granted at sign-in and stamped into the token: projects:read, content:read, content:write, publish, analytics:read. A tool outside the grant answers with a refusal that asks the client to reconnect.

How edits stay safe

• Every save changes a draft. The live site changes only through publish_page, publish_partial, publish_entry, update_theme with publish: true and update_form_schema (a form has no draft), and the skills tell the agent to confirm first.
• Every save carries the lastVersion from the read before it; a stale version is refused instead of overwriting someone else's work.
• A publish carries expectedRevisionId and expectedHeadAnchor from the read the user reviewed, and refuses if the draft moved.
• Saves merge field by field, arrays replace whole, null clears a field. The agent only touches what the user asked for.
• Structural section edits (insert, remove, reorder, bind) take an idempotencyKey so a lost answer can be retried safely.

Skills

Skill	Use it for	References
getting-started	Connecting a client, the complete tool map, scopes, the safety rules
website-management	Pages, sections, partials, collections, entries, images, forms, domains	section guide (96 section types), site recipes, section catalog JSON
content-creation	Blog posts, landing pages, entries and section copy in the brand voice	quality rubric
design-theming	Theme colors, fonts, spacing, radius, appearance, section choice by look	font pairings, section visual guide
seo-optimization	Search Console, metadata, structured data, indexing, redirects	JSON-LD recipes, social meta specs
analytics-growth	Traffic, search performance, forms, AI referrals, Web Vitals
site-operations	Launch checks, publishing order, domains, recovery, monitoring	pre-launch checklist, webhook patterns

Agents

Agent	Focus
site-manager	Any site task end to end, delegating deep work to the specialists
seo-specialist	Audits, Search Console, metadata, structured data, redirects
content-strategist	Brand-aligned writing and entry creation
design-consultant	Theme, typography, composition, section swaps

The 68 tools

Area	Tools
Projects	list_projects, get_project, list_domains, search_content
Pages	list_pages, get_page, get_page_content, get_page_revisions, create_page, duplicate_page, update_page_meta, save_page_content, publish_page, unpublish_page, delete_page, revert_page_revision, revert_page_revision_to_version
Sections	list_section_types, get_section_defaults, get_section_content, save_section_content, insert_section, remove_section, reorder_sections, bind_section_to_collection, unbind_section_from_collection
Collections and entries	list_collections, get_collection, create_collection, update_collection_schema, list_entries, get_entry, create_entry, save_entry_content, update_entry, duplicate_entry, publish_entry, delete_entry
Partials	list_partials, get_partial_content, save_partial_content, publish_partial, unpublish_partial
SEO and analytics	get_gsc_connection_status, get_search_performance, get_page_index_status, get_all_page_statuses, inspect_url, get_site_analytics, get_ai_referral_analytics
Redirects	list_redirects, create_redirect, update_redirect, delete_redirect
Forms	list_forms, get_form, create_form, update_form_schema, get_form_submissions
Assets and images	list_assets, upload_asset, upload_image, search_stock_images, generate_image, get_image_job, get_imagegen_quota
Theme	get_theme, update_theme

Claude clients are offered 62 of these: the three AI image generation tools are withheld there and available in other clients. Read tools change nothing; write tools carry the hints that let clients ask before running them.

Repository layout

pixelesq-skills/
├── .claude-plugin/
│   ├── plugin.json            Claude Code plugin manifest
│   └── marketplace.json       lets the repo install as a marketplace
├── .cursor-plugin/plugin.json Cursor plugin manifest
├── .mcp.json                  the connector for Claude Code (http transport)
├── mcp.json                   the same connector in Cursor's format
├── AGENTS.md                  context for agents that read AGENTS.md
├── CHANGELOG.md
├── agents/                    four specialist agents
├── assets/logo.svg
├── scripts/generate-section-guide.mjs
└── skills/
    ├── getting-started/
    ├── website-management/    references: section-catalog.json, section-guide.md, site-recipes.md
    ├── content-creation/      references: quality-rubric.md
    ├── design-theming/        references: font-pairings.md, section-visual-guide.md
    ├── seo-optimization/      references: json-ld-recipes.md, social-meta-specs.md
    ├── analytics-growth/
    └── site-operations/       references: pre-launch-checklist.md, webhook-patterns.md

Keeping it current

• The section guides are generated. Refresh skills/website-management/references/section-catalog.json from the connector's list_section_types (all groups, full detail), then run node scripts/generate-section-guide.mjs.
• The tool map mirrors the connector's README, which is generated from the tool registry.
• Validate before publishing: claude plugin validate .
• The OpenAI plugin portal takes the skills as a ZIP: node scripts/build-openai-bundle.mjs writes dist/pixelesq-openai-plugin.zip (an Agent Plugins manifest plus skills/).

Links

• Pixelesq
• Connector documentation
• Agent Skills
• Model Context Protocol
• Privacy policy and terms

License

MIT