cms-cultivator

Review a pull request or analyze local changes before submitting. Auto-activates when user mentions reviewing a PR, asks for code review, wants to analyze their changes before submitting, or mentions "pr-review self". Invoke when user provides a PR number to review or says "review self", "review my changes", or "pr review". Supports focus areas: code, security, breaking, testing, size, performance.

Generate properly formatted Teamwork CSV files from Functional Requirements Documents. Converts FRD requirements into CSV backlog with task hierarchy, priorities, story points, and estimated hours. Automatically populates estimated time from story point conversion. Invoke when user asks to "export to CSV", "create Teamwork backlog", or needs project backlog file.

Automatically export audit findings, security issues, performance problems, or accessibility violations to Teamwork tasks when other agents complete their analysis. Converts technical findings into actionable project management tasks with appropriate priorities and templates. Invoke when audit agents finish reports, user says "export to Teamwork", or findings need project tracking.

Automatically look up Teamwork task status, details, or project information when user mentions ticket numbers, asks "what's the status of", or needs quick project context. Performs focused queries without creating or modifying data. Invoke when user asks "status of PROJ-123", "what's in that ticket?", "show me task details", or references Teamwork ticket numbers.

Automatically create properly formatted Teamwork tasks when user provides task details, mentions creating tickets, or shares work that needs tracking. Performs context-aware template selection and ensures all required sections are included. Invoke when user says "create a task", "make a ticket", "track this work", or provides requirements to document.

Strategist-focused site audit for discovery and pre-discovery. Given a site URL and optional qualitative research data, navigates the site via CoWork, audits against all 21 UX Laws from lawsofux.com, reviews content hierarchy, synthesises qualitative data, runs Lighthouse, and produces two deliverables — a Project Knowledge Summary (Markdown for Claude Desktop Projects) and a polished, iterable HTML Artifact for client sharing. Use when a strategist, UX lead, or PM asks for a discovery audit, UX laws audit, content hierarchy review, pre-discovery site review, "audit this site for strategy", "strategist audit", "UX audit", or pastes a site URL with discovery context. Not for developer audits — use accessibility-audit, performance-audit, or live-site-audit for those.

Automatically generate conventional commit messages when user has staged changes and mentions committing. Analyzes git diff and status to create properly formatted commit messages following conventional commits specification. Invoke when user mentions "commit", "staged", "committing", or asks for help with commit messages.

Generate a PR description and create a GitHub pull request. Invoke when user explicitly asks to create a pull request, says "create a PR", "submit a PR", "open a pull request", or uses /pr-create. Requires user confirmation before creating the PR (irreversible GitHub action). Supports ticket numbers and --concise mode.

Generate changelog entries, a deployment checklist, and update a release PR description. Invoke when user asks to prepare a release, generate a changelog, create a deployment checklist, or uses /pr-release. Requires user confirmation before updating the PR (modifies publicly visible content). Supports version numbers and focus areas (changelog/deploy/update).

Automatically guide users through Brene Brown's 5 Cs of Strategic Thinking (Context, Color, Connective Tissue, Cost, Consequence) when making significant decisions. From the book "Strong Ground" by Brene Brown. Invoke when user asks "should we do this?", "help me decide", "what are the trade-offs", "help me think through this", "is this the right approach?", or is weighing options about architecture, tooling, features, project approach, or delegating work.

PM triage skill for reviewing client-submitted Teamwork tasks or comments (feature requests, general questions). Given a Teamwork link, fetches the task, detects the platform (Drupal/WordPress/general web), researches potential solutions, and drafts a warm client-facing reply. Use this skill whenever a user shares a Teamwork task or comment link and wants to understand the client's request, explore implementation options, or draft a response — even if they just say "can you look at this task?" or "help me respond to this client". Also triggers for phrases like "triage this", "review this client request", "what should we tell the client", or "help me draft a reply to this Teamwork task". No estimates are included at this stage.

Quickly prepare a PM for an upcoming client check-in by pulling together context from Teamwork (tasks + messages), Gmail, Slack, and Fathom meeting recordings. Produces a structured briefing with talking points, ticket progress, new feature requests, and suggested next steps — then optionally generates a formatted agenda. Use this skill whenever the user says things like: - "prep me for my meeting with [client]" - "I have a check-in with [project] tomorrow, help me prep" - "what do I need to know before my call with [client]?" - "get me ready for [project name] meeting" - "meeting prep for [project]" Always trigger this skill when meeting preparation is the goal, even if the user doesn't say "skill" or "prep" explicitly. If the user mentions a client name or project name alongside a meeting, check-in, or call — use this skill.

Generate a client-facing project heartbeat / status update message for a Kanopi project, ready to be posted as a Teamwork message. Use this skill whenever the user asks to write, draft, generate, or send a project update, heartbeat, status update, or progress report to a client. Also triggers when the user says things like "time for a project update", "draft the heartbeat", "write up the update for [project]", or "it's been two weeks, let's send an update". Always use this skill — even if the user doesn't say "heartbeat" — whenever the intent is to summarise recent project activity for a client audience.

Perform a full QA review of a Teamwork task by reading the task and all its comments for context, extracting the multi-dev URL, generating dynamic validation steps tailored to the task type, and using CoWork browser automation to execute those steps on the multi-dev environment. Produces a structured validation report with pass/fail per step, screenshots, internal notes, and a client-facing summary — all shown in chat. Use this skill whenever the user asks to QA, test, validate, or review a Teamwork task or multi-dev environment — even if they just say "can you QA this?" or paste a Teamwork link. Also triggers for phrases like "run QA on", "check the multi-dev", "validate this task", "test the dev link", or "review the ticket". Works across Drupal/CMS updates, WordPress/plugin updates, bug fixes, new feature development, and general web development tasks.

Generate comprehensive FRD markdown structure with all required sections. Provides section templates, numbering conventions (FR-XXX, TR-XXX, US-XXX), platform-specific additions, and output format guidelines. Invoke when requirements are gathered and ready to structure into FRD document.

Create Drupal paragraph types from Figma designs or screenshots using the design-specialist agent. Auto-activates when user provides a design reference and asks to create a Drupal paragraph type, content component, or layout section. Invoke when user says "create a Drupal paragraph from this design", "convert this mockup to a paragraph type", or provides a design with Drupal context.

Create WordPress block patterns from Figma designs or screenshots using the design-specialist agent. Auto-activates when user provides a Figma URL or design mockup and asks to create a WordPress block pattern, component, or section. Invoke when user says "create a WordPress block from this design", "convert this Figma to a block pattern", or provides a design reference with WordPress context.

Comprehensive live site audit orchestrating performance, accessibility, security, and code quality specialists in parallel. Invoke when user runs /audit-live-site, requests a comprehensive site health assessment, needs a full multi-dimensional audit, or wants a unified audit report with health score and remediation roadmap. Generates audit-live-site-YYYY-MM-DD-HHMM.md report file.

Comprehensive WCAG 2.1 Level AA accessibility audit for Drupal and WordPress projects. Spawns accessibility-specialist for full site analysis. Invoke when user runs /audit-a11y, requests a full accessibility audit, needs a WCAG compliance report, or asks for comprehensive accessibility analysis across pages or modules. Supports --quick, --standard, --comprehensive depth modes and scope/format flags.

Generate client-facing executive summaries from existing audit report files. Transforms technical CMS Cultivator audit findings into non-technical stakeholder reports. Invoke when user asks to "generate a client report from this audit", "create an executive summary", "make a non-technical version of this audit", or "summarize audit findings for stakeholders". Requires an existing audit report file as input.

Automate Kanopi's complete Drupal/Pantheon DevOps setup for a new project. Invoke when user explicitly asks to set up DevOps for a new project, onboard a Pantheon site to Kanopi's CI/CD pipeline, or uses /devops-setup. This is an irreversible multi-system setup requiring explicit user confirmation at each phase. Creates GitHub repos, configures Pantheon services, and makes code changes.

List and clean up cloned drupal.org repositories in the local cache (~/.cache/drupal-contrib/). Invoke when user asks to list, remove, or clean up cloned Drupal contrib repos, says "cleanup drupal repos", "remove cloned drupal projects", or uses /drupal-cleanup. Has side effects: permanently deletes repository clones. Requires user confirmation before deletion.

Full drupal.org contribution workflow — create an issue and set up a merge request together. Invoke when user wants to contribute to a Drupal module, says "contribute to drupal.org", "create a drupal.org issue and MR", or uses /drupal-contribute. Requires user interaction at two manual steps (CAPTCHA-protected issue creation and issue fork creation). Has side effects: clones repos to ~/.cache/drupal-contrib/ and creates drupal.org issues.

Create, update, or add comments to issues on drupal.org using a guided manual workflow. Invoke when user wants to create a bug report or feature request on drupal.org, says "create a drupal.org issue", "open a drupal issue", or uses /drupal-issue. Has side effects: creates publicly visible issues on drupal.org. Requires user to paste content and submit (CAPTCHA-protected). Also supports listing and updating issues.

Create or list merge requests for drupal.org projects via git.drupalcode.org. Invoke when user wants to create a merge request for a drupal.org issue, says "create a drupal.org MR", "set up a merge request for issue", or uses /drupal-mr. Has side effects: clones repos to ~/.cache/drupal-contrib/ and pushes to git.drupalcode.org. Requires one manual step (issue fork creation via web UI).

Comprehensive performance analysis and Core Web Vitals optimization for Drupal and WordPress projects. Spawns performance-specialist for full analysis. Invoke when user runs /audit-perf, requests a full performance audit, needs Core Web Vitals analysis (LCP, INP, CLS), or asks for comprehensive performance assessment. Supports --quick, --standard, --comprehensive depth modes and scope/format/target flags.

Comprehensive code quality analysis and technical debt assessment for Drupal and WordPress projects. Spawns code-quality-specialist for full analysis. Invoke when user runs /quality-analyze, requests a full code quality audit, needs technical debt assessment, or asks for comprehensive code quality analysis. Supports --quick, --standard, --comprehensive depth modes and scope/format/threshold flags.

Comprehensive OWASP Top 10 security vulnerability scanning and compliance reporting for Drupal and WordPress. Spawns security-specialist for full analysis. Invoke when user runs /audit-security, requests a full security audit, needs OWASP compliance review, or asks for comprehensive vulnerability scanning. Supports --quick, --standard, --comprehensive depth modes and scope/format/severity flags.

Automatically scan code for security vulnerabilities when user asks if code is secure or shows potentially unsafe code. Performs focused security checks on specific code, functions, or patterns. Invoke when user asks "is this secure?", "security issue?", mentions XSS, SQL injection, or shows security-sensitive code.

Install official WordPress agent-skills from the WordPress/agent-skills GitHub repository. Invoke when user asks to install WordPress skills, says "add WordPress skills", "install WordPress agent skills", or uses /wp-add-skills. Has side effects: clones a repository, installs 13 skills to the global skills directory. Requires user confirmation before installation. Supports --list and --update flags.

Export audit findings from markdown report files to Teamwork-compatible CSV format for project management tools (Jira, Monday, Linear also supported). Auto-activates when user asks to "export audit to CSV", "create tasks from audit", or provides an audit report file and asks to export it. Invoke when user provides audit report filename and wants CSV output for project management import.

Automatically audit Google Tag Manager implementations for performance impact when user mentions GTM, tag manager, tracking tags, marketing tags, or asks about tag performance. Analyzes container configuration, measures tag execution timing, identifies blocking tags, audits custom HTML safety, evaluates trigger efficiency, and maps tag impact to Core Web Vitals. Invoke when user says "GTM is slow", "too many tags", "tag manager performance", "tracking tags impact", or asks about marketing tag overhead.

Automatically check and suggest structured data improvements when user mentions JSON-LD, Schema.org, structured data, rich results, SEO markup, or shows HTML/template code that could benefit from structured data. Performs focused checks on specific pages, templates, or code snippets. Invoke when user asks "does this have structured data?", "add JSON-LD", "Schema.org markup", "rich results", "SEO schema", or shows template code for content types like articles, events, products, or FAQs.

Automatically extract technical requirements from design references when user mentions Figma, uploads images, or says "implement this design". Analyzes colors, typography, spacing, layout, and maps to WordPress blocks or Drupal paragraph fields. Provides detailed specifications for developers including exact values, responsive behavior, and accessibility requirements.

Automatically generate mobile-first responsive CSS/SCSS when creating component styles or mentioning responsive design. Implements standard breakpoints (768px, 1024px), ensures WCAG AA color contrast, creates touch-friendly interfaces (44px minimum targets), adds proper focus indicators, supports reduced motion, scales typography responsively, and provides detailed technical specifications with exact values.

Quick help with drupal.org issue templates, formatting, contributing patches, and best practices. Invoke when user asks "how do I write a bug report?", "drupal.org issue template", "issue formatting", "I have a patch", "contribute back", "submit my fix", "I fixed a bug in a module", or needs help structuring issue descriptions or contributing code to drupal.org projects.

Quick help with drupal.org contribution workflows including git commands, branch naming, issue fork setup, and merge request creation. Invoke when user asks "how do I contribute to drupal.org?", "drupal.org git workflow", "issue fork", "drupal merge request", or needs help with git.drupalcode.org commands.

Automatically generate documentation when user mentions needing API docs, README files, user guides, developer guides, or changelogs. Analyzes code and generates appropriate documentation based on context. Invoke when user mentions "document", "docs", "README", "API documentation", "guide", "changelog", or "how to document".

Automatically check specific elements or code for accessibility issues when user asks if something is accessible or mentions WCAG compliance. Performs focused accessibility checks on individual components, forms, or pages. Invoke when user asks "is this accessible?", "WCAG compliant?", or shows code/elements asking about accessibility.

Automatically validate implementations in real browsers after code is written or when user says "test this". Uses Chrome DevTools MCP to test responsive breakpoints (320px, 768px, 1024px), check accessibility compliance (WCAG AA contrast, keyboard navigation, ARIA), validate interactions, and generate detailed technical reports with file paths and specific fixes.