AI Agent Workflow Collection

Use when a framework command needs to parse a task's alignment.md (the scope contract — Goal / Expected result / Success criteria / Non-goals per section). Reads defensively via scripts/alignment-read.sh and returns structured JSON with warnings. Never blocks on malformed input.

Use when user says "create presentation", "make slides", "make carousel", "LinkedIn carousel", "create HTML page", "make landing page", "build web page", "html design system", "design system", "setup brand", "brand init", "extract brand", "get outline", "color palette", "alternative colors", "infographic", "brand assets", "brand project". Use PROACTIVELY when user wants to create any visual content with consistent branding. MUST be invoked for branded content — routes to the correct command for presentations, carousels, infographics, and HTML pages.

Assists with code quality tasks. Use when reviewing code, checking for issues, or improving code quality. NOT for: writing new features from scratch.

Enforces the development discipline for AI-assisted Drupal contributions — evidence over assertion, the no-guessing rule for external facts, the verification-gate artifact contracts, and re-verification on post-gate change. Use PROACTIVELY during any development between claiming an issue and verifying it. Use when user says 'guardrails', 'evidence over assertion', 'no guessing', 'verify this fact', 'is this actually tested', or whenever AI-assisted code is being written for a Drupal contribution. MUST apply before claiming any gate passed.

Works the Drupal issue lifecycle — reviews prior work on an issue first, then creates / comments on / claims it, and checks out the issue fork + branch with three-way fork handling. Use when the user runs /drupal-ai-contrib:issue or asks to find, create, claim, or check out a Drupal issue or issue fork. Wraps drupalorg-cli for no-auth reads; delegates authenticated GitLab fork/push to the drupal-gitlab skill.

Fetches the real GitLab merge-request pipeline for a Drupal contribution and gates on it — the authoritative final check. Use when the user runs /drupal-ai-contrib:pipeline or asks to check the real pipeline, the CI status, or whether a Drupal contribution is done. A contribution is not complete until the real drupalci pipeline is green.

Runs honest fresh-context review of a Drupal contribution — dispatches isolated reviewer agents with no session narrative to check the work against scope, coding standards, security, and the AI policy. Use when the user runs /drupal-ai-contrib:review or asks for an honest review, a fresh-eyes review, or a pre-submission review of a Drupal contribution. A builder cannot objectively review its own work.

Stands up and environment-matches a Drupal contribution workspace — DDEV with the workflow-matched add-on, CI gate config (new-module scaffold or existing-module discovery), the Drupal AI skills, the drupalorg CLI, the GitLab CLI (glab) for authenticated git.drupalcode.org operations, and a contribution-credentials (SSH-key) check. Use when the user runs /drupal-ai-contrib:setup or asks to set up a Drupal contribution environment. Idempotent and detect-driven — does only what is missing; never a gate, never a prerequisite.

Creates or updates a Drupal merge request and generates the AI-disclosure comment at the policy threshold. Use when the user runs /drupal-ai-contrib:submit or asks to submit, open, or update a Drupal merge request or patch. Creates the cross-project MR via the drupal-gitlab skill (glab); wraps drupalorg-cli for no-auth reads; surfaces status and RTBC guidance.

Runs the local verification inner loop for a Drupal contribution — the drupalci-parity gate set at CI strictness, the AI-policy gate, and the eval gate, every gate passing only on a captured artifact. Use when the user runs /drupal-ai-contrib:verify or asks to verify, check, or locally test a Drupal contribution before submitting. This is the centerpiece — evidence over assertion, never a bare 'passes'.

Use when needing the framework's canonical implementation example for a pattern - searches the framework's own source for the pattern and returns file-path…

Use when ANY development task might benefit from a guide. Use when user says "how do I", "best practice", "pattern for", "guide for", "Drupal form", "entity type", "plugin type", "routing", "caching", "config management", "SDC component", "design system", "Bootstrap mapping", "Radix theme", "JSX to Twig", "Tailwind tokens", "SOLID", "DRY", "TDD", "security", "CSS", "Next.js". Use PROACTIVELY before any design, architecture, or implementation work. MUST be invoked before writing code that touches Drupal APIs, theming, design systems, or security. NEVER skip guide check — patterns prevent bugs.

Routes Drupal contribution work to the right contribution-quality stage and supplies the contribution knowledge layer. Use when user says 'contribute to Drupal', 'Drupal contribution', 'submit a Drupal patch', 'Drupal merge request', 'fix a Drupal core issue', 'contribute a module', 'AI-assisted Drupal contribution', or works a drupal.org / GitLab Drupal issue. Use PROACTIVELY whenever AI-assisted code is headed for a Drupal contribution — drupalci and maintainer review are unforgiving.

Use when converting a flat task into an epic folder with children, promoting a subtask to a subepic, or expanding an existing epic with more children. Runs the 8-step transactional migration via scripts/migrate-to-epic.sh. Supports --dry-run for preflight plan. Never leaves half-migrated state on disk.

Greets users warmly. Use when user says hello, hi, good morning, or wants a friendly greeting.

Use when a phase command (research/design/implement) needs to load methodology references, online dev-guides, and project playbooks before task work begins. v4.10.0+: hybrid detection — a deterministic phase-aware methodology floor + lexical catalog candidates via scripts/dev-guides-detect.sh, plus semantic matches from the guides-matcher agent. Delegates guide fetching to dev-guides-navigator. Loads playbook layers via scripts/playbook-load-deterministic.sh. Cross-references conflicts. Records loaded guide IDs into sessioncontext.json loadedGuides[] to prevent re-loads.

Use when a framework task requires specialized guide content — delegates to the dev-guides-navigator plugin for online guide discovery with caching and disambiguation.

Use when generating branded HTML pages and components from a design system. Creates standalone HTML components and composes them into full pages with embedded CSS, responsive design, and brand integration.

Use when implementing HTMX in Drupal, migrating from AJAX to HTMX, building dynamic forms, dependent dropdowns, infinite scroll, real-time validation, or multi-step wizards. Use when user says "HTMX", "migrate AJAX", "dependent dropdown", "dynamic form", "infinite scroll", "load more", "real-time validation", "multi-step wizard", "hx-get", "hx-post", "Htmx class". Use PROACTIVELY for any Drupal 11.3+ dynamic interaction that could use HTMX instead of AJAX. MUST check HTMX patterns before implementing AJAX callbacks.

Use when breaking down a component for implementation - creates task file in implementationprocess/inprogress/ with TDD steps and acceptance…

Use when testing code, skills, commands, or configs through mental execution — trace logic line-by-line with concrete values to find bugs, logic errors, edge cases, contract violations, and AI hallucinations. Use when user says "paper test", "trace this", "find bugs", "check for edge cases", "audit this code", "verify AI code", "test this skill", "test this agent", "validate this implementation", "review this logic", "check dependencies", "check this config", "walk through this code", "step through this", "dry run", "sanity check", "red team this", "poke holes in this". MUST verify external calls — never assume methods exist. Use proactively before deploying changes or after AI generates code.

Use when determining task phase - analyzes task file to identify Phase 1, 2, or 3 for a specific…

Use when creating Claude Code plugins - covers skills, commands, agents, hooks, MCP servers, and plugin configuration. Use when user says "create plugin", "make a skill", "add command", "add hooks", "skill authoring", "SKILL.md", "plugin components", "package reusable behavior", "distribute skills", "scaffold plugin", "plugin structure", "write a skill description". NOT for: using existing plugins, installing plugins, plugin marketplace browsing.

Use when a lifecycle orchestrator reaches a phase boundary and needs the framework-specific process recipe that drives that phase. Checks projectstate first (a recorded source is the memory of the prior decision and resolves directly); on a miss resolves by source order (repo-local, machine-local, dev-guides) and on a true miss returns action:ask-user for the orchestrator to ask the user. Tags provenance strictly (verified:true only for dev-guides upstream), records the source choice in projectstate.md, and reports a bodypath the orchestrator reads alongside a structured JSON report. Delegates ALL fetching and store operations to the dev-guides-navigator plugin; never touches the navigator plugin's filesystem directly.