By camoa Verified
Enforce Drupal contribution quality gates locally with drupalci-parity checks (phpcs, phpstan, phpunit), AI-policy validation, fresh-context review, and live GitLab pipeline confirmation so AI-assisted contributions pass maintainer review.
Onboard and environment-match a Drupal contribution workspace — DDEV with the workflow-matched add-on, CI gate config, the Drupal AI skills, the drupalorg CLI, and a contribution-credentials (SSH-key) check. Use when user says 'set up Drupal contribution', 'contribution environment', 'scaffold a contrib module', 'drupal-ai-contrib setup'. Idempotent — does only what is missing.
Create or update a Drupal merge request and generate the AI-disclosure comment at the policy threshold. Use when user says 'submit Drupal contribution', 'open a merge request', 'update the MR', 'submit patch', 'drupal-ai-contrib submit'. Wraps drupalorg-cli.
Run 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 user says 'verify Drupal contribution', 'run the gates', 'check before submitting', 'drupalci parity', 'drupal-ai-contrib verify'.
Work the Drupal issue lifecycle — review prior work first, then create / comment on / claim an issue and check out its fork + branch with three-way fork handling. Use when user says 'Drupal issue', 'claim an issue', 'create an issue', 'check out issue fork', 'drupal-ai-contrib issue'. Wraps drupalorg-cli.
Fetch the real GitLab merge-request pipeline for a Drupal contribution and gate on it — the authoritative final check. Use when user says 'check the pipeline', 'real CI status', 'is the contribution done', 'drupalci pipeline', 'drupal-ai-contrib pipeline'.
Live-fetches the current state of the Drupal AI-contribution policy, ai_best_practices, and the eval landscape, and returns a SETTLED / DRAFT / DISCUSSION-tagged summary. Use proactively per contribution — the AI-policy and eval landscape is the fastest-moving area and must be re-confirmed each time, never assumed from memory.
Verifies a single external-fact claim — an SDK symbol, API header/parameter, beta-feature slug, or library-version behavior — against vendor source or a live probe, and returns verified or unverified with evidence. Use proactively whenever AI-assisted Drupal contribution code relies on an external fact recalled from model memory or a changelog line. An unverified external fact is a blocker.
Reviews a Drupal contribution diff honestly with no session narrative — checks scope adherence, Drupal + PHP coding standards, security, and AI-policy disclosure. Use proactively when a contribution needs honest validation before submission; dispatched by the contribution-review skill. A builder cannot objectively review its own work.
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.
Modifies files
Hook triggers on file write and edit operations
Uses power tools
Uses Bash, Write, or Edit tools
Verified owner:Carlos Ospina
Based on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Custom plugins and tools for Claude Code.
Heads up (transition notice, kept through ~August 2026).
drupal-dev-frameworkhas been renamed toai-dev-assistant(same workflow, broader scope, command names unchanged). If you already have the old plugin installed: installai-dev-assistant, run/drupal-dev-framework:upgradeonce to migrate your project store and per-project wiring, then uninstalldrupal-dev-framework(/plugin uninstall drupal-dev-framework@camoa-skills). The shell exposes only/drupal-dev-framework:upgrade; everything else now lives under theai-dev-assistant:namespace. A few other plugins got minor description and tone cleanups in the same pass. Full steps: drupal-dev-framework/README.md.
I started building what I called "frameworks" over a year before Claude officially released Skills. Same concept, different name.
The idea came from frustration. I was tired of repeating the same instructions every conversation. Instead of starting fresh each time, I asked AI to analyze our successful interactions and create frameworks capturing recurring requirements and preferences. These became reusable project knowledge.
This approach produced results: 3 published Drupal contrib modules, 17+ blog articles, automated social media campaigns, and phase-based editorial workflows.
When Claude released Skills officially, I recognized what I'd been building. This repository translates those frameworks into proper Skills with tooling.
I wrote more about this methodology in My Journey with AI Tools.
# Add the marketplace
/plugin marketplace add https://github.com/camoa/claude-skills
# Install individual plugins
/plugin install dev-guides-navigator@camoa-skills
/plugin install ai-dev-assistant@camoa-skills
/plugin install plugin-creation-tools@camoa-skills
/plugin install brand-content-design@camoa-skills
/plugin install code-quality-tools@camoa-skills
/plugin install drupal-htmx@camoa-skills
/plugin install code-paper-test@camoa-skills
/plugin install drupal-ai-contrib@camoa-skills
Skills in this marketplace conform to the open agentskills.io standard and work in Cursor, Codex CLI, VS Code Copilot, Gemini CLI, Cline, OpenCode, and more. Commands, agents, and hooks are Claude-Code-specific by format but can be emulated. See PORTABILITY.md for the full guide and CURSOR.md for Cursor-specific notes.
There's a known bug in Claude Code affecting git-based marketplaces. Skills may fail to load during initialization with "no such file or directory" errors because Claude Code looks for skill files in the wrong location.
Workaround: Skills still work when invoked via the Skill tool (slash commands). The issue only affects automatic discovery at startup.
Status: Awaiting fix from Anthropic.
Smart guide discovery and routing for the dev-guides site. Routes AI to the correct guide using hash-based caching and KG metadata for disambiguation.
llms.txt with hash-based freshness check: no redundant fetchesconcepts/not fields) prevents wrong-guide selection (e.g., "story.yml" routes to UI Patterns, not Storybook)llms.txt → topic index.md → specific guide# Invoked automatically before design/dev tasks, or manually:
/dev-guides-navigator style guide
An AI assistant for developers that focuses on getting the process right, not just getting code out fast. Most AI dev tools optimize for speed. This one keeps the work disciplined: understand the problem before coding, reuse what already exists, follow your standards, and verify. It runs each task through Research → Architecture → Implementation → Review, with deterministic gates (SOLID, TDD, DRY, security, code purposefulness) the AI can't quietly skip, and grounds its decisions in best-practice guides instead of whatever the model guessed. Requires dev-guides-navigator. Stack-agnostic engine; ships with a Drupal-flavored reference implementation for the deep components (a stack-neutral generalization is in progress).
npx claudepluginhub camoa/claude-skills --plugin drupal-ai-contribCreate branded visual content (presentations, carousels, infographics, HTML pages) with Aaker personality-driven design, style recommendation engine, visual components, 26 visual styles, design systems, and Presentation Zen principles
An AI assistant for developers that focuses on getting the process right, not just getting code out fast. It runs each task through Research → Architecture → Implementation → Review before code gets written, and checks the work against your standards (SOLID, TDD, DRY, security) with gates the AI can't quietly skip. Decisions stay grounded in best-practice guides instead of whatever the model guessed. Stack-agnostic, so stack specifics live in consumable dev-guides, recipes, and playbooks.
HTMX development guidance and AJAX-to-HTMX migration tools for Drupal 11.3+. Includes analyzers, pattern recommendations, and validation.
Systematic testing through mental execution - trace code, skills, commands, and configs line-by-line with concrete values to find bugs, missing logic, edge cases, and AI hallucinations
Smart guide discovery and routing for dev-guides. Uses hash-based caching and KG metadata (concepts, disambiguation, relationships) to route AI to the correct guide. All fetches use curl (never WebFetch) to preserve raw structured content.
DEPRECATED — renamed to ai-dev-assistant. This shell remains installable only to run a one-time upgrade: it repoints your project store at the new plugin and re-stamps per-project session-remembrance hooks to the new paths, then is safe to uninstall. Install ai-dev-assistant going forward.
Drupal development workflow with live autopilot: 19 skills, 4 agents, 10 commands, behavioral evals, session analysis, and Magic Loop Autopilot for task classification and drift detection.
Audit and optimize Claude Code configurations with dynamic best-practice research
Complete plugin development toolkit for creating, refactoring, and validating Claude Code plugins and agents. Use when creating new plugins/skills/agents, refactoring existing plugins/skills, validating frontmatter, or restructuring plugin components. Includes specialized agents for assessment, planning, execution, and validation workflows.
Complete developer toolkit for Claude Code
Prompt engineering techniques for accurate, grounded Claude responses — anti-hallucination workflow with citation-backed analysis