Analyze Python package build systems, dependencies, and license compliance for Red Hat product inclusion; debug GitLab CI/CD pipelines; manage Jira tickets and generate documentation from PRs and code reviews
Use this skill to analyze context sufficiency for documentation generation. Reads workspace/context-package.json and produces workspace/gap-report.json with severity-rated gaps and a proceed/gather-more/stop recommendation.
Use when you need to gather context for a Jira ticket or PR. Resolves ticket metadata, clones relevant repos, collects candidate files, runs filtering pipeline, and produces workspace/context-package.json.
Retrieve and display full details of a Jira ticket. Fetches all fields and formats them for conversation context. Use when user needs ticket information or wants to examine a ticket.
Verify acli installation and authentication. Checks if acli is installed, authenticated to Jira, and can query projects. Use when troubleshooting acli issues or setting up acli for the first time.
Review an Architectural Decision Record (ADR) using a team of six specialist reviewer subagents and produce a consolidated report as both PDF and PPTX slide deck. Use this skill whenever the user asks to review, critique, audit, or get feedback on an ADR, architecture decision, design doc, or RFC — whether the input is a Markdown file, a .docx document, or pasted text. Trigger even if the user does not explicitly say "ADR"; phrases like "review this architecture decision", "critique this design doc", or "run the reviewer panel on this" should also invoke this skill.
Uses power tools
Uses Bash, Write, or Edit tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
This repository is a collaborative place hosting collections of AI plugins to automate and assist with various tasks.
[!NOTE] Right now the focus is to support Claude Code, OpenCode.ai, Gemini Gems, and Cursor AI. Other tools are welcome here, please submit Pull Requests.
[!NOTE] This project was inspired by the OpenShift AI helpers.
Have an idea for a new plugin, command, or assistant but not sure how to implement it? We'd love to hear about it! Simply file a GitHub issue with your idea in the title and we'll work together to make it happen.
[!TIP] Share your idea
No implementation details needed - just describe what you'd like to automate or what workflow you think could be improved. The community can help figure out the best way to build it.
Want to work on an issue? Comment /assign on it to assign yourself.
This repository is made for collaboration. We highly welcome contributions.
For skills, check out the helpers/skills/ directory for examples.
For agents, see the helpers/agents/ directory.
Using AI code assistant itself to develop the tools is highly encouraged.
When contributing new tools:
helpers/skills/ directory following the agentskills.io formathelpers/agents/ directory with appropriate documentationhelpers/gems/ directoryOnce you have added the tool, you'd have to run have to run make update in order to generate the website data.
Then you should git commit your change and after than running make lint would run local tests to validate the syntax.
claude/plugin marketplace add .//plugin then install the local pluginThe AI Helpers marketplace uses a centralized category registry in categories.yaml to organize specialized tools by category. Tools not listed in any category are automatically placed in the "General" category - perfect for most contributions!
Specialized tool categories are registered in categories.yaml:
CategoryName:
- specialized-tool
- another-tool
AnotherCategory:
- domain-specific-tool
To add a new category, edit categories.yaml to include the new category as a top-level key:
Add category with tools:
YourCategory:
- your-tool-name
- another-tool
Update documentation: Run make update to regenerate the website
The build system automatically handles tool organization and validation:
categories.yaml are automatically assigned to "General" categoryClaude Code Marketplace extends Claude's functionality with custom commands, agents, and skills for specific workflows and tasks. They enable you to automate repetitive development activities, integrate with tools, and create specialized AI assistants tailored to your needs.
For comprehensive information about plugin architecture and development, see the official Claude Code plugins documentation.
Add the marketplace:
/plugin marketplace add opendatahub-io/ai-helpers
Install a plugin:
/plugin install odh-ai-helpers
[!TIP] To browse and install multiple plugins interactively, use
/pluginafter adding the marketplace. This will show you all available plugins and allow you to install them selectively. For a complete list of all available tools, see categories.yaml or visit our website.
/hello-world:echo Hello from OpenDataHub!
For IDE users, we have supplied a devcontainer.json file. For setup and prerequisites, see Dev Container README.
For setup with the standard CLI see the following.
A container image is available with Claude Code and all plugins pre-installed:
ghcr.io/opendatahub-io/ai-helpers:latest
You can also build it yourself by running:
podman build -f images/claude/Containerfile -t ai-helpers .
npx claudepluginhub opendatahub-io/ai-helpersAgent and skill evaluation harness with MLflow integration
Site generation skills for the OpenDataHub Skills Registry
Assess RFEs against quality criteria using a structured rubric
Documentation review, writing, and workflow tools for AsciiDoc and Markdown documentation
Orchestrator skills, agent prompts, and state management for the Jira autofix pipeline
Claude Code skill pack for CodeRabbit (24 skills)
Language-agnostic development process harness implementing the Stateless Agent Methodology (SAM) 7-stage pipeline with ARL human touchpoint model and Voltron-style language plugin composition. Provides orchestration, workflows, planning, verification, and testing methodology that any language plugin can compose with.
Plugin-first Claude Code workflows with planning, CI/CD debugging, reusable agents, TODOs, and MCP safety policies.
DevOps patterns: CI debugging, tech debt detection, own all failures
Personal Claude Code + Codex dev stack: security hooks, AI-first code conventions, /security-review, /repo-map, /stack-check, portable statusline. Designed to complement other skills-based plugins, not replace them.
Prompt engineering techniques for accurate, grounded Claude responses — anti-hallucination workflow with citation-backed analysis