Claude Code skills for agentic-starter-kits contributors.
Add behavioral testing (pytest + EvalHub) to an agent in the agentic-starter-kits repo. Covers runner compatibility, test files, golden queries, thresholds, EvalHub fixture, Containerfile, docs, and MLflow tracing verification. Use when implementing behavioral tests for a new agent or when the user mentions btest, behavioral tests, eval coverage, or test harness integration.
Add integration deployment tests (health-check on OpenShift) to an agent in the agentic-starter-kits repo. Creates conftest.py, test_deployment.py, __init__.py, adds test-integration Makefile target, and updates the CI workflow matrix. Use when implementing integration tests, deployment tests, or health-check tests for a new agent.
Adds manual MLflow trace wrapping for tool and agent spans in Level B and C agents where autolog doesn't cover everything.
Researches and classifies a framework's MLflow autolog support level (A, B, or C) to determine what manual tracing is needed.
Creates the tracing.py module with enable_tracing(), health check, and framework-specific autolog configuration.
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.
Claude Code skills for agentic-starter-kits contributors.
| Skill | Description | Usage |
|---|---|---|
| deploy-agents | Deploy agents to OpenShift with auto-detected cluster config and MLflow token refresh | /agentic-starter-kits-skills:deploy-agents <agent_paths or 'all'> [--token-only] |
| add-behavioral-tests | Scaffold behavioral testing (pytest + EvalHub) for an agent | /agentic-starter-kits-skills:add-behavioral-tests <agent_path> [JIRA-KEY] |
| run-behavioral-tests | Run and validate behavioral tests for an agent | /agentic-starter-kits-skills:run-behavioral-tests <agent_path> |
| add-integration-tests | Add integration tests for agent deployment verification | /agentic-starter-kits-skills:add-integration-tests <agent_path> [JIRA-KEY] |
| integrate-tracing | Orchestrate end-to-end MLflow tracing integration into an agent template | /agentic-starter-kits-skills:integrate-tracing <framework> <agent_path> |
| check-autolog-support | Research and classify a framework's MLflow autolog support level (A, B, or C) | /agentic-starter-kits-skills:check-autolog-support <framework> |
| create-tracing-module | Create the tracing.py module with enable_tracing() and framework-specific autolog | /agentic-starter-kits-skills:create-tracing-module <agent_path> [framework] |
| wire-into-lifespan | Wire enable_tracing() into the FastAPI lifespan and add imports to main.py | /agentic-starter-kits-skills:wire-into-lifespan <agent_path> |
| add-manual-tracing | Add manual MLflow trace wrapping for tool and agent spans (Level B/C agents) | /agentic-starter-kits-skills:add-manual-tracing <agent_path> |
| verify-traces | Verify tracing works correctly via code review and live trace testing | /agentic-starter-kits-skills:verify-traces <agent_path> |
| review-tracing-code | Review tracing integration code for correctness against repo patterns | /agentic-starter-kits-skills:review-tracing-code <agent_path> |
| test-tracing | Test MLflow tracing end-to-end by starting servers, sending requests, and verifying spans | /agentic-starter-kits-skills:test-tracing <agent_path> |
| kagenti-deploy | Deploy A2A-compliant agents to OpenShift/Kubernetes with kagenti integration | /agentic-starter-kits-skills:kagenti-deploy |
Add the marketplace and install the plugin:
claude plugin marketplace add red-hat-data-services/agentic-starter-kits-skills
claude plugin install agentic-starter-kits-skills@agentic-starter-kits-skills
To add a new skill:
skills/ (e.g., skills/my-new-skill/)SKILL.md file with YAML frontmatter (name, description) and markdown contentskills/<skill-name>/references/eval-criteria-<name>.json for gate evaluation -- use agentic-starter-kits-skills:<skill-name> as the top-level key.claude-plugin/marketplace.json to include the new skill's name and description if it belongs in a separate plugin entryplugin.json (in .claude-plugin/) is the plugin manifest -- it tells Claude Code where to find skills. It does not need updating when adding a skill, since it points to the skills/ directory and auto-discovers SKILL.md files.
Run the eval-hook test suite:
./scripts/test-eval-hook.sh
If you previously used these skills from .claude/skills/ in the agentic-starter-kits repo or from ~/.claude/skills/, remove the old local directories after installing the plugin to prevent duplicates:
# From agentic-starter-kits repo root (if skills were checked in)
rm -rf .claude/skills/integrate-tracing
rm -rf .claude/skills/check-autolog-support
rm -rf .claude/skills/create-tracing-module
rm -rf .claude/skills/wire-into-lifespan
rm -rf .claude/skills/add-manual-tracing
rm -rf .claude/skills/verify-traces
rm -rf .claude/skills/review-tracing-code
rm -rf .claude/skills/test-tracing
rm -rf .claude/skills/kagenti-deploy
# From user-level skills (if any were installed locally)
rm -rf ~/.claude/skills/deploy-agents
rm -rf ~/.claude/skills/add-behavioral-tests
rm -rf ~/.claude/skills/run-behavioral-tests
rm -rf ~/.claude/skills/integrate-tracing
rm -rf ~/.claude/skills/check-autolog-support
rm -rf ~/.claude/skills/create-tracing-module
rm -rf ~/.claude/skills/wire-into-lifespan
rm -rf ~/.claude/skills/add-manual-tracing
rm -rf ~/.claude/skills/verify-traces
rm -rf ~/.claude/skills/review-tracing-code
rm -rf ~/.claude/skills/test-tracing
rm -rf ~/.claude/skills/kagenti-deploy
npx claudepluginhub red-hat-data-services/agentic-starter-kits-skills --plugin agentic-starter-kits-skillsComplete collection of battle-tested Claude Code configs from an Anthropic hackathon winner - agents, skills, hooks, and rules evolved over 10+ months of intensive daily use
Modern R development skills for Claude Code - tidyverse patterns, rlang metaprogramming, Bayesian inference, performance optimization, and more
20 SEO/GEO skills and 5 commands on one shared contract for keyword research, content creation, technical audits, schema markup, monitoring, quality gates, entity truth, and campaign memory.
Comprehensive SEO analysis plugin for Claude Code. 25 sub-skills (21 core + 1 orchestrator + 1 framework + 2 extension mirrors) and 18 sub-agents cover technical SEO, content quality, schema, sitemaps, Core Web Vitals, local SEO, backlinks, AI/GEO, ecommerce, hreflang, SXO, clustering, drift monitoring, and Google APIs. Includes optional MCP extensions, SPA-aware rendering, portability, and hardened SSRF/DNS-rebinding safe fetchers.
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Develop, test, build, and deploy Godot 4.x games with Claude Code. Includes GdUnit4 testing, web/desktop exports, CI/CD pipelines, and deployment to Vercel/GitHub Pages/itch.io.