Help us improve
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
By laurigates
Evaluate and benchmark Claude Code skills/plugins: run behavioral test cases on skills, grade outputs against assertions with evidence, aggregate plugin-level reports, compare versions blindly, analyze patterns for strengths/weaknesses, track quality trends over time, and get prioritized suggestions to improve instructions/examples/structure.
npx claudepluginhub laurigates/claude-plugins --plugin evaluate-pluginAnalyze evaluation results to identify patterns, weaknesses, and improvement opportunities. Operates in comparison mode (with-skill vs baseline) or benchmark mode (trends across runs). Use after grading to generate suggestions.
Blind comparison of two outputs without knowing their origin. Rates content quality and structure quality to objectively determine which output is better. Use to compare with-skill vs baseline runs without bias.
Grade evaluation runs against predefined assertions. Examines execution transcripts and outputs to determine pass/fail with cited evidence. Use as a subagent from evaluation orchestration skills.
Analyze evaluation results and suggest concrete skill improvements. Use after running evaluations to get actionable recommendations for improving skill quality, descriptions, or instructions.
Batch evaluate all skills in a plugin. Runs /evaluate:skill for each skill that has eval cases, then produces a plugin-level report. Use when auditing an entire plugin's quality or before a release.
View evaluation results and benchmark reports. Use when you want to see past eval results, compare benchmark runs, or review quality trends for a skill or plugin.
Evaluate a skill's effectiveness by running test cases and grading results. Use when you want to test whether a skill produces correct guidance, validate skill improvements, or benchmark a skill before release.
Uses power tools
Uses Bash, Write, or Edit tools
Share bugs, ideas, or general feedback.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
No description provided.
Prompt engineering techniques for accurate, grounded Claude responses — anti-hallucination workflow with citation-backed analysis
Core skills: ecosystem guide, skill creator, research patterns, session reflection, and plugin development. Includes UserPromptSubmit hook for forced skill evaluation.
Audit Claude Code plugins and skills for best practices, deprecations, compatibility, usability, coverage gaps, duplication, and workflow optimization
Create new skills, improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, update or optimize an existing skill, run evals to test a skill, or benchmark skill performance with variance analysis.
Create, test, measure, and iteratively improve Claude Code skills with category-aware design, gotchas-driven development, progressive disclosure coaching, and automated description optimization.
Rust development - cargo, clippy, testing, memory safety
Bevy game engine development - ECS, rendering, game architecture
Test execution, TDD workflow, testing strategies, and quality analysis
Python development ecosystem - uv, ruff, pytest, packaging, type checking
Home Assistant configuration management - YAML configuration, automations, scripts, scenes, and entity management for Home Assistant installations
A curated collection of 38 Claude Code plugins providing 300+ skills and 14 agents for development workflows.
Install the full plugin collection as a marketplace:
claude plugin install laurigates/claude-plugins
This registers all 38 plugins. You can then enable individual plugins as needed.
If you prefer to install plugins one at a time:
claude plugin install laurigates-claude-plugins/<plugin-name>
For example:
claude plugin install laurigates-claude-plugins/git-plugin
claude plugin install laurigates-claude-plugins/python-plugin
claude plugin install laurigates-claude-plugins/testing-plugin
/health:check then /health:audit to diagnose your setup and get plugin recommendations for your stackUse the included justfile for quick MCP server configuration:
# Set up all MCP servers and cclsp
just claude-setup
# Or install individual servers
just mcp-github
just mcp-playwright
just mcp-context7
Alternatively, use the /configure:mcp skill for interactive configuration.
brew install bash.| Plugin | Skills | Description |
|---|---|---|
| agent-patterns-plugin | 16 | Multi-agent coordination and orchestration patterns |
| agents-plugin | 1 + 10 agents | Task-focused agents for test, review, debug, docs, and CI workflows |
| langchain-plugin | 4 | LangChain JS/TS development - agents, chains, LangGraph, Deep Agents |
| prompt-engineering-plugin | 1 | Prompt engineering for accurate, grounded responses - anti-hallucination workflow |
| Plugin | Skills | Description |
|---|---|---|
| api-plugin | 2 | API integration and testing - REST endpoints, client generation |
| blueprint-plugin | 30 | Blueprint Development methodology - PRD/PRP workflow with version tracking |
| home-assistant-plugin | 4 | Home Assistant configuration - automations, scripts, scenes, entities |
| obsidian-plugin | 6 | Obsidian CLI operations - vault management, search, properties, tasks |
| project-plugin | 6 | Project initialization, management, maintenance, and continuous development |
| Plugin | Skills | Description |
|---|---|---|
| css-plugin | 2 | CSS tooling - Lightning CSS transpilation, UnoCSS atomic utilities |
| python-plugin | 17 | Python ecosystem - uv, ruff, pytest, basedpyright, packaging |
| rust-plugin | 5 | Rust development - cargo, clippy, nextest, memory safety |
| typescript-plugin | 17 | TypeScript development - Bun, Biome, ESLint, strict types |
| Plugin | Skills | Description |
|---|---|---|
| code-quality-plugin | 13 | Code review, refactoring, linting, static analysis, debugging methodology |
| evaluate-plugin | 4 + 3 agents | Skill evaluation and benchmarking - test effectiveness, grade results |
| codebase-attributes-plugin | 3 | Structured codebase health attributes with severity-based agent routing |
| feedback-plugin | 1 | Session feedback analysis - capture skill bugs and enhancements as issues |
| testing-plugin | 15 | Test execution, TDD workflow, Vitest, Playwright, mutation testing |
| Plugin | Skills | Description |
|---|---|---|
| git-plugin | 27 + 1 agent | Git workflows - commits, branches, PRs, worktrees, release-please |
| Plugin | Skills | Description |
|---|---|---|
| finops-plugin | 7 | GitHub Actions FinOps - billing, cache usage, workflow efficiency |
| github-actions-plugin | 8 | GitHub Actions CI/CD - workflows, authentication, inspection |
| Plugin | Skills | Description |
|---|---|---|
| configure-plugin | 42 | Project infrastructure standards - pre-commit, CI/CD, Docker, testing |
| container-plugin | 9 + 1 agent | Container development - Docker, registry, Skaffold, OrbStack |
| kubernetes-plugin | 8 + 1 agent | Kubernetes and Helm - deployments, charts, releases, ArgoCD |
| migration-patterns-plugin | 2 | Safe database and system migration - dual write, shadow mode |
| networking-plugin | 6 | Network diagnostics, discovery, monitoring, HTTP load testing |
| terraform-plugin | 6 + 1 agent | Terraform and Terraform Cloud - infrastructure as code |