By wangke19
Structured learning and analysis skills for understanding concepts, technologies, codebases, and making technical decisions
Architecture review of a repository or codebase
Structured root cause analysis for bugs and errors
Trace a specific mechanism step by step
System design consultation with trade-offs and recommendation
Side-by-side comparison of two technologies or approaches
Ramp up on a new project, framework, library, or technical concept from scratch — structured as a system walkthrough with analogies for an engineer who has general experience but zero prior exposure to this specific thing. Use when the user is encountering something for the first time: a new framework (React, Terraform, Kafka), a new project they just joined, a new protocol or standard, a new tool or platform. Trigger on phrases like "I'm new to X", "just started learning X", "onboard me on X", "walk me through X", "ramp me up on X", "I need to get up to speed on X". Do NOT use for concepts the user already knows and wants a deeper technical briefing on (use ask:tech), or for general non-technical topics (use ask:thing).
Explain any technical concept, system, protocol, or technology as a system design briefing for an experienced engineer — then follow up with common pitfalls and key takeaways. Use when the user asks about technical topics like databases, protocols, distributed systems, algorithms, infrastructure, frameworks, networking, OS concepts, cloud services, etc. Trigger on phrases like "explain X technically", "how does X work under the hood", "break down X for me", "what is X (technical topic)". Do NOT use for general non-technical concepts (use ask:thing), code/repo analysis, or debugging — those have dedicated skills.
Quickly understand any general concept, phenomenon, or thing using a structured cognitive model. Use when the user asks "what is X", "explain X", "help me understand X", "tell me about X", or any variation of wanting to learn about a non-technical, general-knowledge topic (e.g., economics concepts, scientific phenomena, philosophies, historical events, social systems, everyday things like coffee or batteries). Do NOT use for code/repo analysis, debugging, system design, or tech deep-dives — those have dedicated ask:* skills.
Perform a systematic architecture review of a repository or codebase. Analyzes project structure, core components, data/control flows, key abstractions, and design decisions — focused on the critical path, not line-by-line code explanation. Use when the user asks to "analyze this repo", "review this codebase", "walk me through this project's architecture", "what does this repo do", "break down this project", "explain the structure of this code", or points you at a repository and wants to understand how it's designed. Also trigger when the user shares a repo URL or path and asks broad questions like "how does this work" or "what's going on here". Do NOT use for debugging (use ask:debug), general tech concepts (use ask:tech), or non-technical topics (use ask:thing).
Structured debugging assistance — analyze a problem description, logs, and symptoms to produce ranked root causes with verification steps and a minimal investigation path. Use when the user reports a bug, error, unexpected behavior, or production issue and wants help figuring out what's wrong. Trigger on "I'm seeing X error", "this is broken", "help me debug X", "why is X happening", "getting this error", "something went wrong with X", or when the user pastes logs/errors and asks for help. Do NOT use for understanding how systems work (use ask:tech or ask:deep-dive), designing new systems (use ask:design), or general learning (use ask:thing).
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.
Personal Claude Code plugin marketplace.
| Plugin | Description | Skills |
|---|---|---|
| ask | Structured learning and analysis | thing, tech, onboard, analyze-repo, deep-dive, design, debug, diff |
| utils | Productivity tools | slack-copy-rich, technical-presentation-generator |
| cc-aid | Claude Code helpers | session-init, session-checkpoint, session-summary, session-postmortem |
| report | Work report generation | work-report |
| ci | CI/CD helpers | prow-job-retry |
Register as a local marketplace in ~/.claude/plugins/known_marketplaces.json:
{
"my-claude-skills": {
"source": {
"source": "directory",
"path": "/home/kewang/src/gitlab/my-claude-skills"
},
"installLocation": "/home/kewang/src/gitlab/my-claude-skills",
"lastUpdated": "2026-03-26T00:00:00.000Z"
}
}
Then enable plugins in ~/.claude/settings.json under enabledPlugins.
.claude-plugin/marketplace.json # Plugin registry
plugins/
<plugin-name>/
.claude-plugin/plugin.json # Plugin metadata
skills/
<skill-name>/SKILL.md # Skill definition
Ke Wang — [email protected] — Red Hat OpenShift Control Plane Team
npx claudepluginhub wangke19/my-claude-skills --plugin askStructured learning and step-by-step coaching for technical topics
Claude Code session management and quality-of-life helpers
Work report generation from Jira and GitHub data
CI/CD helpers for Prow jobs and OpenShift CI
Utility skills for presentations, clipboard, and other productivity tools
Core skills: ecosystem guide, skill creator, research patterns, session reflection, and plugin development. Includes UserPromptSubmit hook for forced skill evaluation.
Meta-cognitive tools for Claude Code self-improvement. Learn from feedback, optimize configuration, and evolve your AI development workflow.
Curate auto-memory, promote learnings to CLAUDE.md and rules, extract proven patterns into reusable skills.
AI Agent Skills
Skill and agent authoring tools: generate, audit, and improve Claude Code skills, commands, and agents
Create, test, measure, and iteratively improve Claude Code skills with category-aware design, gotchas-driven development, progressive disclosure coaching, and automated description optimization.