By WeZZard
Execute complex coding plans in Claude Code sessions via subagents that parallelize topological task execution from dependency graphs, recover from errors autonomously, generate and audit detailed plans, brainstorm designs collaboratively, and provide structured explanations of prior actions.
You MUST invoke after plan execution completes to verify all planned changes were implemented correctly. Use as the final step of a plan-based workflow.
<MANDATORY>You MUST invoke this skill when the user wants to explore ideas, discuss approaches, research a topic, or has been stuck on a problem. Always brainstorm before beginning implementation.</MANDATORY>
You MUST invoke this skill immediately when you have a finalized plan file and are ready to begin implementation. Always use this skill before starting to write code based on a plan.
<MANDATORY>You MUST invoke this skill immediately when you encounter repeated errors, unexpected failures, or blockers during plan execution.</MANDATORY>
You MUST invoke this skill when the user asks you to explain, clarify, or justify your previous message. Produces an adaptively structured explanation with evidence, confidence, and ASCII art—format is chosen per message, not fixed.
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 standalone Claude Code plugin marketplace containing WeZZard skills collection.
From inside Claude Code:
/plugin marketplace add ./
If you host on GitHub later:
/plugin marketplace add WeZZard/skills
/plugin install amplify@wezzard-skills
# wezzard plugin skills
/amplify:brainstorming
/amplify:write-plan
/amplify:execute-plan
/amplify:recover-from-errors
Development workflow skills for planning and execution.
| Skill | Description |
|---|---|
brainstorming | Explore user intent, requirements and design before implementation |
write-plan | Create and update plan files with structured templates |
execute-plan | Execute a plan file step by step |
recover-from-errors | Recover from errors during execution |
same-page | Explain previous message with adaptive layout, evidence, confidence, and ASCII art |
.claude-plugin/marketplace.json
claude/amplify/.claude-plugin/plugin.json
claude/<plugin-name>/skills/<skill-name>/SKILL.md
Notes:
plugin.json lives inside .claude-plugin/. All other folders stay at the plugin root./<plugin-name>:<skill-name>.mkdir -p claude/<plugin-name>/skills/<skill-name>
claude/<plugin-name>/skills/<skill-name>/SKILL.md
Frontmatter should include at least name and description. You can add disable-model-invocation: true to make it manual-only.
claude --plugin-dir ./claude/<plugin-name>
marketplace.json, use Git or GitHub sources instead of relative paths.After cloning, run the setup script to enable automatic plugin version bumping:
sh scripts/setup.sh
This configures Git to use tracked hooks from .githooks/. When you commit changes to any plugin under claude/, the patch version in its plugin.json is automatically incremented. To set major or minor versions manually, edit plugin.json and stage it before committing — the hook respects manually staged version changes.
The website/ directory contains a static site that showcases the skills with LLM-generated explanations.
cd website
npm install
Requires DEEPSEEK_API_KEY environment variable:
export DEEPSEEK_API_KEY=your-api-key
npm run generate
This reads each SKILL.md and generates user-friendly descriptions with workflow diagrams. Generated content is cached in src/content/generated/ - only regenerated when source changes.
npm run dev
npm run build
Output goes to website/dist/.
npx claudepluginhub wezzard/skills --plugin amplifyZelda BotW & TotK sound effects for Claude Code events with GUI configurator
Complete toolkit for creating, validating, and managing Claude Code skills with intelligent agents, interactive commands, and professional templates
Structured implementation planning, interactive annotation review, and autonomous plan execution
Claude Code customization tools. Includes 0 agents, 13 commands, and 12 skills.
Create, test, measure, and iteratively improve Claude Code skills with category-aware design, gotchas-driven development, progressive disclosure coaching, and automated description optimization.
Meta-skills infrastructure for Claude Code plugin ecosystem - skill authoring, hook development, modular design patterns, and evaluation frameworks
Ultra-compressed communication mode. Cuts ~75% of tokens while keeping full technical accuracy by speaking like a caveman.