plugin-forge
Create and manage Claude Code plugins with proper structure, manifests, and marketplace integration. Use when creating plugins for a marketplace, adding plugin components (commands, agents, hooks), bumping plugin versions, or working with plugin.json/marketplace.json manifests.
- License 许可
- MIT
- 最近更新
- 2026-11-13
- Stars
- ★ 3.3w
- Forks
- 3.9k
01 前言 Front Matter
- name
- plugin-forge
- description
- Create and manage Claude Code plugins with proper structure, manifests, and marketplace integration. Use when creating plugins for a marketplace, adding plugin components (commands, agents, hooks), bumping plugin versions, or working with plugin.json/marketplace.json manifests.
02 资源文件 6
- 参考文档README.md8.6 KB
- 参考文档references/marketplace-schema.md2.4 KB
- 参考文档references/plugin-structure.md2.7 KB
- 参考文档references/workflows.md3.8 KB
- 脚本scripts/bump_version.py3.3 KB
- 脚本scripts/create_plugin.py4.5 KB
03 SKILL.md 正文
CC Plugin Forge
Purpose
Build and manage Claude Code plugins with correct structure, manifests, and marketplace integration. Includes workflows, automation scripts, and reference docs.
When to Use
- Creating new plugins for a marketplace
- Adding/modifying plugin components (commands, skills, agents, hooks)
- Updating plugin versions
- Working with plugin or marketplace manifests
- Setting up local plugin testing
- Publishing plugins
Getting Started
Create New Plugin
Use create_plugin.py to generate plugin structure:
python scripts/create_plugin.py plugin-name \
--marketplace-root /path/to/marketplace \
--author-name "Your Name" \
--author-email "your.email@example.com" \
--description "Plugin description" \
--keywords "keyword1,keyword2" \
--category "productivity"
This automatically:
- Creates plugin directory structure
- Generates
plugin.jsonmanifest - Creates README template
- Updates
marketplace.json
Bump Version
Use bump_version.py to update versions in both manifests:
python scripts/bump_version.py plugin-name major|minor|patch \
--marketplace-root /path/to/marketplace
Semantic versioning:
- major: Breaking changes (1.0.0 → 2.0.0)
- minor: New features, refactoring (1.0.0 → 1.1.0)
- patch: Bug fixes, docs (1.0.0 → 1.0.1)
Development Workflow
1. Create Structure
Manual approach (if not using script):
mkdir -p plugins/plugin-name/.claude-plugin
mkdir -p plugins/plugin-name/commands
mkdir -p plugins/plugin-name/skills
2. Plugin Manifest
File: plugins/plugin-name/.claude-plugin/plugin.json
{
"name": "plugin-name",
"version": "0.1.0",
"description": "Plugin description",
"author": {
"name": "Your Name",
"email": "your.email@example.com"
},
"keywords": ["keyword1", "keyword2"]
}
3. Register in Marketplace
Update .claude-plugin/marketplace.json:
{
"name": "plugin-name",
"source": "./plugins/plugin-name",
"description": "Plugin description",
"version": "0.1.0",
"keywords": ["keyword1", "keyword2"],
"category": "productivity"
}
4. Add Components
Create in respective directories:
| Component | Location | Format |
|---|---|---|
| Commands | commands/ |
Markdown with frontmatter |
| Skills | skills/<name>/ |
Directory with SKILL.md |
| Agents | agents/ |
Markdown definitions |
| Hooks | hooks/hooks.json |
Event handlers |
| MCP Servers | .mcp.json |
External integrations |
5. Local Testing
# Add marketplace
/plugin marketplace add /path/to/marketplace-root
# Install plugin
/plugin install plugin-name@marketplace-name
# After changes: reinstall
/plugin uninstall plugin-name@marketplace-name
/plugin install plugin-name@marketplace-name
Plugin Patterns
Framework Plugin
For framework-specific guidance (React, Vue, etc.):
plugins/framework-name/
├── .claude-plugin/plugin.json
├── skills/
│ └── framework-name/
│ ├── SKILL.md
│ └── references/
├── commands/
│ └── prime/
│ ├── components.md
│ └── framework.md
└── README.md
Utility Plugin
For tools and commands:
plugins/utility-name/
├── .claude-plugin/plugin.json
├── commands/
│ ├── action1.md
│ └── action2.md
└── README.md
Domain Plugin
For domain-specific knowledge:
plugins/domain-name/
├── .claude-plugin/plugin.json
├── skills/
│ └── domain-name/
│ ├── SKILL.md
│ ├── references/
│ └── scripts/
└── README.md
Command Naming
Subdirectory-based namespacing with : separator:
commands/namespace/command.md→/namespace:commandcommands/simple.md→/simple
Examples:
commands/prime/vue.md→/prime:vuecommands/docs/generate.md→/docs:generate
Version Management
Important: Update version in BOTH locations:
plugins/<name>/.claude-plugin/plugin.json.claude-plugin/marketplace.json
Use bump_version.py to automate.
Git Commits
Use conventional commits:
git commit -m "feat: add new plugin"
git commit -m "fix: correct plugin manifest"
git commit -m "docs: update plugin README"
git commit -m "feat!: breaking change"
Reference Docs
Detailed documentation included:
| Reference | Content |
|---|---|
references/plugin-structure.md |
Directory structure, manifest schema, components |
references/marketplace-schema.md |
Marketplace format, plugin entries, distribution |
references/workflows.md |
Step-by-step workflows, patterns, publishing |
Scripts
| Script | Purpose |
|---|---|
scripts/create_plugin.py |
Scaffold new plugin |
scripts/bump_version.py |
Update versions |
04 同仓库更多 Skills
wealthville-pool-scoring
Score DeFi liquidity pools before providing liquidity. Returns a 0-100 pool score and an Enter/Hold/Exit/Reduce/Avoid verdict with calibrated confidence for ~68,800 Solana pools and 575 EVM pools, plus a public miss-inclusive track record. Use when asked whether a pool is worth LPing into, which pools look best right now, or how accurate the scores have actually been.
technical-debt-auditor
Scans a codebase and produces a quantified technical debt report with a prioritized remediation plan. Analyzes dead code, TODO/FIXME/HACK markers, dependency staleness, complexity hotspots, code duplication signals, test coverage gaps, unused exports, and outdated patterns. Use this skill when the user asks to audit their codebase for tech debt, wants a health check of their code quality, says things like "where should I focus refactoring", "find code smells", "audit my codebase", "what technical debt do we have", "prioritize cleanup work", or asks about code quality metrics. Also trigger when the user mentions "code rot", "legacy cleanup", "refactoring priorities", or wants to understand the overall health of a project before a major effort. Trigger even if the user doesn't say "technical debt" explicitly — any request to systematically assess code quality and identify improvement priorities belongs here.
readonly-sql-guard
Make an agent's database access provably read-only. Use when an agent runs caller-supplied SQL against a production/ERP/analytics database (a "query" MCP tool, text-to-SQL, an admin console), or when reviewing DB-access code for write/DDL/side-effect/transaction-escape risks. Checks what a statement CALLS, not just its shape.
web-artifacts-builder
Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts.
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
discernment-nudge
After you give a substantive answer or draft that the user may act on — advice or recommendations, drafted artifacts such as goals, plans, pitches, proposals, or emails, estimates or projections, analysis or interpretation of data, factual claims they may rely on, or a multi-step argument — invoke this skill BEFORE finalizing your reply and then, if it applies, append 2-3 short follow-up questions, each tied to something specific in what you just produced, that help the user check key facts, probe the reasoning or assumptions, and notice missing context. Do this at most once per conversation. Skip it when the user asked a trivial how-to or simple lookup, wants a purely educational explanation, asked you only to format, convert, or assemble a file from content they provided, is writing code they will run, is doing creative writing or casual chat, or already asked you to double-check, cite, or review — the skill file explains these boundaries and the exact output format.