菜单
This skill should be used when the user asks to "validate plugin structure", "review manifest files", "check frontmatter compliance", "verify tool invocation patterns", "explain plugin component types", or needs Claude Code plugin architectural guidance.
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/FradSer/dotclaude --skill plugin-best-practices命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
正在显示 SKILL.md
| name | plugin-best-practices |
| description | This skill should be used when the user asks to "validate plugin structure", "review manifest files", "check frontmatter compliance", "verify tool invocation patterns", "explain plugin component types", or needs Claude Code plugin architectural guidance. |
| user-invocable | false |
Validates Claude Code plugins against architectural standards. This file is a navigation guide; detailed content lives in references/.
Run validation on a plugin:
python3 ${CLAUDE_PLUGIN_ROOT}/scripts/validate-plugin.py <plugin-path>
For specific checks only:
python3 ${CLAUDE_PLUGIN_ROOT}/scripts/validate-plugin.py <plugin-path> --check=manifest,frontmatter
| Component | When to Use | Key Requirements |
|---|---|---|
| Instruction-type Skills | User-invoked workflows, linear process | Imperative voice, phase-based, declared in commands; name with use-<action> prefix (e.g., use-kicad-cli) |
| Knowledge-type Skills | Reference knowledge for agents | Declarative voice, topic-based, declared in skills; name with using-<topic> prefix (e.g., ) |
using-git-worktrees| Agents | Isolated, specialized decision-making | Restricted tools, 2-4 <example> blocks, isolated context |
| MCP Servers | External tool/data integration | stdio/http/sse transport, ${CLAUDE_PLUGIN_ROOT} paths |
| LSP Servers | IDE features (go to definition) | Language server binary, extension mapping |
| Hooks | Event-driven automation | Lifecycle events, command/http/mcp_tool/prompt/agent types |
| Monitors | Long-running watchers (logs, deploys) | name+command+description per entry; v2.1.105+ |
| Themes | Bundled color presets | JSON with name, base, overrides |
| Output Styles | Adjust response formatting | Markdown with name + description frontmatter |
See ./references/component-model.md for detailed selection criteria and ./references/components/ for implementation guides.
Three-tier token structure ensures efficient context usage:
| Level | Content | Token Budget | Loading |
|---|---|---|---|
| 1 | Metadata (name + description) | ~100 tokens | Always (at startup) |
| 2 | SKILL.md body | Under 5k tokens | When skill triggered |
| 3 | References/ files | Effectively unlimited | On-demand via bash |
Implementation Pattern:
See ./references/component-model.md for complete token budget guidelines.
Five sequential checks cover all plugin quality dimensions:
Run validation with -v flag for verbose output showing all passing checks.
See ./references/validation-checklist.md for complete criteria.
Plugin documentation uses RFC 2119 requirement levels:
See ./references/rfc-2119.md for complete RFC 2119 specification.
| Tool | Style | Example |
|---|---|---|
| Read, Write, Edit, Glob, Grep | Implicit | "Find files matching..." |
| Bash | Implicit | "Run git status" |
| Task | Implicit | "Launch plugin-name:agent-name agent" |
| Skill | Explicit | "Load plugin-name:skill-name skill using the Skill tool" |
| TaskCreate | Explicit | "Use TaskCreate tool to track progress" |
| AskUserQuestion | Explicit | "Use AskUserQuestion tool to [action]" |
| MCP Tools | Implicit | "Query the database for user records" |
Qualified names: MUST use plugin-name:component-name format for plugin components.
allowed-tools: NEVER use bare Bash - always use filters like Bash(git:*).
Inline Bash: Use inline syntax (exclamation + backtick + command + backtick) for dynamic context.
MCP Tool Invocation: Use natural language to describe intent — Claude automatically identifies the appropriate MCP tool. Never specify exact MCP tool names like mcp__server__tool in skill content.
See ./references/tool-invocations.md for complete patterns and anti-patterns.
See ./references/mcp-patterns.md for MCP-specific invocation patterns.
Required fields:
name: Max 64 chars, lowercase letters/numbers/hyphens only. Naming convention by type: instruction-type skills use a use-<action> prefix (e.g., use-kicad-cli); knowledge-type skills use a using-<topic> prefix (e.g., using-git-worktrees).description: Max 1024 chars. MUST use third-person voice with specific trigger phrases.Description Best Practices:
| Requirement | Description |
|---|---|
| Person | Third-person only ("This skill should be used when...") |
| Structure | [What it does]. Use when [scenario 1], [scenario 2], or [user phrases]. |
| Purpose | Skill discovery - Claude uses this to select from 100+ skills |
| Trigger phrases | Include specific user phrases like "validate plugin", "check frontmatter" |
Additional fields are supported but affect progressive disclosure alignment.
See ./references/components/skills.md for complete frontmatter specification.
Required fields (per upstream spec):
name: 3-50 chars, kebab-casedescription: trigger conditions plus 2-4 <example> blocksOptional fields: model, color, effort, maxTurns, tools, disallowedTools, skills, memory, background, isolation (only "worktree" is valid).
Forbidden fields in plugin agents (security): hooks, mcpServers, permissionMode.
Field order: name → description (a | block scalar containing trigger conditions and the <example> blocks) → other YAML fields → closing ---. Bare <example> blocks outside the description break YAML parsing.
See ./references/components/agents.md for complete agent design guidelines including CO-STAR framework.
Tasks with 3+ distinct steps, multi-file work, or sequential dependencies warrant TaskCreate. Single-file edits and 1-2 step operations do not.
Core Requirements:
in_progress BEFORE starting, completed AFTER finishingcompleted when FULLY doneSee ./references/task-management.md for complete patterns and examples.
MCP servers are configured in .mcp.json at plugin root or inline in plugin.json under mcpServers. Three transport types are supported: stdio (local CLI tools), http (remote APIs, most widely supported), and sse (real-time streaming).
NEVER hardcode secrets — always use ${ENV_VAR} syntax.
See ./references/mcp-patterns.md for complete MCP integration patterns.
See ./references/components/mcp-servers.md for component configuration details.
Hook events cover the full session lifecycle (28+ events including PreToolUse, PostToolUse, PostToolUseFailure, PostToolBatch, PermissionRequest, PermissionDenied, UserPromptSubmit, UserPromptExpansion, Setup, Notification, Stop/StopFailure, SubagentStart/SubagentStop, TaskCreated/TaskCompleted, TeammateIdle, InstructionsLoaded, ConfigChange, CwdChanged, FileChanged, WorktreeCreate/WorktreeRemove, PreCompact/PostCompact, Elicitation/ElicitationResult, SessionStart/SessionEnd). Five hook types: command, http, mcp_tool, prompt, agent.
See ./references/components/hooks.md for the full event table and AI-native structured output patterns.
Subagents are isolated, single-direction sub-processes returning results to the caller. Agent Teams are multiple independent sessions sharing a task list with direct peer-to-peer communication — suited for parallel investigation, multi-module features, and competing hypotheses.
| Subagents | Agent Teams | |
|---|---|---|
| Context | Returns to caller | Fully independent |
| Communication | To main agent only | Direct peer-to-peer |
| Token cost | Lower (summarized) | Higher (full instances) |
Agent Teams are experimental. Enable with export CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1.
See ./references/agent-teams.md for complete guide and ./references/parallel-execution.md for parallel coordination patterns.
Standard Layout:
plugin-name/
├── .claude-plugin/plugin.json # Manifest (declare components here)
├── skills/ # Agent Skills (RECOMMENDED)
│ └── skill-name/
│ ├── SKILL.md
│ └── references/
├── commands/ # Skills as flat .md files (legacy)
├── agents/ # Subagent definitions
├── output-styles/ # Output style markdown
├── themes/ # Color theme JSON
├── monitors/monitors.json # Background monitor configs
├── hooks/hooks.json # Hook configuration
├── bin/ # Executables added to Bash PATH
├── settings.json # Plugin default settings
├── .mcp.json # MCP server definitions
├── .lsp.json # LSP server configurations
└── scripts/ # Executable scripts
Critical Rules:
.claude-plugin/${CLAUDE_PLUGIN_ROOT} for paths./See ./references/directory-structure.md for complete layout guidelines.
./references/validation-checklist.md - Complete quality checklist./references/rfc-2119.md - Requirement levels (MUST/SHOULD/MAY)./references/component-model.md - Component types, selection criteria, token budgets./references/components/skills.md - Skill structure, frontmatter, progressive disclosure./references/components/agents.md - Agent design, CO-STAR framework, forbidden fields./references/components/commands.md - Command frontmatter, dynamic context./references/components/hooks.md - Hook events, types, AI-native patterns, templates./references/components/mcp-servers.md - MCP configuration, stdio/http/sse./references/components/lsp-servers.md - LSP setup, binary requirements./references/components/monitors.md - Background monitor configuration./references/components/themes.md - Color theme JSON structure./references/components/output-styles.md - Output style frontmatter./references/directory-structure.md - Plugin layout, naming conventions./references/manifest-schema.md - plugin.json schema, required fields./references/mcp-patterns.md - MCP transport types, security best practices./references/tool-invocations.md - Tool usage patterns and anti-patterns./references/tool-design-philosophy.md - Principles for designing tools that work with Claude's strengths./references/task-management.md - TaskCreate patterns, dual-form naming./references/cli-commands.md - CLI commands for plugin management./references/agent-teams.md - Parallelizable tasks, multi-perspective analysis./references/parallel-execution.md - Parallel agent coordination patterns./references/debugging.md - Common issues, error messages, troubleshootingReviews a pull request: runs its own baseline review of the PR diff, then a persistent Monitor watches CI and incoming reviewer comments, triages each comment through an independent skeptical agent, applies only verified fixes, and commits+pushes via inline git commands until CI passes and no comments remain to adopt — then asks whether to merge. Use this skill when the user asks to "review a PR", "monitor PR review comments", "address reviewer feedback on #123", or "watch CI on a pull request".
Creates atomic conventional git commits using git-agent and pushes changes to the remote repository.
Creates atomic conventional git commits using git-agent. This skill should be used when the user requests "commit", "git commit", "create commit", or wants to commit changes using AI atomic commits.
基于 SOC 职业分类
