plugin-structure
This skill should be used when the user asks to "create a plugin", "scaffold a plugin", "understand plugin structure", "organize plugin components", "set up plugin.json", "use ${PLUGIN_ROOT}", "add commands/agents/skills/hooks", "configure auto-discovery", or needs guidance on plugin directory layout, manifest configuration, component organization, file naming conventions, or DeepSeek Harness plugin architecture best practices.
- License 许可
- MIT
- 最近更新
- 2026-11-14
- Stars
- ★ 21
- Forks
- 2
01 前言 Front Matter
- name
- plugin-structure
- description
- This skill should be used when the user asks to "create a plugin", "scaffold a plugin", "understand plugin structure", "organize plugin components", "set up plugin.json", "use ${PLUGIN_ROOT}", "add commands/agents/skills/hooks", "configure auto-discovery", or needs guidance on plugin directory layout, manifest configuration, component organization, file naming conventions, or DeepSeek Harness plugin architecture best practices.
02 资源文件 6
- 参考文档examples/advanced-plugin.md18.2 KB
- 参考文档examples/minimal-plugin.md1.7 KB
- 参考文档examples/standard-plugin.md12.9 KB
- 参考文档README.md3.1 KB
- 参考文档references/component-patterns.md11.9 KB
- 参考文档references/manifest-reference.md11.8 KB
03 SKILL.md 正文
Plugin Structure for DeepSeek Harness
Overview
DeepSeek Harness plugins follow a standardized directory structure with automatic component discovery. Understanding this structure enables creating well-organized, maintainable plugins that integrate seamlessly with DeepSeek Harness.
Key concepts:
- Conventional directory layout for automatic discovery
- Manifest-driven configuration in
plugin.json - Component-based organization (commands, agents, skills, hooks)
- Portable path references using
${PLUGIN_ROOT} - Explicit vs. auto-discovered component loading
Directory Structure
Every DeepSeek Harness plugin follows this organizational pattern:
plugin-name/
├── plugin.json # Required: Plugin manifest
├── mcp.json # Optional: MCP server definitions (portable)
├── skills/ # Agent skills (subdirectories)
│ └── skill-name/
│ └── SKILL.md # Required for each skill
└── com.deepseek.harness/ # Optional client namespace directory
├── commands/ # Slash commands (.md files)
├── agents/ # Subagent definitions (.md files)
├── hooks/
│ └── hooks.json # Event handler configuration
└── lsp.json # LSP server declarations
Critical rules:
- Manifest location: The
plugin.jsonmanifest MUST be at the plugin root - Namespace declaration: The
com.deepseek.harness/directory is read only when the manifest declaresextensions["com.deepseek.harness"].schemaVersionas"1.0.0"; without it the portable core (skills/,mcp.json) still loads - Optional components: Only create directories for components the plugin actually uses
- Naming convention: Use kebab-case for all directory and file names
Plugin Manifest (plugin.json)
The manifest defines plugin metadata and configuration. Located at plugin.json:
Required Fields
{
"name": "plugin-name"
}
Name requirements:
- Use kebab-case format (lowercase with hyphens)
- Must be unique across installed plugins
- No spaces or special characters
- Example:
code-review-assistant,test-runner,api-docs
Recommended Metadata
{
"name": "plugin-name",
"version": "1.0.0",
"description": "Brief explanation of plugin purpose",
"author": {
"name": "Author Name",
"email": "author@example.com",
"url": "https://example.com"
},
"homepage": "https://docs.example.com",
"repository": "https://github.com/user/plugin-name",
"license": "MIT",
"keywords": ["testing", "automation", "ci-cd"]
}
Version format: Follow semantic versioning (MAJOR.MINOR.PATCH) Keywords: Use for plugin discovery and categorization
Component Path Configuration
Specify custom paths for components (supplements default directories):
{
"name": "plugin-name",
"commands": "./custom-commands",
"agents": ["./agents", "./specialized-agents"],
"hooks": "./config/hooks.json",
"mcpServers": "./mcp.json"
}
Important: Custom paths supplement defaults—they don't replace them. Components in both default directories and custom paths will load.
Path rules:
- Must be relative to plugin root
- Must start with
./ - Cannot use absolute paths
- Support arrays for multiple locations
Component Organization
Commands
Location: com.deepseek.harness/commands/ directory
Format: Markdown files with YAML frontmatter
Auto-discovery: All .md files in com.deepseek.harness/commands/ load automatically
Example structure:
commands/
├── review.md # /review command
├── test.md # /test command
└── deploy.md # /deploy command
File format:
---
name: command-name
description: Command description
---
Command implementation instructions...
Usage: Commands integrate as native slash commands in DeepSeek Harness
Agents
Location: com.deepseek.harness/agents/ directory
Format: Markdown files with YAML frontmatter
Auto-discovery: All .md files in com.deepseek.harness/agents/ load automatically
Example structure:
agents/
├── code-reviewer.md
├── test-generator.md
└── refactorer.md
File format:
---
description: Agent role and expertise
capabilities:
- Specific task 1
- Specific task 2
---
Detailed agent instructions and knowledge...
Usage: Users can invoke agents manually, or DeepSeek Harness selects them automatically based on task context
Skills
Location: skills/ directory with subdirectories per skill
Format: Each skill in its own directory with SKILL.md file
Auto-discovery: All SKILL.md files in skill subdirectories load automatically
Example structure:
skills/
├── api-testing/
│ ├── SKILL.md
│ ├── scripts/
│ │ └── test-runner.py
│ └── references/
│ └── api-spec.md
└── database-migrations/
├── SKILL.md
└── examples/
└── migration-template.sql
SKILL.md format:
---
name: Skill Name
description: When to use this skill
version: 1.0.0
---
Skill instructions and guidance...
Supporting files: Skills can include scripts, references, examples, or assets in subdirectories
Usage: DeepSeek Harness autonomously activates skills based on task context matching the description
Hooks
Location: com.deepseek.harness/hooks/hooks.json or inline in plugin.json
Format: JSON configuration defining event handlers
Registration: Hooks register automatically when plugin enables
Example structure:
hooks/
├── hooks.json # Hook configuration
└── scripts/
├── validate.sh # Hook script
└── check-style.sh # Hook script
Configuration format:
{
"PreToolUse": [{
"matcher": "Write|Edit",
"hooks": [{
"type": "command",
"command": "bash ${PLUGIN_ROOT}/hooks/scripts/validate.sh",
"timeout": 30
}]
}]
}
Available events: PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification
Usage: Hooks execute automatically in response to DeepSeek Harness events
MCP Servers
Location: mcp.json at plugin root or inline in plugin.json
Format: JSON configuration for MCP server definitions
Auto-start: Servers start automatically when plugin enables
Example format:
{
"mcpServers": {
"server-name": {
"command": "node",
"args": ["${PLUGIN_ROOT}/servers/server.js"],
"env": {
"API_KEY": "${API_KEY}"
}
}
}
}
Usage: MCP servers integrate seamlessly with DeepSeek Harness's tool system
Portable Path References
${PLUGIN_ROOT}
Use ${PLUGIN_ROOT} environment variable for all intra-plugin path references:
{
"command": "bash ${PLUGIN_ROOT}/scripts/run.sh"
}
Why it matters: Plugins install in different locations depending on:
- User installation method (marketplace, local, npm)
- Operating system conventions
- User preferences
Where to use it:
- Hook command paths
- MCP server command arguments
- Script execution references
- Resource file paths
Never use:
- Hardcoded absolute paths (
/Users/name/plugins/...) - Relative paths from working directory (
./scripts/...in commands) - Home directory shortcuts (
~/plugins/...)
Path Resolution Rules
In manifest JSON fields (hooks, MCP servers):
"command": "${PLUGIN_ROOT}/scripts/tool.sh"
In component files (commands, agents, skills):
Reference scripts at: ${PLUGIN_ROOT}/scripts/helper.py
In executed scripts:
#!/bin/bash
# ${PLUGIN_ROOT} available as environment variable
source "${PLUGIN_ROOT}/lib/common.sh"
File Naming Conventions
Component Files
Commands: Use kebab-case .md files
code-review.md→/code-reviewrun-tests.md→/run-testsapi-docs.md→/api-docs
Agents: Use kebab-case .md files describing role
test-generator.mdcode-reviewer.mdperformance-analyzer.md
Skills: Use kebab-case directory names
api-testing/database-migrations/error-handling/
Supporting Files
Scripts: Use descriptive kebab-case names with appropriate extensions
validate-input.shgenerate-report.pyprocess-data.js
Documentation: Use kebab-case markdown files
api-reference.mdmigration-guide.mdbest-practices.md
Configuration: Use standard names
hooks.jsonmcp.jsonplugin.json
Auto-Discovery Mechanism
DeepSeek Harness automatically discovers and loads components:
- Plugin manifest: Reads
plugin.jsonwhen plugin enables - Commands: Scans
com.deepseek.harness/commands/directory for.mdfiles - Agents: Scans
com.deepseek.harness/agents/directory for.mdfiles - Skills: Scans
skills/for subdirectories containingSKILL.md - Hooks: Loads configuration from
com.deepseek.harness/hooks/hooks.jsonor manifest - MCP servers: Loads configuration from
mcp.jsonor manifest
Discovery timing:
- Plugin installation: Components register with DeepSeek Harness
- Plugin enable: Components become available for use
- No restart required: Changes take effect on next DeepSeek Harness session
Override behavior: Custom paths in plugin.json supplement (not replace) default directories
Best Practices
Organization
-
Logical grouping: Group related components together
- Put test-related commands, agents, and skills together
- Create subdirectories in
scripts/for different purposes
-
Minimal manifest: Keep
plugin.jsonlean- Only specify custom paths when necessary
- Rely on auto-discovery for standard layouts
- Use inline configuration only for simple cases
-
Documentation: Include README files
- Plugin root: Overall purpose and usage
- Component directories: Specific guidance
- Script directories: Usage and requirements
Naming
-
Consistency: Use consistent naming across components
- If command is
test-runner, name related agenttest-runner-agent - Match skill directory names to their purpose
- If command is
-
Clarity: Use descriptive names that indicate purpose
- Good:
api-integration-testing/,code-quality-checker.md - Avoid:
utils/,misc.md,temp.sh
- Good:
-
Length: Balance brevity with clarity
- Commands: 2-3 words (
review-pr,run-ci) - Agents: Describe role clearly (
code-reviewer,test-generator) - Skills: Topic-focused (
error-handling,api-design)
- Commands: 2-3 words (
Portability
- Always use ${PLUGIN_ROOT}: Never hardcode paths
- Test on multiple systems: Verify on macOS, Linux, Windows
- Document dependencies: List required tools and versions
- Avoid system-specific features: Use portable bash/Python constructs
Maintenance
- Version consistently: Update version in plugin.json for releases
- Deprecate gracefully: Mark old components clearly before removal
- Document breaking changes: Note changes affecting existing users
- Test thoroughly: Verify all components work after changes
Common Patterns
Minimal Plugin
Single command with no dependencies:
my-plugin/
├── plugin.json
└── commands/
└── hello.md # Single command
Full-Featured Plugin
Complete plugin with all component types:
my-plugin/
├── plugin.json
├── com.deepseek.harness/
│ ├── commands/ # User-facing commands
│ ├── agents/ # Specialized subagents
│ └── hooks/
│ ├── hooks.json
│ └── scripts/
├── skills/ # Auto-activating skills
├── mcp.json # External integrations
└── scripts/ # Shared utilities
Skill-Focused Plugin
Plugin providing only skills:
my-plugin/
├── plugin.json
└── skills/
├── skill-one/
│ └── SKILL.md
└── skill-two/
└── SKILL.md
Troubleshooting
Component not loading:
- Verify file is in correct directory with correct extension
- Check YAML frontmatter syntax (commands, agents, skills)
- Ensure skill has
SKILL.md(notREADME.mdor other name) - For namespace components, confirm the manifest declares
extensions["com.deepseek.harness"].schemaVersion - Confirm plugin is enabled in DeepSeek Harness settings
Path resolution errors:
- Replace all hardcoded paths with
${PLUGIN_ROOT} - Check that referenced files exist at specified paths
- Test with
echo $PLUGIN_ROOTin hook scripts
Auto-discovery not working:
- Confirm skills sit at
skills/<name>/SKILL.md(one level deep) - Confirm namespace components sit under
com.deepseek.harness/ - Check file naming follows conventions (kebab-case, correct extensions)
- Restart DeepSeek Harness to reload plugin configuration
Conflicts between plugins:
- Use unique, descriptive component names
- Namespace commands with plugin name if needed
- Document potential conflicts in plugin README
- Consider command prefixes for related functionality
For detailed examples and advanced patterns, see files in references/ and examples/ directories.
04 同仓库更多 Skills
verify
Verify that a code change actually does what it's supposed to by running the app and observing behavior. Use when asked to verify a PR, confirm a fix works, test a change manually, check that a feature works, or validate local changes before pushing.
simplify
Review changed code for reuse, quality, and efficiency, then fix any issues found. Use when the user asks to "simplify the code", "clean up the diff", "reduce duplication in my changes", or after finishing a feature before committing.
insight
Analyze this machine's DeepSeek Harness session history and report how sessions actually go — operating style, what works, friction points, and what to try next. Use when the user asks "how have I been using this", "analyze my sessions", "make an insight report", or wants a retrospective.
init
Set up a minimal AGENTS.md (and optionally skills and hooks) for this repo. Use when the user asks to "initialize the project", "generate AGENTS.md", "set up project instructions", or runs /init.
explore
Fast read-only codebase exploration that returns a report instead of filling the main context. Use when the user asks to "explore the codebase", "find where X is handled", "how does Y work", or when a search would take many reads to answer.
automation-recommender
Analyze a codebase and recommend DeepSeek Harness automations (hooks, subagents, skills, plugins, MCP servers). Use when user asks for automation recommendations, wants to optimize their DeepSeek Harness setup, mentions improving DeepSeek Harness workflows, asks how to first set up DeepSeek Harness for a project, or wants to know what DeepSeek Harness features they should use.