This skill should be used when the user asks to "install a plugin", "extend a plugin", "create a .local.md file", "add project context for a plugin", "customize plugin for this project", or mentions project-specific paths, conventions, or workflows that relate to an installed plugin. Covers the .local.md extension pattern for bridging general plugin skills to specific codebases.
When installing a plugin or needing project-specific plugin guidance, create `.claude/<plugin-name>.local.md` files to bridge general plugin skills to your codebase with custom paths, conventions, and workflows.
/plugin marketplace add ImproperSubset/hh-agentics/plugin install cc-governance@hh-agenticsThis skill inherits all available tools. When active, it can use any tool Claude has access to.
Extend marketplace plugins with project-specific context using .local.md files. These files bridge general plugin skills to a specific codebase.
Apply this skill when:
.local.md files are agent context (for Claude), not human documentation (like READMEs or guides). Treat them like CLAUDE.md in purpose.
.claude/<plugin-name>.local.md
Examples:
.claude/cc-governance-skills.local.md.claude/fvtt-skills.local.md---
plugin: <plugin-name>
project: <project-name>
---
# <Plugin Name> - Project-Specific Context
This file extends the `<plugin-name>` plugin with <project>-specific information.
## <Section relevant to plugin's skills>
<Project-specific details>
| Field | Purpose |
|---|---|
plugin | Name of the marketplace plugin being extended |
project | Name of the current project |
File paths - Where plugin patterns are implemented in this project
| Skill | Implementation Files |
|-------|---------------------|
| `fvtt-performance-safe-updates` | `scripts/lib/update-queue.js`, `scripts/hooks.js` |
Project conventions - How general patterns apply here
### Actor Types
- `character` - Player characters
- `crew` - Crew sheets
Workflows - Project-specific processes
### Git Workflow
- Feature branches → PR to `upstream/rc-1.1.0`
- Use `--head ImproperSubset:branch-name` for cross-fork PRs
Build commands - Project-specific tooling
## Build Commands
npm run build:css # Compile SCSS
npm run lint:css # Stylelint
Reminders - Project-specific gotchas related to plugin skills
### Multi-Client Development
Every update handler MUST have:
1. Ownership guard
2. No-op check
3. Batched updates
settings.local.json)Commit extension files containing project-specific context to the repository. This ensures all contributors using the plugins get the enhanced context.
# .gitignore - DON'T ignore project context
# .claude/*.local.md <-- Remove this line
Gitignore only personal settings:
# .gitignore
.claude/settings.local.json
---
plugin: fvtt-skills
project: my-foundry-module
---
# FVTT Skills - Project-Specific Context
This file extends the `fvtt-skills` plugin with my-foundry-module-specific information.
## File Paths
| Skill | Implementation Files |
|-------|---------------------|
| `fvtt-performance-safe-updates` | `scripts/lib/update-queue.js` |
| `fvtt-version-compat` | `scripts/compat.js` |
## Project Conventions
### Document Types
- `character` - Player characters
- `npc` - Non-player characters
### Flag Namespace
```javascript
actor.getFlag("my-foundry-module", "flagName")
npm run build # Build module
npm run test # Run tests
## When NOT to Create Extension Files
- Plugin is used without project-specific customization
- Information belongs in CLAUDE.md (not plugin-specific)
- Content is personal preference (use `settings.local.json`)
This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.
This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, or command development best practices for Claude Code.
This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.