Best practices for creating custom slash commands with frontmatter, arguments, bash execution, and file references. Use when creating slash commands.
Creates custom slash commands with frontmatter, arguments, bash execution, and file references.
npx claudepluginhub kkhys/claude-code-marketplaceThis skill inherits all available tools. When active, it can use any tool Claude has access to.
references/examples.mdreferences/frontmatter.mdFirst, ask the user:
.claude/commands/ (project-scoped, shared via git)~/.claude/commands/ (user-scoped, personal across all projects)Then create a .md file:
---
description: Review code for security vulnerabilities
---
Review this code for:
- SQL injection risks
- XSS vulnerabilities
- Authentication issues
See frontmatter.md for complete reference.
---
description: Brief, specific description
argument-hint: [arg1] [arg2]
allowed-tools: Bash(git:*), Read, Edit
model: claude-sonnet-4-5-20250929
---
All arguments: $ARGUMENTS
Fix issue #$ARGUMENTS following coding standards
Positional: $1, $2, etc.
---
argument-hint: [pr-number] [priority]
---
Review PR #$1 with priority $2
Use exclamation mark followed by backtick-quoted bash command (requires allowed-tools: Bash(...))
Syntax: !backtick + bash command + backtick
Example:
---
allowed-tools: Bash(git:*)
---
Status: !backtick git status backtick
Recent: !backtick git log --oneline -5 backtick
Prefix: @
Review @src/utils/auth.js for security issues
Compare @old-version.ts with @new-version.ts
Write specific descriptions:
# ✓ Good
description: Create git commit with Conventional Commits format
# ✗ Bad
description: Git helper
Use argument hints:
argument-hint: [component-name] [type:functional|class]
Scope tools appropriately:
# ✓ Good - specific commands only
allowed-tools: Bash(git add:*), Bash(git commit:*)
# ✗ Bad - too broad
allowed-tools: Bash(*)
Keep commands focused:
# ✓ Good - one clear purpose
Create unit tests for the selected code
# ✗ Bad - multiple unrelated tasks
Create tests, update docs, and refactor code
Include context via bash:
---
allowed-tools: Bash(git:*)
---
Current changes: !backtick git diff HEAD backtick
Create commit message based on changes above
Avoid overly broad permissions:
# ✗ Avoid
allowed-tools: Bash(*), Write, Edit, Read
Don't skip descriptions:
# ✗ Bad - no description
Review this code
Don't mix unrelated tasks:
# ✗ Bad
Run tests, deploy to staging, and update documentation
Don't forget argument hints:
# ✗ Bad - uses $1 but no hint
---
description: Create component
---
Create component: $1
# ✓ Good
---
description: Create component
argument-hint: [component-name]
---
Create component: $1
See examples.md for detailed examples.
---
description: Create conventional commit
allowed-tools: Bash(git:*)
---
Changes: !backtick git diff --cached backtick
Status: !backtick git status --short backtick
Create Conventional Commits format message
---
description: Security-focused code review
---
Review for:
- Input validation
- SQL injection
- XSS prevention
- Auth/authz issues
---
description: Fix GitHub issue
argument-hint: [issue-number] [priority]
---
Fix issue #$1 with priority $2
Follow project coding standards
Prevent Claude from auto-calling via Skill tool:
---
description: Destructive operation
disable-model-invocation: true
---
Use for:
| Feature | Syntax | Example |
|---|---|---|
| All args | $ARGUMENTS | Fix #$ARGUMENTS |
| Positional | $1, $2 | Review PR #$1 |
| Bash | !backtick cmd backtick | !backtick git status backtick |
| File ref | @path | @src/main.ts |
Search, retrieve, and install Agent Skills from the prompts.chat registry using MCP tools. Use when the user asks to find skills, browse skill catalogs, install a skill for Claude, or extend Claude's capabilities with reusable AI agent components.
Activates when the user asks about AI prompts, needs prompt templates, wants to search for prompts, or mentions prompts.chat. Use for discovering, retrieving, and improving prompts.
Expert guidance for Next.js Cache Components and Partial Prerendering (PPR). **PROACTIVE ACTIVATION**: Use this skill automatically when working in Next.js projects that have `cacheComponents: true` in their next.config.ts/next.config.js. When this config is detected, proactively apply Cache Components patterns and best practices to all React Server Component implementations. **DETECTION**: At the start of a session in a Next.js project, check for `cacheComponents: true` in next.config. If enabled, this skill's patterns should guide all component authoring, data fetching, and caching decisions. **USE CASES**: Implementing 'use cache' directive, configuring cache lifetimes with cacheLife(), tagging cached data with cacheTag(), invalidating caches with updateTag()/revalidateTag(), optimizing static vs dynamic content boundaries, debugging cache issues, and reviewing Cache Component implementations.